Subjects -> MEDICAL SCIENCES (Total: 8529 journals)
    - ALLERGOLOGY AND IMMUNOLOGY (216 journals)
    - ANAESTHESIOLOGY (120 journals)
    - CARDIOVASCULAR DISEASES (332 journals)
    - CHIROPRACTIC, HOMEOPATHY, OSTEOPATHY (21 journals)
    - COMMUNICABLE DISEASES, EPIDEMIOLOGY (231 journals)
    - DENTISTRY (292 journals)
    - DERMATOLOGY AND VENEREOLOGY (164 journals)
    - EMERGENCY AND INTENSIVE CRITICAL CARE (120 journals)
    - ENDOCRINOLOGY (150 journals)
    - FORENSIC SCIENCES (41 journals)
    - GASTROENTEROLOGY AND HEPATOLOGY (186 journals)
    - GERONTOLOGY AND GERIATRICS (136 journals)
    - HEMATOLOGY (155 journals)
    - HYPNOSIS (4 journals)
    - INTERNAL MEDICINE (167 journals)
    - LABORATORY AND EXPERIMENTAL MEDICINE (99 journals)
    - MEDICAL GENETICS (58 journals)
    - MEDICAL SCIENCES (2342 journals)
    - NURSES AND NURSING (362 journals)
    - OBSTETRICS AND GYNECOLOGY (207 journals)
    - ONCOLOGY (381 journals)
    - OPHTHALMOLOGY AND OPTOMETRY (138 journals)
    - ORTHOPEDICS AND TRAUMATOLOGY (167 journals)
    - OTORHINOLARYNGOLOGY (82 journals)
    - PATHOLOGY (98 journals)
    - PEDIATRICS (273 journals)
    - PHYSICAL MEDICINE AND REHABILITATION (157 journals)
    - PSYCHIATRY AND NEUROLOGY (822 journals)
    - RADIOLOGY AND NUCLEAR MEDICINE (192 journals)
    - RESPIRATORY DISEASES (103 journals)
    - RHEUMATOLOGY (78 journals)
    - SPORTS MEDICINE (81 journals)
    - SURGERY (401 journals)
    - UROLOGY, NEPHROLOGY AND ANDROLOGY (153 journals)

MEDICAL SCIENCES (2342 journals)                  1 2 3 4 5 6 7 8 | Last

Showing 1 - 200 of 3562 Journals sorted alphabetically
16 de Abril     Open Access   (Followers: 3)
3D Printing in Medicine     Open Access   (Followers: 5)
4 open     Open Access  
AADE in Practice     Hybrid Journal   (Followers: 6)
AAS Open Research     Open Access  
ABCS Health Sciences     Open Access   (Followers: 9)
Abia State University Medical Students' Association Journal     Full-text available via subscription   (Followers: 2)
AboutOpen     Open Access  
ACIMED     Open Access   (Followers: 1)
ACS Medicinal Chemistry Letters     Hybrid Journal   (Followers: 48)
Acta Bio Medica     Full-text available via subscription   (Followers: 2)
Acta Bioethica     Open Access  
Acta Bioquimica Clinica Latinoamericana     Open Access   (Followers: 1)
Acta Científica Estudiantil     Open Access  
Acta Facultatis Medicae Naissensis     Open Access   (Followers: 1)
Acta Herediana     Open Access  
Acta Informatica Medica     Open Access  
Acta Medica (Hradec Králové)     Open Access  
Acta Medica Bulgarica     Open Access  
Acta Medica Colombiana     Open Access   (Followers: 1)
Acta Médica Costarricense     Open Access   (Followers: 2)
Acta Medica Indonesiana     Open Access  
Acta Medica International     Open Access  
Acta medica Lituanica     Open Access  
Acta Medica Marisiensis     Open Access  
Acta Medica Martiniana     Open Access  
Acta Medica Nagasakiensia     Open Access   (Followers: 1)
Acta Medica Peruana     Open Access   (Followers: 2)
Acta Médica Portuguesa     Open Access  
Acta Medica Saliniana     Open Access  
Acta Scientiarum. Health Sciences     Open Access   (Followers: 2)
Acupuncture & Electro-Therapeutics Research     Full-text available via subscription   (Followers: 6)
Acupuncture and Natural Medicine     Open Access  
Addiction Science & Clinical Practice     Open Access   (Followers: 8)
Addictive Behaviors Reports     Open Access   (Followers: 9)
Adıyaman Üniversitesi Sağlık Bilimleri Dergisi / Health Sciences Journal of Adıyaman University     Open Access   (Followers: 1)
Adnan Menderes Üniversitesi Sağlık Bilimleri Fakültesi Dergisi     Open Access   (Followers: 1)
Advanced Biomedical Research     Open Access  
Advanced Health Care Technologies     Open Access   (Followers: 10)
Advanced Science, Engineering and Medicine     Partially Free   (Followers: 9)
Advanced Therapeutics     Hybrid Journal   (Followers: 1)
Advances in Bioscience and Clinical Medicine     Open Access   (Followers: 8)
Advances in Cell and Gene Therapy     Hybrid Journal   (Followers: 2)
Advances in Clinical Chemistry     Full-text available via subscription   (Followers: 27)
Advances in Clinical Radiology     Full-text available via subscription   (Followers: 2)
Advances in Life Course Research     Hybrid Journal   (Followers: 10)
Advances in Lipobiology     Full-text available via subscription   (Followers: 1)
Advances in Medical Education and Practice     Open Access   (Followers: 32)
Advances in Medical Ethics     Open Access   (Followers: 1)
Advances in Medical Research     Open Access   (Followers: 2)
Advances in Medical Sciences     Hybrid Journal   (Followers: 9)
Advances in Medicinal Chemistry     Full-text available via subscription   (Followers: 6)
Advances in Medicine     Open Access   (Followers: 3)
Advances in Microbial Physiology     Full-text available via subscription   (Followers: 5)
Advances in Molecular Oncology     Open Access   (Followers: 2)
Advances in Molecular Toxicology     Full-text available via subscription   (Followers: 7)
Advances in Parkinson's Disease     Open Access   (Followers: 1)
Advances in Phytomedicine     Full-text available via subscription  
Advances in Preventive Medicine     Open Access   (Followers: 6)
Advances in Protein Chemistry and Structural Biology     Full-text available via subscription   (Followers: 20)
Advances in Regenerative Medicine     Open Access   (Followers: 3)
Advances in Skeletal Muscle Function Assessment     Open Access  
Advances in Therapy     Hybrid Journal   (Followers: 5)
Advances in Traditional Medicine     Hybrid Journal   (Followers: 2)
Advances in Veterinary Science and Comparative Medicine     Full-text available via subscription   (Followers: 15)
Advances in Virus Research     Full-text available via subscription   (Followers: 6)
Advances in Wound Care     Hybrid Journal   (Followers: 14)
Aerospace Medicine and Human Performance     Full-text available via subscription   (Followers: 13)
African Health Sciences     Open Access   (Followers: 4)
African Journal of Biomedical Research     Open Access   (Followers: 1)
African Journal of Clinical and Experimental Microbiology     Open Access   (Followers: 4)
African Journal of Laboratory Medicine     Open Access   (Followers: 2)
African Journal of Medical and Health Sciences     Open Access   (Followers: 3)
African Journal of Thoracic and Critical Care Medicine     Open Access  
African Journal of Trauma     Open Access   (Followers: 1)
Afrimedic Journal     Open Access   (Followers: 2)
Aggiornamenti CIO     Hybrid Journal   (Followers: 1)
AIDS Research and Human Retroviruses     Hybrid Journal   (Followers: 9)
AJOB Empirical Bioethics     Hybrid Journal   (Followers: 3)
AJSP: Reviews & Reports     Hybrid Journal  
Aktuelle Ernährungsmedizin     Hybrid Journal   (Followers: 4)
Al-Azhar Assiut Medical Journal     Open Access   (Followers: 2)
Al-Qadisiah Medical Journal     Open Access   (Followers: 1)
Alerta : Revista Científica del Instituto Nacional de Salud     Open Access  
Alexandria Journal of Medicine     Open Access   (Followers: 1)
Allgemeine Homöopathische Zeitung     Hybrid Journal   (Followers: 3)
Alpha Omegan     Full-text available via subscription  
ALTEX : Alternatives to Animal Experimentation     Open Access   (Followers: 2)
Althea Medical Journal     Open Access   (Followers: 2)
American Journal of Biomedical Engineering     Open Access   (Followers: 15)
American Journal of Biomedical Research     Open Access   (Followers: 2)
American Journal of Biomedicine     Full-text available via subscription   (Followers: 7)
American Journal of Chinese Medicine, The     Hybrid Journal   (Followers: 4)
American Journal of Clinical Medicine Research     Open Access   (Followers: 8)
American Journal of Family Therapy     Hybrid Journal   (Followers: 10)
American Journal of Law & Medicine     Full-text available via subscription   (Followers: 12)
American Journal of Lifestyle Medicine     Hybrid Journal   (Followers: 6)
American Journal of Managed Care     Full-text available via subscription   (Followers: 12)
American Journal of Medical Case Reports     Open Access   (Followers: 1)
American Journal of Medical Sciences and Medicine     Open Access   (Followers: 4)
American Journal of Medicine     Hybrid Journal   (Followers: 51)
American Journal of Medicine and Medical Sciences     Open Access   (Followers: 1)
American Journal of Medicine Studies     Open Access   (Followers: 3)
American Journal of Medicine Supplements     Full-text available via subscription   (Followers: 3)
American Journal of the Medical Sciences     Hybrid Journal   (Followers: 12)
American Journal on Addictions     Hybrid Journal   (Followers: 10)
American medical news     Free   (Followers: 3)
American Medical Writers Association Journal     Full-text available via subscription   (Followers: 6)
Amyloid: The Journal of Protein Folding Disorders     Hybrid Journal   (Followers: 5)
Anales de la Facultad de Medicina     Open Access  
Anales de la Facultad de Medicina, Universidad de la República, Uruguay     Open Access  
Anales del Sistema Sanitario de Navarra     Open Access   (Followers: 1)
Analgesia & Resuscitation : Current Research     Hybrid Journal   (Followers: 6)
Anatolian Clinic the Journal of Medical Sciences     Open Access  
Anatomica Medical Journal     Open Access  
Anatomical Science International     Hybrid Journal   (Followers: 3)
Anatomical Sciences Education     Hybrid Journal   (Followers: 2)
Anatomy     Open Access   (Followers: 3)
Anatomy Research International     Open Access   (Followers: 4)
Angewandte Schmerztherapie und Palliativmedizin     Hybrid Journal  
Angiogenesis     Hybrid Journal   (Followers: 3)
Ankara Medical Journal     Open Access   (Followers: 2)
Ankara Üniversitesi Tıp Fakültesi Mecmuası     Open Access  
Annales de Pathologie     Full-text available via subscription  
Annales des Sciences de la Santé     Open Access  
Annales françaises d'Oto-rhino-laryngologie et de Pathologie Cervico-faciale     Full-text available via subscription   (Followers: 3)
Annals of African Medicine     Open Access   (Followers: 2)
Annals of Anatomy - Anatomischer Anzeiger     Hybrid Journal   (Followers: 3)
Annals of Bioanthropology     Open Access   (Followers: 5)
Annals of Biomedical Engineering     Hybrid Journal   (Followers: 19)
Annals of Biomedical Sciences     Full-text available via subscription   (Followers: 4)
Annals of Clinical Hypertension     Open Access  
Annals of Clinical Microbiology and Antimicrobials     Open Access   (Followers: 14)
Annals of Family Medicine     Open Access   (Followers: 15)
Annals of Health Research     Open Access   (Followers: 1)
Annals of Ibadan Postgraduate Medicine     Open Access  
Annals of Medical and Health Sciences Research     Open Access   (Followers: 7)
Annals of Medicine     Hybrid Journal   (Followers: 12)
Annals of Medicine and Surgery     Open Access   (Followers: 7)
Annals of Microbiology     Hybrid Journal   (Followers: 13)
Annals of Musculoskeletal Medicine     Open Access   (Followers: 1)
Annals of Nigerian Medicine     Open Access   (Followers: 1)
Annals of Rehabilitation Medicine     Open Access  
Annals of Saudi Medicine     Open Access  
Annals of the College of Medicine, Mosul     Open Access   (Followers: 1)
Annals of the New York Academy of Sciences     Hybrid Journal   (Followers: 5)
Annals of The Royal College of Surgeons of England     Full-text available via subscription   (Followers: 3)
Annals of the RussianAacademy of Medical Sciences     Open Access  
Annual Reports in Medicinal Chemistry     Full-text available via subscription   (Followers: 7)
Annual Reports on NMR Spectroscopy     Full-text available via subscription   (Followers: 5)
Annual Review of Medicine     Full-text available via subscription   (Followers: 18)
Anthropological Review     Open Access   (Followers: 24)
Anthropologie et santé     Open Access   (Followers: 5)
Antibiotics     Open Access   (Followers: 9)
Antibodies     Open Access   (Followers: 2)
Antibody Reports     Open Access  
Antibody Technology Journal     Open Access   (Followers: 1)
Antibody Therapeutics     Open Access  
Anuradhapura Medical Journal     Open Access  
Anwer Khan Modern Medical College Journal     Open Access   (Followers: 2)
Apmis     Hybrid Journal   (Followers: 2)
Apparence(s)     Open Access   (Followers: 1)
Applied Clinical Informatics     Hybrid Journal   (Followers: 4)
Applied Clinical Research, Clinical Trials and Regulatory Affairs     Hybrid Journal   (Followers: 2)
Applied Medical Informatics     Open Access   (Followers: 14)
Arab Journal of Nephrology and Transplantation     Open Access   (Followers: 1)
Archive of Biomedical Science and Engineering     Open Access   (Followers: 1)
Archive of Clinical Medicine     Open Access   (Followers: 1)
Archive of Community Health     Open Access   (Followers: 1)
Archives Medical Review Journal / Arşiv Kaynak Tarama Dergisi     Open Access  
Archives of Asthma, Allergy and Immunology     Open Access  
Archives of Clinical Hypertension     Open Access   (Followers: 1)
Archives of Medical and Biomedical Research     Open Access   (Followers: 3)
Archives of Medical Laboratory Sciences     Open Access   (Followers: 1)
Archives of Medicine and Health Sciences     Open Access   (Followers: 4)
Archives of Medicine and Surgery     Open Access  
Archives of Organ Transplantation     Open Access   (Followers: 1)
Archives of Preventive Medicine     Open Access   (Followers: 1)
Archives of Pulmonology and Respiratory Care     Open Access   (Followers: 1)
Archives of Renal Diseases and Management     Open Access   (Followers: 1)
Archives of Trauma Research     Open Access   (Followers: 4)
Archivos de Medicina (Manizales)     Open Access  
ArgoSpine News & Journal     Hybrid Journal  
Arquivos Brasileiros de Oftalmologia     Open Access   (Followers: 1)
Arquivos de Ciências da Saúde     Open Access  
Arquivos de Medicina     Open Access  
Ars Medica : Revista de Ciencias Médicas     Open Access  
ARS Medica Tomitana     Open Access   (Followers: 1)
Art Therapy: Journal of the American Art Therapy Association     Hybrid Journal   (Followers: 18)
Arterial Hypertension     Open Access   (Followers: 1)
Artificial Intelligence in Medicine     Hybrid Journal   (Followers: 18)
Artificial Organs     Hybrid Journal   (Followers: 1)
ASHA Leader     Open Access   (Followers: 3)
Asia Pacific Family Medicine Journal     Open Access   (Followers: 2)
Asia Pacific Journal of Clinical Nutrition     Full-text available via subscription   (Followers: 13)
Asia Pacific Journal of Clinical Trials : Nervous System Diseases     Open Access  
Asian Bioethics Review     Full-text available via subscription   (Followers: 3)
Asian Biomedicine     Open Access   (Followers: 2)
Asian Journal of Cell Biology     Open Access   (Followers: 6)
Asian Journal of Health     Open Access   (Followers: 3)

        1 2 3 4 5 6 7 8 | Last

Similar Journals
Journal Cover
Artificial Intelligence in Medicine
Journal Prestige (SJR): 0.766
Citation Impact (citeScore): 3
Number of Followers: 18  
 
  Hybrid Journal Hybrid journal (It can contain Open Access articles)
ISSN (Print) 0933-3657 - ISSN (Online) 1873-2860
Published by Elsevier Homepage  [3203 journals]
  • Computerized decision support and machine learning applications for the
           prevention and treatment of childhood obesity: A systematic review of the
           literature
    • Abstract: Publication date: April 2020Source: Artificial Intelligence in Medicine, Volume 104Author(s): Andreas Triantafyllidis, Eleftheria Polychronidou, Anastasios Alexiadis, Cleilton Lima Rocha, Douglas Nogueira Oliveira, Amanda S. da Silva, Ananda Lima Freire, Crislanio Macedo, Igor Farias Sousa, Eriko Werbet, Elena Arredondo Lillo, Henar González Luengo, Macarena Torrego Ellacuría, Konstantinos Votis, Dimitrios Tzovaras
       
  • Fuzzy support vector machine-based personalizing method to address the
           inter-subject variance problem of physiological signals in a driver
           monitoring system
    • Abstract: Publication date: Available online 21 March 2020Source: Artificial Intelligence in MedicineAuthor(s): Minho Choi, Minseok Seo, Jun Seong Lee, Sang Woo Kim
       
  • Modeling and Processing Up-To-Dateness of Patient Information in
           Probabilistic Therapy Decision Support
    • Abstract: Publication date: Available online 9 March 2020Source: Artificial Intelligence in MedicineAuthor(s): Jan Gaebel, Hans-Georg Wu, Alexander Oeser, Mario A Cypko, Matthaeus Stoehr, Andreas Dietz, Thomas Neumuth, Stefan Franke, Steffen Oeltze-Jafra
       
  • Explainable AI Meets Persuasiveness: Translating Reasoning Results Into
           Behavioral Change Advice
    • Abstract: Publication date: Available online 5 March 2020Source: Artificial Intelligence in MedicineAuthor(s): Mauro Dragoni, Ivan Donadello, Claudio Eccher
       
  • Characterizing the critical features when personalizing antihypertensive
           drugs using spectrum analysis and machine learning methods
    • Abstract: Publication date: Available online 29 February 2020Source: Artificial Intelligence in MedicineAuthor(s): Liu Chunyu, Liu Ran, Zhou Junteng, Wang Miye, Xu Jing, Su Lan, Zuo Yixuan, Zhang Rui, Feng Yizhou, Wang Chen, Yan Hongmei, Zhang Qing
       
  • A neutrosophic-entropy based adaptive thresholding segmentation algorithm:
           A special application in MR images of Parkinson's disease
    • Abstract: Publication date: Available online 28 February 2020Source: Artificial Intelligence in MedicineAuthor(s): Pritpal Singh
       
  • Offline identification of surgical deviations in laparoscopic rectopexy
    • Abstract: Publication date: Available online 27 February 2020Source: Artificial Intelligence in MedicineAuthor(s): Arnaud Huaulmé, Sandrine Voros, Fabian Reche, Jean-Luc Faucheron, Alexandre Moreau-Gaudry, Pierre Jannin
       
  • Detecting Potential Signals of Adverse Drug Events from Prescription Data
    • Abstract: Publication date: Available online 27 February 2020Source: Artificial Intelligence in MedicineAuthor(s): Chen Zhan, Elizabeth Roughead, Lin Liu, Nicole Pratt, Jiuyong Li
       
  • The impact of machine learning on patient care: A systematic review
    • Abstract: Publication date: March 2020Source: Artificial Intelligence in Medicine, Volume 103Author(s): David Ben-Israel, W. Bradley Jacobs, Steve Casha, Stefan Lang, Won Hyung A. Ryu, Madeleine de Lotbiniere-Bassett, David W. Cadotte
       
  • A Novel Deep Mining Model for Effective Knowledge Discovery from Omics
           Data
    • Abstract: Publication date: Available online 24 February 2020Source: Artificial Intelligence in MedicineAuthor(s): Abeer Alzubaidi, Jonathan Tepper, Ahmad lotfi
       
  • Feature Selection based Multivariate Time Series Forecasting: An
           Application to Antibiotic Resistance Outbreaks Prediction
    • Abstract: Publication date: Available online 19 February 2020Source: Artificial Intelligence in MedicineAuthor(s): Fernando Jiménez, José Palma, Gracia Sánchez, David Marín, Francisco Palacios, M.D, Lucía López, M.D
       
  • Toward Development of PreVoid Alerting System for Nocturnal Enuresis
           Patients: A Fuzzy-Based Approach for Determining the Level of Liquid
           Encased in Urinary Bladder
    • Abstract: Publication date: Available online 22 February 2020Source: Artificial Intelligence in MedicineAuthor(s): Mahdi Amina, Javad Yazdani, Stefano Rovetta, Francesco Masulli Preventive and accurate assessment of bladder voiding dysfunctions necessitates measuring the amount of liquid encapsulated within urinary bladder walls in a non-invasive and real-time manner. The real-time monitoring of urine levels helps patients with urological disorders such as Nocturnal Enuresis (NE) by preventing the occurrence of enuresis via a pre-void stage alerting system. Although some advances have been achieved toward developing a non-invasive approach for determining the amount of accumulated urine inside the bladder, there is still a lack of an easy-to-implement technique which is suitable to embed in a wearable pre-warning device. This study aims to develop a machine-learning empowered technique to quantify to what extent an individual's bladder is filled by observing the filling-voiding pattern of a patient over a training period. In this experiment, a pulse-echo sonar element is used to generate ultrasound pulses while the probe surface is positioned perpendicular to the bladder's position. From the reflected echoes, four features which show sufficient sensitiveness and therefore could be modulated noticeably by different levels of liquid encased in the bladder, are extracted. The extracted features are then fed into a novel intelligent decision support system– known as FECOC – which is based on hybridization of fuzzy inference systems (FIS) and error correcting output codes (ECOC). The proposed scheme tends to achieve better results when examined in real case studies.
       
  • Automated Machine Learning: Review of the State-of-the-Art and
           Opportunities for Healthcare
    • Abstract: Publication date: Available online 21 February 2020Source: Artificial Intelligence in MedicineAuthor(s): Jonathan Waring, Charlotta Lindvall, Renato Umeton ObjectiveThis work aims to provide a review of the existing literature in the field of automated machine learning (AutoML) to help healthcare professionals better utilize machine learning models “off-the-shelf” with limited data science expertise. We also identify the potential opportunities and barriers to using AutoML in healthcare, as well as existing applications of AutoML in healthcare.MethodsPublished papers, accompanied with code, describing work in the field of AutoML from both a computer science perspective or a biomedical informatics perspective were reviewed. We also provide a short summary of a series of AutoML challenges hosted by ChaLearn.ResultsA review of 101 papers in the field of AutoML revealed that these automated techniques can match or improve upon expert human performance in certain machine learning tasks, sometimes in a shorter amount of time. The main limitation of AutoML at this point is the ability to get these systems to work efficiently on a large scale, i.e. beyond small- and medium-size retrospective datasets.DiscussionThe utilization of machine learning techniques has the demonstrated potential to improve health outcomes, cut healthcare costs, and advance clinical research. However, most hospitals are not currently deploying machine learning solutions. One reason for this is that health care professionals often lack the machine learning expertise that is necessary to build a successful model, deploy it in production, and integrate it with the clinical workflow. In order to make machine learning techniques easier to apply and to reduce the demand for human experts, automated machine learning (AutoML) has emerged as a growing field that seeks to automatically select, compose, and parametrize machine learning models, so as to achieve optimal performance on a given task and/or dataset.ConclusionWhile there have already been some use cases of AutoML in the healthcare field, more work needs to be done in order for there to be widespread adoption of AutoML in healthcare.
       
  • Reinforcement Learning Application in Diabetes Blood Glucose Control: A
           Systematic Review
    • Abstract: Publication date: Available online 21 February 2020Source: Artificial Intelligence in MedicineAuthor(s): Miguel Tejedor, Ashenafi Zebene Woldaregay, Fred Godtliebsen BackgroundReinforcement learning (RL) is a computational approach to understanding and automating goal-directed learning and decision-making. It is designed for problems which include a learning agent interacting with its environment to achieve a goal. For example, blood glucose (BG) control in diabetes mellitus (DM), where the learning agent and its environment are the controller and the body of the patient respectively. RL algorithms could be used to design a fully closed-loop controller, providing a truly personalized insulin dosage regimen based exclusively on the patient’s own data.ObjectiveIn this review we aim to evaluate state-of-the-art RL approaches to designing BG control algorithms in DM patients, reporting successfully implemented RL algorithms in closed-loop, insulin infusion, decision support and personalized feedback in the context of DM.MethodsAn exhaustive literature search was performed using different online databases, analyzing the literature from 1990 to 2019. In a first stage, a set of selection criteria were established in order to select the most relevant papers according to the title, keywords and abstract. Research questions were established and answered in a second stage, using the information extracted from the articles selected during the preliminary selection.ResultsThe initial search using title, keywords, and abstracts resulted in a total of 404 articles. After removal of duplicates from the record, 347 articles remained. An independent analysis and screening of the records against our inclusion and exclusion criteria defined in Methods section resulted in removal of 296 articles, leaving 51 relevant articles. A full-text assessment was conducted on the remaining relevant articles, which resulted in 29 relevant articles that were critically analyzed. The inter-rater agreement was measured using Cohen Kappa test, and disagreements were resolved through discussion.ConclusionsThe advances in health technologies and mobile devices have facilitated the implementation of RL algorithms for optimal glycemic regulation in diabetes. However, there exists few articles in the literature focused on the application of these algorithms to the BG regulation problem. Moreover, such algorithms are designed for control tasks as BG adjustment and their use have increased recently in the diabetes research area, therefore we foresee RL algorithms will be used more frequently for BG control in the coming years. Furthermore, in the literature there is a lack of focus on aspects that influence BG level such as meal intakes and physical activity (PA), which should be included in the control problem. Finally, there exists a need to perform clinical validation of the algorithms.
       
  • Wearable sensor-based evaluation of psychosocial stress in patients with
           Metabolic Syndrome
    • Abstract: Publication date: Available online 20 February 2020Source: Artificial Intelligence in MedicineAuthor(s): Fatma Patlar Akbulut, Baris Ikitimur, Aydin Akan The prevalence of metabolic disorders has increased rapidly as such they become a major health issue recently. Despite the definition of genetic associations with obesity and cardiovascular diseases, they constitute only a small part of the incidence of disease. Environmental and physiological effects such as stress, behavioral and metabolic disturbances, infections, and nutritional deficiencies have now revealed as contributing factors to develop metabolic diseases. This study presents a multivariate methodology for the modeling of stress on metabolic syndrome (MES) patients. We have developed a supporting system to cope with MES patients’ anxiety and stress by means of several biosignals such as ECG, GSR, body temperature, SPO2, glucose level, and blood pressure that are measured by a wearable device. We employed a neural network model to classify emotions with HRV analysis in the detection of stressor moments. We have accurately recognized the stressful situations using physiological responses to stimuli by utilizing our proposed affective state detection algorithm. We evaluated our system with a dataset of 312 biosignal records from 30 participants and the results showed that our proposed method achieved an average accuracy of 92% and 89% in distinguishing stress level in MES and other groups respectively. Both being the focus of an MES group and others proved to be highly arousing experiences which were significantly reflected in the physiological signal. Exposure to the stress in MES and cardiovascular heart disease patients increases the chronic symptoms. An early stage of comprehensive intervention may reduce the risk of general cardiovascular events in these particular groups. In this context, the use of e-Health applications such as our proposed system facilitates these processes.
       
  • A recurrent neural network approach to predicting hemoglobin trajectories
           in patients with End-Stage Renal Disease
    • Abstract: Publication date: Available online 19 February 2020Source: Artificial Intelligence in MedicineAuthor(s): Benjamin Lobo, Emaad Abdel-Rahman, Donald Brown, Lori Dunn, Brendan Bowman The most severe form of kidney disease, End-Stage Renal Disease (ESRD) is treated with various forms of dialysis – artificial blood cleansing. Dialysis patients suffer many health burdens including high mortality and hospitalization rates, and symptomatic anemia: a low red blood cell count as indicated by a low hemoglobin (Hgb) level. ESRD-induced anemia is treated, with variable patient response, by erythropoiesis stimulating agents (ESAs): expensive injectable medications typically administered during dialysis sessions. The dosing protocol is typically a population level protocol based on original clinical trials, the use of which often results in Hgb cycling. This cycling phenomenon occurs primarily due to the mismatch in the time between dosing decisions and the time it takes for the effects of a dosing change to be fully realized. In this paper we develop a recurrent neural network approach that uses historic data together with future ESA and iron dosing data to predict the 1, 2, and 3 month Hgb levels of patients with ESRD-induced anemia. The results of extensive experimentation indicate that this approach generates predictions that are clinically relevant: the mean absolute error of the predictions is comparable to estimates of the intra-individual variability of the laboratory test for Hgb.
       
  • Multimodal Data Analysis of Epileptic EEG and rs-fMRI via Deep Learning
           and Edge Computing
    • Abstract: Publication date: Available online 19 February 2020Source: Artificial Intelligence in MedicineAuthor(s): Mohammad-Parsa Hosseini, Tuyen X. Tran, Dario Pompili, Kost Elisevich, Hamid Soltanian-Zadeh Background and ObjectiveMultimodal data analysis and large-scale computational capability is entering medicine in an accelerative fashion and has begun to influence investigational work in a variety of disciplines. It is also informing us of therapeutic interventions that will come about with such development. Epilepsy is a chronic brain disorder in which functional changes may precede structural ones and which may be detectable using existing modalities.MethodsFunctional connectivity analysis using electroencephalography (EEG) and resting state-functional magnetic resonance imaging (rs-fMRI) has provided such meaningful input in cases of epilepsy. By leveraging the potential of autonomic edge computing in epilepsy, we develop and deploy both noninvasive and invasive methods for monitoring, evaluation, and regulation of the epileptic brain. First, an autonomic edge computing framework is proposed for the processing of big data as part of a decision support system for surgical candidacy. Second, a multimodal data analysis using independently acquired EEG and rs-fMRI is presented for estimation and prediction of the epileptogenic network. Third, an unsupervised feature extraction model is developed for EEG analysis and seizure prediction based on a Convolutional deep learning (CNN) structure for distinguishing preictal (pre-seizure) state from non-preictal periods by support vector machine (SVM) classifier.ResultsExperimental and simulation results from actual patient data validate the effectiveness of the proposed methods.ConclusionsThe combination of rs-fMRI and EEG/iEEG can reveal more information about dynamic functional connectivity. However, simultaneous fMRI and EEG data acquisition present challenges. We have proposed system models for leveraging and processing independently acquired fMRI and EEG data.
       
  • Early detection of sepsis utilizing deep learning on electronic health
           record event sequences
    • Abstract: Publication date: Available online 19 February 2020Source: Artificial Intelligence in MedicineAuthor(s): Simon Meyer Lauritsen, Mads Ellersgaard Kalør, Emil Lund Kongsgaard, Katrine Meyer Lauritsen, Marianne Johansson Jørgensen, Jeppe Lange, Bo Thiesson Background: The timeliness of detection of a sepsis incidence in progress is a crucial factor in the outcome for the patient. Machine learning models built from data in electronic health records can be used as an effective tool for improving this timeliness, but so far, the potential for clinical implementations has been largely limited to studies in intensive care units. This study will employ a richer data set that will expand the applicability of these models beyond intensive care units. Furthermore, we will circumvent several important limitations that have been found in the literature: 1) Model evaluations neglect the clinical consequences of a decision to start, or not start, an intervention for sepsis. 2) Models are evaluated shortly before sepsis onset without considering interventions already initiated. 3) Machine learning models are built on a restricted set of clinical parameters, which are not necessarily measured in all departments. 4) Model performance is limited by current knowledge of sepsis, as feature interactions and time dependencies are hard-coded into the model. Methods: In this study, we present a model to overcome these shortcomings using a deep learning approach on a diverse multicenter data set. We used retrospective data from multiple Danish hospitals over a seven-year period. Our sepsis detection system is constructed as a combination of a convolutional neural network and a long short-term memory network. We assess model quality by standard concepts of accuracy as well as clinical usefulness, and we suggest a retrospective assessment of interventions by looking at intravenous antibiotics and blood cultures preceding the prediction time. Results: Results show performance ranging from AUROC 0.856 (3 hours before sepsis onset) to AUROC 0.756 (24 hours before sepsis onset). Evaluating the clinical utility of the model, we find that a large proportion of septic patients did not receive antibiotic treatment or blood culture at the time of the sepsis prediction, and the model could, therefore, facilitate such interventions at an earlier point in time. Conclusion: We present a deep learning system for early detection of sepsis that can learn characteristics of the key factors and interactions from the raw event sequence data itself, without relying on a labor-intensive feature extraction work. Our system outperforms baseline models, such as gradient boosting, which rely on specific data elements and therefore suffer from many missing values in our dataset.
       
  • Efficient Treatment of Outliers and Class Imbalance for Diabetes
           Prediction
    • Abstract: Publication date: Available online 10 February 2020Source: Artificial Intelligence in MedicineAuthor(s): Nonso Nnamoko, Ioannis Korkontzelos Learning from outliers and imbalanced data remains one of the major difficulties for machine learning classifiers. Among the numerous techniques dedicated to tackle this problem, data preprocessing solutions are known to be efficient and easy to implement. In this paper, we propose a selective data preprocessing approach that embeds knowledge of the outlier instances into artificially generated subset to achieve an even distribution. The synthetic minority oversampling technique (smote) was used to balance the training data by introducing artificial minority instances. However, this was not before the outliers were identified and oversampled (irrespective of class). The aim is to balance the training dataset while controlling the effect of outliers. The experiments prove that such selective oversampling empowers smote, ultimately leading to improved classification performance.Graphical abstractGraphical abstract for this article
       
  • Real-world data medical knowledge graph: construction and applications
    • Abstract: Publication date: Available online 6 February 2020Source: Artificial Intelligence in MedicineAuthor(s): Linfeng Li, Peng Wang, Jun Yan, Yao Wang, Simin Li, Jinpeng Jiang, Zhe Sun, Buzhou Tang, Tsung-Hui Chang, Shenghui Wang, Yuting Liu ObjectiveMedical knowledge graph (KG) is attracting attention from both academic and healthcare industry due to its power in intelligent healthcare applications. In this paper, we introduce a systematic approach to build medical KG from electronic medical records (EMRs) with evaluation by both technical experiments and end to end application examples.Materials and MethodsThe original data set contains 16,217,270 de-identified clinical visit data of 3,767,198 patients. The KG construction procedure includes 8 steps, which are data preparation, entity recognition, entity normalization, relation extraction, property calculation, graph cleaning, related-entity ranking, and graph embedding respectively. We propose a novel quadruplet structure to represent medical knowledge instead of the classical triplet in KG. A novel related-entity ranking function considering probability, specificity and reliability (PSR) is proposed. Besides, probabilistic translation on hyperplanes (PrTransH) algorithm is used to learn graph embedding for the generated KG.ResultsA medical KG with 9 entity types including disease, symptom, etc. was established, which contains 22,508 entities and 579,094 quadruplets. Compared with term frequency - inverse document frequency (TF/IDF) method, the normalized discounted cumulative gain (NDCG@10) increased from 0.799 to 0.906 with the proposed ranking function. The embedding representation for all entities and relations were learned, which are proven to be effective using disease clustering.ConclusionThe established systematic procedure can efficiently construct a high-quality medical KG from large-scale EMRs. The proposed ranking function PSR achieves the best performance under all relations, and the disease clustering result validates the efficacy of the learned embedding vector as entity’s semantic representation. Moreover, the obtained KG finds many successful applications due to its statistics-based quadruplet.where Ncomin is a minimum co-occurrence number and R is the basic reliability value. The reliability value can measure how reliable is the relationship between Si and Oij. The reason for the definition is the higher value of Nco(Si, Oij), the relationship is more reliable. However, the reliability values of the two relationships should not have a big difference if both of their co-occurrence numbers are very big. In our study, we finally set Ncomin = 10 and R = 1 after some experiments. For instance, if co-occurrence numbers of three relationships are 1, 100 and 10000, their reliability values are 1, 2.96 and 5 respectively.
       
  • A multicenter random forest model for effective prognosis prediction in
           collaborative clinical research network
    • Abstract: Publication date: Available online 5 February 2020Source: Artificial Intelligence in MedicineAuthor(s): Jin Li, Yu Tian, Yan Zhu, Tianshu Zhou, Jun Li, Kefeng Ding, Jingsong Li BackgroundThe accuracy of a prognostic prediction model has become an essential aspect of the quality and reliability of the health-related decisions made by clinicians in modern medicine. Unfortunately, individual institutions often lack sufficient samples, which might not provide sufficient statistical power for models. One mitigation is to expand data collection from a single institution to multiple centers to collectively increase the sample size. However, sharing sensitive biomedical data for research involves complicated issues. Machine learning models such as random forests (RF), though they are commonly used and achieve good performances for prognostic prediction, usually suffer worse performance under multicenter privacy-preserving data mining scenarios compared to a centrally trained version.Methods and materialsIn this study, a multicenter random forest prognosis prediction model is proposed that enables federated clinical data mining from horizontally partitioned datasets. By using a novel data enhancement approach based on a differentially private generative adversarial network customized to clinical prognosis data, the proposed model is able to provide a multicenter RF model with performances on par with—or even better than—centrally trained RF but without the need to aggregate the raw data. Moreover, our model also incorporates an importance ranking step designed for feature selection without sharing patient-level information.ResultThe proposed model was evaluated on colorectal cancer datasets from the US and China. Two groups of datasets with different levels of heterogeneity within the collaborative research network were selected. First, we compare the performance of the distributed random forest model under different privacy parameters with different percentages of enhancement datasets and validate the effectiveness and plausibility of our approach. Then, we compare the discrimination and calibration ability of the proposed multicenter random forest with a centrally trained random forest model and other tree-based classifiers as well as some commonly used machine learning methods. The results show that the proposed model can provide better prediction performance in terms of discrimination and calibration ability than the centrally trained RF model or the other candidate models while following the privacy-preserving rules in both groups. Additionally, good discrimination and calibration ability are shown on the simplified model based on the feature importance ranking in the proposed approach.ConclusionThe proposed random forest model exhibits ideal prediction capability using multicenter clinical data and overcomes the performance limitation arising from privacy guarantees. It can also provide feature importance ranking across institutions without pooling the data at a central site. This study offers a practical solution for building a prognosis prediction model in the collaborative clinical research network and solves practical issues in real-world applications of medical artificial intelligence.
       
  • Automatic computation of mandibular indices in dental panoramic
           radiographs for early osteoporosis detection
    • Abstract: Publication date: Available online 5 February 2020Source: Artificial Intelligence in MedicineAuthor(s): Ignacio Aliaga, Vicente Vera, María Vera, Enrique García, María Pedrera, Gonzalo Pajares AIMA new automatic method for detecting specific points and lines (straight and curves) in dental panoramic radiographies (orthopantomographies) is proposed, where the human knowledge is mapped to the automatic system. The goal is to compute relevant mandibular indices (Mandibular Cortical Width, Panoramic Mandibular Index, Mandibular Ratio, Mandibular Cortical Index) in order to detect the thinning and deterioration of the mandibular bone. Data can be stored for posterior massive analysis.METHODSPanoramic radiographies are intrinsically complex, including: artificial structures, unclear limits in bony structures, jawbones with irregular curvatures and intensity levels, irregular shapes and borders of the mental foramen, irregular teeth alignments or missing dental pieces. An intelligent sequence of linked imaging segmentation processes is proposed to cope with the above situations towards the design of the automatic segmentation, making the following contributions: (i) Fuzzy K-means classification for identifying artificial structures; (ii) adjust a tangent line to the lower border of the lower jawbone (lower cortex), based on texture analysis, grey scale dilation, binarization and labelling; (iii) identification of the mental foramen region and its centre, based on multi-thresholding, binarization, morphological operations and labelling; (iv) tracing a perpendicular line to the tangent passing through the centre of the mental foramen region and two parallel lines to the tangent, passing through borders on the mental foramen intersected by the perpendicular; (v) following the perpendicular line, a sweep is made moving up the tangent for detecting accumulation of binary points after applying adaptive filtering; (vi) detection of the lower mandible alveolar crest line based on the identification of inter-teeth gaps by saliency and interest points feature description.RESULTSThe performance of the proposed approach was quantitatively compared against the criteria of expert dentists, verifying also its validity with statistical studies based on the analysis of deterioration of bone structures with different levels of osteoporosis. All indices are computed inside two regions of interest, which tolerate flexibility in sizes and locations, making this process robust enough.CONCLUSIONSThe proposed approach provides an automatic procedure able to process with efficiency and reliability panoramic X-Ray images for early osteoporosis detection.
       
  • Random Forest Enhancement using Improved Artificial Fish Swarm for the
           Medial Knee Contact Force Prediction
    • Abstract: Publication date: Available online 3 February 2020Source: Artificial Intelligence in MedicineAuthor(s): Yean Zhu, Weiyi XU, Guoliang Luo, Haolun Wang, Jingjing Yang, Wei Lu Knee Contact Force (KCF) is an important factor to evaluate the knee joint function for the patients with knee joint impairment. However, the KCF measurement based on the instrumented prosthetic implants or inverse dynamics analysis is limited due to the invasive, expensive price and time consumption. In this work, we propose a KCF prediction method by integrating the artificial fish swarm and the random forest algorithm. First, we train a random forest to learn the nonlinear relation between gait parameters (input) and contact pressures (output) based on a dataset of three patients instrumented with knee replacement. Then, we use the improved artificial fish group algorithm to optimize the main parameters of the random forest based KCF prediction model. The extensive experiments verify that our method can predict the medial knee contact force both before and after the intervention of gait patterns, and the performance outperforms the classical multi-body dynamics analysis and artificial neural network model.
       
  • An Incremental Explanation of Inference in Bayesian Networks for
           Increasing Model Trustworthiness and Supporting Clinical Decision Making
    • Abstract: Publication date: Available online 31 January 2020Source: Artificial Intelligence in MedicineAuthor(s): Evangelia Kyrimi, Somayyeh Mossadegh, Nigel Tai, William Marsh Various AI models are increasingly being considered as part of clinical decision-support tools. However, the trustworthiness of such models is rarely considered. Clinicians are more likely to use a model if they can understand and trust its predictions. Key to this is if its underlying reasoning can be explained. A Bayesian network (BN) model has the advantage that it is not a black-box and its reasoning can be explained. In this paper, we propose an incremental explanation of inference that can be applied to ‘hybrid’ BNs, i.e. those that contain both discrete and continuous nodes. The key questions that we answer are: (1) which important evidence supports or contradicts the prediction, and (2) through which intermediate variables does the information flow. The explanation is illustrated using a real clinical case study. A small evaluation study is also conducted.
       
  • Mixed-Integer Optimization Approach to Learning Association Rules for
           Unplanned ICU Transfer
    • Abstract: Publication date: Available online 30 January 2020Source: Artificial Intelligence in MedicineAuthor(s): Chun-An Chou, Qingtao Cao, Shao-Jen Weng, Che-Hung Tsai After admission to emergency department (ED), patients with critical illnesses are transferred to intensive care unit (ICU) due to unexpected clinical deterioration occurrence. Identifying such unplanned ICU transfers is urgently needed for medical physicians to achieve two-fold goals: improving critical care quality and preventing mortality. A priority task is to understand the crucial rationale behind diagnosis results of individual patients during stay in ED, which helps prepare for an early transfer to ICU. Most existing prediction studies were based on univariate analysis or multiple logistic regression to provide one-size-fit-all results. However, patient condition varying from case to case may not be accurately examined by such a simplistic judgment. In this study, we present a new decision tool using a mathematical optimization approach aiming to automatically discover rules associating diagnostic features with high-risk outcome (i.e., unplanned transfers) in different deterioration scenarios. We consider four mutually exclusive patient subgroups based on the principal reasons of ED visits: infections, cardiovascular/respiratory diseases, gastrointestinal diseases, and neurological/other diseases at a suburban teaching hospital. The analysis results demonstrate significant rules associated with unplanned transfer outcome for each subgroups and also show comparable prediction accuracy (>70%) compared to state-of-the-art machine learning methods while providing easy-to-interpret symptom-outcome information.
       
  • Retraction notice to “Diagnosis Labeling with Disease-Specific
           Characteristics Mining” [Artif. Intell. Med. 90 (2018) 25–33]
    • Abstract: Publication date: Available online 27 January 2020Source: Artificial Intelligence in MedicineAuthor(s): Jun Guo, Xuan Yuan, Xia Zheng, Xu Pengfei, Yun Xiao, Baoying Liu
       
  • Batch Mode Active Learning on the Riemannian Manifold for Automated
           Scoring of Nuclear Pleomorphism in Breast Cancer
    • Abstract: Publication date: Available online 25 January 2020Source: Artificial Intelligence in MedicineAuthor(s): Asha Das, Madhu S. Nair, David Peter S. Breast cancer is the most prevalent invasive type of cancer among women. The mortality rate of the disease can be reduced considerably through timely prognosis and felicitous treatment planning, by utilizing the computer aided detection and diagnosis techniques. With the advent of whole slide image (WSI) scanners for digitizing the histopathological tissue samples, there is a drastic increase in the availability of digital histopathological images. However, these samples are often unlabeled and hence they need labeling to be done through manual annotations by domain experts and experienced pathologists. But this annotation process required for acquiring high quality large labeled training set for nuclear atypia scoring is a tedious, expensive and time consuming job. Active learning techniques have achieved widespread acceptance in reducing this human effort in annotating the data samples. In this paper, we explore the possibilities of active learning on nuclear pleomorphism scoring over a non-Euclidean framework, the Riemannian manifold. Active learning technique adopted for the cancer grading is in the batch-mode framework, that adaptively identifies the apt batch size along with the batch of instances to be queried, following a submodular optimization framework. Samples for annotation are selected considering the diversity and redundancy between the pair of samples, based on the kernelized Riemannian distance measures such as log-Euclidean metrics and the two Bregman divergences - Stein and Jeffrey divergences. Results of the adaptive Batch Mode Active Learning on the Riemannian metric show a superior performance when compared with the state-of-the-art techniques for breast cancer nuclear pleomorphism scoring, as it makes use of the information from the unlabeled samples.
       
  • Classification of glomerular hypercellularity using convolutional features
           and support vector machine
    • Abstract: Publication date: Available online 25 January 2020Source: Artificial Intelligence in MedicineAuthor(s): Paulo Chagas, Luiz Souza, Ikaro Araújo, Nayze Aldeman, Angelo Duarte, Michele Angelo, Washington LC dos-Santos, Luciano Oliveira Glomeruli are histological structures of the kidney cortex formed by interwoven blood capillaries, and are responsible for blood filtration. Glomerular lesions impair kidney filtration capability, leading to protein loss and metabolic waste retention. An example of lesion is the glomerular hypercellularity, which is characterized by an increase in the number of cell nuclei in different areas of the glomeruli. Glomerular hypercellularity is a frequent lesion present in different kidney diseases. Automatic detection of glomerular hypercellularity would accelerate the screening of scanned histological slides for the lesion, enhancing clinical diagnosis. Having this in mind, we propose a new approach for classification of hypercellularity in human kidney images. Our proposed method introduces a novel architecture of a convolutional neural network (CNN) along with a support vector machine, achieving near perfect average results on FIOCRUZ data set in a binary classification (lesion or normal). Additionally, classification of hypercellularity sub-lesions was also evaluated, considering mesangial, endocapilar and both lesions, reaching an average accuracy of 82%. Either in binary task or in the multi-classification one, our proposed method outperformed Xception, ResNet50 and InceptionV3 networks, as well as a traditional handcrafted-based method. To the best of our knowledge, this is the first study on deep learning over a data set of glomerular hypercellularity images of human kidney.
       
  • Quantitative knowledge presentation models of Traditional Chinese Medicine
           (TCM): A review
    • Abstract: Publication date: Available online 24 January 2020Source: Artificial Intelligence in MedicineAuthor(s): Xiaoli Chu, Bingzhen Sun, Qingchun Huang, Shouping Peng, Yingyan Zhou, Yan Zhang Modern computer technology sheds light on new ways of innovating Traditional Chinese Medicine (TCM). One method that gets increasing attention is the quantitative research method, which makes use of data mining and artificial intelligence technology as well as the mathematical principles in the research on rationales, academic viewpoints of famous doctors of TCM, dialectical treatment by TCM, clinical technology of TCM, the patterns of TCM prescriptions, clinical curative effects of TCM and other aspects. This paper reviews the methods, means, progress and achievements of quantitative research on TCM. In the core database of the Web of Science, "Traditional Chinese Medicine", "Computational Science" and "Mathematical Computational Biology" are selected as the main retrieval fields, and the retrieval time interval from 1999 to 2019 is used to collect relevant literature. It is found that researchers from China Academy of Chinese Medical Sciences, Zhejiang University, Chinese Academy of Sciences and other institutes have opened up new methods of research on TCM since 2009, with quantitative methods and knowledge presentation models. The adopted tools mainly consist of text mining, knowledge discovery, technologies of the TCM database, data mining and drug discovery through TCM calculation, etc. In the future, research on quantitative models of TCM will focus on solving the heterogeneity and incompleteness of big data of TCM, establishing standardized treatment systems, and promoting the development of modernization and internationalization of TCM.
       
  • Prognostic Factors of Rapid Symptoms Progression in Patients with Newly
           Diagnosed Parkinson’s Disease
    • Abstract: Publication date: Available online 21 January 2020Source: Artificial Intelligence in MedicineAuthor(s): Kostas M. Tsiouris, Spiros Konitsiotis, Dimitrios D. Koutsouris, Dimitrios I. Fotiadis Tracking symptoms progression in the early stages of Parkinson’s disease (PD) is a laborious endeavor as the disease can be expressed with vastly different phenotypes, forcing clinicians to follow a multi-parametric approach in patient evaluation, looking for not only motor symptomatology but also non-motor complications, including cognitive decline, sleep problems and mood disturbances. Being neurodegenerative in nature, PD is expected to inflict a continuous degradation in patients’ condition over time. The rate of symptoms progression, however, is found to be even more chaotic than the vastly different phenotypes that can be expressed in the initial stages of PD. In this work, an analysis of baseline PD characteristics is performed using machine learning techniques, to identify prognostic factors for early rapid progression of PD symptoms. Using open data from the Parkinson’s Progression Markers Initiative (PPMI) study, an extensive set of baseline patient evaluation outcomes is examined to isolate determinants of rapid progression within the first two and four years of PD. The rate of symptoms progression is estimated by tracking the change of the Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS‐UPDRS) total score over the corresponding follow-up period. Patients are ranked according to their progression rates and those who expressed the highest rates of MDS-UPDRS total score increase per year of follow-up period are assigned into the rapid progression class, using 5- and 10-quantiles partition. Classification performance against the rapid progression class was evaluated in a per quantile partition analysis scheme and in quantile-independent approach, respectively. The results shown a more accurate patient discrimination with quantile partitioning, however, a much more compact subset of baseline factors is extracted in the latter, making a more suitable for actual interventions in practice. Classification accuracy improved in all cases when using the longer 4-year follow-up period to estimate PD progression, suggesting that a prolonged patient evaluation can provide better outcomes in identifying rapid progression phenotype. Non-motor symptoms are found to be the main determinants of rapid symptoms progression in both follow-up periods, with autonomic dysfunction, mood impairment, anxiety, REM sleep behavior disorders, cognitive decline and memory impairment being alarming signs at baseline evaluation, along with rigidity symptoms, certain laboratory blood test results and genetic mutations.
       
  • Comprehensive electrocardiographic diagnosis based on deep learning
    • Abstract: Publication date: Available online 20 January 2020Source: Artificial Intelligence in MedicineAuthor(s): Oh Shu Lih, V Jahmunah, Tan Ru San, Edward J Ciaccio, Toshitaka Yamakawa, Masayuki Tanabe, Makiko Kobayashi, Oliver Faust, U Rajendra Acharya Cardiovascular disease (CVD) is the leading cause of death worldwide, and coronary artery disease (CAD) is a major contributor. Early-stage CAD can progress if undiagnosed and left untreated, leading to myocardial infarction (MI) that may induce irreversible heart muscle damage, resulting in heart chamber remodeling and eventual congestive heart failure (CHF). Electrocardiography (ECG) signals can be useful to detect established MI, and may also be helpful for early diagnosis of CAD. For the latter especially, the ECG perturbations can be subtle and potentially misclassified on manual interpretation and/or when analyzed by traditional algorithms found in ECG instrumentation. For automated diagnostic systems (ADS), deep learning techniques are favored over conventional machine learning techniques, due to the automatic feature extraction and selection processes involved. This paper highlights various deep learning algorithms exploited for the classification of ECG signals into CAD, MI, and CHF conditions. The Convolutional Neural Network (CNN), followed by combined CNN and Long Short-Term Memory (LSTM) models, appear to be the most useful architectures for classification. A 16-layer LSTM model was developed in our study and validated using 10-fold cross validation. A classification accuracy of 98.5% was achieved. Our proposed model has the potential to be a useful diagnostic tool in hospitals for the classification of abnormal ECG signals.
       
  • Scalogram based Prediction Model for Respiratory disorders using Optimized
           Convolutional Neural Networks
    • Abstract: Publication date: Available online 20 January 2020Source: Artificial Intelligence in MedicineAuthor(s): S. Jayalakshmy, Gnanou Florence Sudha Auscultation of the lung is a conventional technique used for diagnosing chronic obstructive pulmonary diseases (COPDs) and lower respiratory infections and disorders in patients. In most of the earlier works, wavelet transforms or spectrograms have been used to analyze the lung sounds. However, an accurate prediction model for respiratory disorders has not been developed so far. In this paper, a pre-trained optimized Alexnet Convolutional Neural Network (CNN) architecture is proposed for predicting respiratory disorders. The proposed approach models the segmented respiratory sound signal into Bump and Morse scalograms from several intrinsic mode functions (IMFs) using empirical mode decomposition (EMD) method. From the extracted intrinsic mode functions, the percentage energy calculated for each wavelet coefficient in the form of scalograms are computed. Subsequently, these scalograms are given as input to the pre-trained optimized CNN model for training and testing. Stochastic gradient descent with momentum (SGDM) and adaptive data momentum (ADAM) optimization algorithms were examined to check the prediction accuracy on the dataset comprising of four classes of lung sounds, normal, crackles (coarse and fine), wheezes (monophonic & polyphonic) and low-pitched wheezes (Rhonchi). On comparison to the baseline method of standard Bump and Morse wavelet transform approach which produced 79.04% and 81.27% validation accuracy, an improved accuracy of 83.78% is achieved by the virtue of scalogram representation of various IMFs of EMD. Hence, the proposed approach achieves significant performance improvement in accuracy compared to the existing state-of- the-art techniques in literature.
       
  • Measuring the effects of confounders in medical supervised classification
           problems: the Confounding Index (CI)
    • Abstract: Publication date: Available online 13 January 2020Source: Artificial Intelligence in MedicineAuthor(s): Elisa Ferrari, Alessandra Retico, Davide Bacciu Over the years, there has been growing interest in using Machine Learning techniques for biomedical data processing. When tackling these tasks, one needs to bear in mind that biomedical data depends on a variety of characteristics, such as demographic aspects (age, gender, etc) or the acquisition technology, which might be unrelated with the target of the analysis. In supervised tasks, failing to match the ground truth targets with respect to such characteristics, called confounders, may lead to very misleading estimates of the predictive performance. Many strategies have been proposed to handle confounders, ranging from data selection, to normalization techniques, up to the use of training algorithm for learning with imbalanced data. However, all these solutions require the confounders to be known a priori. To this aim, we introduce a novel index that is able to measure the confounding effect of a data attribute in a bias-agnostic way. This index can be used to quantitatively compare the confounding effects of different variables and to inform correction methods such as normalization procedures or ad-hoc-prepared learning algorithms. The effectiveness of this index is validated on both simulated data and real-world neuroimaging data.
       
  • ADHD classification by dual subspace learning using resting-state
           functional connectivity
    • Abstract: Publication date: Available online 13 January 2020Source: Artificial Intelligence in MedicineAuthor(s): Ying Chen, Yibin Tang, Chun Wang, Xiaofeng Liu, Li Zhao, Zhishun Wang As one of the most common neurobehavioral diseases in school-age children, Attention Deficit Hyperactivity Disorder (ADHD) has been increasingly studied in recent years. But it is still a challenge problem to accurately identify ADHD patients from healthy persons. To address this issue, we propose a dual subspace classification algorithm by using individual resting-state Functional Connectivity (FC). In detail, two subspaces respectively containing ADHD and healthy control features, called as dual subspaces, are learned with several subspace measures, wherein a modified graph embedding measure is employed to enhance the intra-class relationship of these features. Therefore, given a subject (used as test data) with its FCs, the basic classification principle is to compare its projected component energy of FCs on each subspace and then predict the ADHD or control label according to the subspace with larger energy. However, this principle in practice works with low efficiency, since the dual subspaces are unstably obtained from ADHD databases of small size. Thereby, we present an ADHD classification framework by a binary hypothesis testing of test data. Here, the FCs of test data with its ADHD or control label hypothesis are employed in the discriminative FC selection of training data to promote the stability of dual subspaces. For each hypothesis, the dual subspaces are learned from the selected FCs of training data. The total projected energy of these FCs is also calculated on the subspaces. Sequentially, the energy comparison is carried out under the binary hypotheses. The ADHD or control label is finally predicted for test data with the hypothesis of larger total energy. In the experiments on ADHD-200 dataset, our method achieves a significant classification performance compared with several state-of-the-art machine learning and deep learning methods, where our accuracy is about 90% for most of ADHD databases in the leave-one-out cross-validation test.
       
  • Seven Pillars of Precision Digital Health and Medicine
    • Abstract: Publication date: Available online 11 January 2020Source: Artificial Intelligence in MedicineAuthor(s): Arash Shaban-Nejad, Martin Michalowski, Niels Peek, John S. Brownstein, David L. Buckeridge
       
  • Comprenhensive analysis of rule formalisms to represent clinical
           guidelines: Selection criteria and case study on antibiotic clinical
           guidelines
    • Abstract: Publication date: Available online 9 January 2020Source: Artificial Intelligence in MedicineAuthor(s): Natalia Iglesias, Jose M. Juarez, Manuel Campos BackgroundThe over-use of antibiotics in clinical domains is causing an alarming increase in bacterial resistance, thus endangering their effectiveness as regards the treatment of highly recurring severe infectious diseases. Whilst Clinical Guidelines (CGs) focus on the correct prescription of antibiotics in a narrative form, Clinical Decision Support Systems (CDSS) operationalize the knowledge contained in CGs in the form of rules at the point of care. Despite the efforts made to computerize CGs, there is still a gap between CGs and the myriad of rule technologies (based on different logic formalisms) that are available to implement CDSSs in real clinical settings.ObjectiveTo helpCDSS designers to determine the most suitable rule-based technology (medical-oriented rules, production rules and semantic web rules) with which to model knowledge from CGs for the prescription of antibiotics. We propose a framework of criteria for this purpose that is extensible to more generic CGs.Materials and methodsOur proposal is based on the identification of core technical requirements extracted from both literature and the analysis of CGs for antibiotics, establishing three dimensions for analysis: language expressivity, interoperability and industrial aspects. We present a case study regarding the John Hopkins Hospital (JHH) Antibiotic Guidelines for Urinary Tract Infection (UTI), a highly recurring hospital acquired infection. We have adopted our framework of criteria in order to analyse and implement these CGs using various rule technologies: HL7 Arden Syntax, general-purpose Production Rules System (Drools), HL7 standard Rule Interchange Format (RIF), Semantic Web Rule Language (SWRL) and SParql Inference Notation (SPIN) rule extensions (implementing our own ontology for UTI).ResultsWe have identified the main criteria required to attain a maintainable and cost-affordable computable knowledge representation for CGs. We have represented the JHH UTI CGs knowledge in a total of 12 Arden Syntax MLMs, 81 Drools rules and 154 ontology classes, properties and individuals. Our experiments confirm the relevance of the proposed set of criteria and show the level of compliance of the different rule technologies with the JHH UTI CGs knowledge representation.ConclusionsThe proposed framework of criteria may help clinical institutions to select the most suitable rule technology for the representation of CGs in general, and for the antibiotic prescription domain in particular, depicting the main aspects that lead to Computer Interpretable Guidelines (CIGs), such as Logic expressivity (Open/Closed World Assumption, Negation-As-Failure), Temporal Reasoning and Interoperability with existing HIS and clinical workflow. Future work will focus on providing clinicians with suggestions regarding new potential steps for CGs, considering process mining approaches and CGs Process Workflows, the use of HL7 FHIR for HIS interoperability and the representation of Knowledge-as- a-Service (KaaS).
       
  • Optimisation and control of the supply of blood bags in hemotherapic
           centres via Markov Decision Process with discounted arrival rate
    • Abstract: Publication date: Available online 8 January 2020Source: Artificial Intelligence in MedicineAuthor(s): Henrique L.F. Soares, Edilson F. Arruda, Laura Bahiense, Daniel Gartner, Luiz Amorim Filho Running a cost-effective human blood transfusion supply chain challenges decision makers in blood services world-wide. In this paper, we develop a Markov decision process with the objective of minimising the overall costs of internal and external collections, storing, producing and disposing of blood bags, whilst explicitly considering the probability that a donated blog bag will perish before demanded. The model finds an optimal policy to collect additional bags based on the number of bags in stock rather than using information about the age of the oldest item. Using data from the literature, we validate our model and carry out a case study based on data from a large blood supplier in South America. The study helped achieve an overall increase of 4.5% in blood donations in one year.
       
  • An effective approach for CT lung segmentation using mask region-based
           convolutional neural networks
    • Abstract: Publication date: Available online 8 January 2020Source: Artificial Intelligence in MedicineAuthor(s): Qinhua Hu, Luís Fabrício de F. Souza, Gabriel Bandeira Holanda, Shara S.A. Alves, Francisco Hércules dos S. Silva, Tao Han, Pedro P. Rebouças Filho Computer vision systems have numerous tools to assist in various medical fields, notably in image diagnosis. Computed tomography (CT) is the principal imaging method used to assist in the diagnosis of diseases such as bone fractures, lung cancer, heart disease, and emphysema, among others. Lung cancer is one of the four main causes of death in the world. The lung regions in the CT images are marked manually by a specialist as this initial step is a significant challenge for computer vision techniques. Once defined, the lung regions are segmented for clinical diagnoses. This work proposes an automatic segmentation of the lungs in CT images, using the Convolutional Neural Network (CNN) Mask R-CNN, to specialize the model for lung region mapping, combined with supervised and unsupervised machine learning methods (Bayes, Support Vectors Machine (SVM), K-means and Gaussian Mixture Models (GMMs)). Our approach using Mask R-CNN with the K-means kernel produced the best results for lung segmentation reaching an accuracy of 97.68 ± 3.42% and an average runtime of 11.2 s. We compared our results against other works for validation purposes, and our approach had the highest accuracy and was faster than some state-of-the-art methods.Graphical abstractGraphical abstract for this article
       
  • An intelligent learning approach for improving ECG signal classification
           and arrhythmia analysis
    • Abstract: Publication date: March 2020Source: Artificial Intelligence in Medicine, Volume 103Author(s): Arun Kumar Sangaiah, Maheswari Arumugam, Gui-Bin Bian The recognition of cardiac arrhythmia in minimal time is important to prevent sudden and untimely deaths. The proposed work includes a complete framework for analyzing the Electrocardiogram (ECG) signal. The three phases of analysis include 1) the ECG signal quality enhancement through noise suppression by a dedicated filter combination; 2) the feature extraction by a devoted wavelet design and 3) a proposed hidden Markov model (HMM) for cardiac arrhythmia classification into Normal (N), Right Bundle Branch Block (RBBB), Left Bundle Branch Block (LBBB), Premature Ventricular Contraction (PVC) and Atrial Premature Contraction (APC). The main features extracted in the proposed work are minimum, maximum, mean, standard deviation, and median. The experiments were conducted on forty-five ECG records in MIT BIH arrhythmia database and in MIT BIH noise stress test database. The proposed model has an overall accuracy of 99.7 % with a sensitivity of 99.7 % and a positive predictive value of 100 %. The detection error rate for the proposed model is 0.0004. This paper also includes a study of the cardiac arrhythmia recognition using an IoMT (Internet of Medical Things) approach.
       
  • Multi-planar 3D breast segmentation in MRI via deep convolutional neural
           networks
    • Abstract: Publication date: March 2020Source: Artificial Intelligence in Medicine, Volume 103Author(s): Gabriele Piantadosi, Mario Sansone, Roberta Fusco, Carlo Sansone Nowadays, Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) has demonstrated to be a valid complementary diagnostic tool for early detection and diagnosis of breast cancer. However, without a CAD (Computer Aided Detection) system, manual DCE-MRI examination can be difficult and error-prone. The early stage of breast tissue segmentation, in a typical CAD, is crucial to increase reliability and reduce the computational effort by reducing the number of voxels to analyze and removing foreign tissues and air. In recent years, the deep convolutional neural networks (CNNs) enabled a sensible improvement in many visual tasks automation, such as image classification and object recognition. These advances also involved radiomics, enabling high-throughput extraction of quantitative features, resulting in a strong improvement in automatic diagnosis through medical imaging. However, machine learning and, in particular, deep learning approaches are gaining popularity in the radiomics field for tissue segmentation. This work aims to accurately segment breast parenchyma from the air and other tissues (such as chest-wall) by applying an ensemble of deep CNNs on 3D MR data. The novelty, besides applying cutting-edge techniques in the radiomics field, is a multi-planar combination of U-Net CNNs by a suitable projection-fusing approach, enabling multi-protocol applications. The proposed approach has been validated over two different datasets for a total of 109 DCE-MRI studies with histopathologically proven lesions and two different acquisition protocols. The median dice similarity index for both the datasets is 96.60 % (±0.30 %) and 95.78 % (±0.51 %) respectively with p 
       
  • A fusion framework to extract typical treatment patterns from electronic
           medical records
    • Abstract: Publication date: March 2020Source: Artificial Intelligence in Medicine, Volume 103Author(s): Jingfeng Chen, Leilei Sun, Chonghui Guo, Yanming Xie ObjectiveElectronic Medical Records (EMRs) contain temporal and heterogeneous doctor order information that can be used for treatment pattern discovery. Our objective is to identify “right patient”, “right drug”, “right dose”, “right route”, and “right time” from doctor order information.MethodsWe propose a fusion framework to extract typical treatment patterns based on multi-view similarity Network Fusion (SNF) method. The multi-view SNF method involves three similarity measures: content-view similarity, sequence-view similarity and duration-view similarity. An EMR dataset and two metrics were utilized to evaluate the performance and to extract typical treatment patterns.ResultsExperimental results on a real-world EMR dataset show that the multi-view similarity network fusion method outperforms all the single-view similarity measures and also outperforms the existing similarity measure methods. Furthermore, we extract and visualize typical treatment patterns by clustering analysis.ConclusionThe extracted typical treatment patterns by combining doctor order content, sequence, and duration views can provide data-driven guidelines for artificial intelligence in medicine and help clinicians make better decisions in clinical practice.
       
  • Gait characteristics and clinical relevance of hereditary spinocerebellar
           ataxia on deep learning
    • Abstract: Publication date: Available online 7 January 2020Source: Artificial Intelligence in MedicineAuthor(s): Luya Jin, Wen Lv, Guocan Han, Linhui Ni, Di sun, Xingyue Hu, Huaying Cai BackgroundDeep learning has always been at the forefront of scientific research. It has also been applied to medical research. Hereditary spinocerebellar ataxia (SCA) is characterized by gait abnormalities and is usually evaluated semi-quantitatively by scales. However, more detailed gait characteristics of SCA and related objective methods have not yet been established. Therefore, the purpose of this study was to evaluate the gait characteristics of SCA patients, as well as to analyze the correlation between gait parameters, clinical scales, and imaging on deep learning.MethodsTwenty SCA patients diagnosed by genetic detection were included in the study. Ten patients who were tested via functional magnetic resonance imaging (fMRI) were included in the SCA imaging subgroup. All SCA patients were evaluated with the International Cooperative Ataxia Rating Scale (ICARS) and Scale for the Assessment and Rating of Ataxia (SARA) clinical scales. The gait control group included 16 healthy subjects, and the imaging control group included seven healthy subjects. Gait data consisting of 10 m of free walking of each individual in the SCA group and the gait control group were detected by wearable gait-detection equipment. Stride length, stride time, velocity, supporting-phase percentage, and swinging-phase percentage were extracted as gait parameters. Cerebellar volume and the midsagittal cerebellar proportion in the posterior fossa (MRVD) were calculated according to MR.ResultsThere were significant differences in stride length, velocity, supporting-phase percentage, and swinging-phase percentage between the SCA group and the gait control group. The stride length and stride velocity of SCA groups were lower while supporting phase was longer than those of the gait control group. SCA group's velocity was negatively correlated with both the ICARS and SARA scores. The cerebellar volume and MRVD of the SCA imaging subgroup were significantly smaller than those of the imaging control group. MRVD was significantly correlated with ICARS and SARA scores, as well as stride velocity variability.ConclusionSCA gait parameters were characterized by a reduced stride length, slower walking velocity, and longer supporting phase. Additionally, a smaller cerebellar volume correlated with an increased irregularity in gait. Gait characteristics exhibited considerable clinical relevance to hereditary SCA. We conclude that a combination of gait parameters, ataxia scales, and MRVD may represent more objective markers for clinical evaluations of SCA.
       
  • An Improved Multi-swarm Particle Swarm Optimizer for Optimizing the
           Electric Field Distribution of Multichannel Transcranial Magnetic
           Stimulation
    • Abstract: Publication date: Available online 3 January 2020Source: Artificial Intelligence in MedicineAuthor(s): Hui Xiong, Bowen Qiu, Jinzhen Liu Multichannel transcranial magnetic stimulation (mTMS) is a therapeutic method to improve psychiatric diseases, which has a flexible working pattern used to different applications. In order to make the electric field distribution in the brain meet the treatment expectations, we have developed a novel multi-swam particle swarm optimizer (NMSPSO) to optimize the current configuration of double layer coil array. To balance the exploration and exploitation abilities, three novel improved strategies are used in NMSPSO based on multi-swarm particle swarm optimizer. Firstly, a novel information exchange strategy is achieved by individual exchanges between sub-swarms. Secondly, a novel leaning strategy is used to control knowledge dissemination in the population, which not only increases the diversity of the particles but also guarantees the convergence. Finally, a novel mutation strategy is introduced, which can help the population jump out of the local optimum for better exploration ability. The method is examined on a set of well-known benchmark functions and the results show that NMSPSO has better performance than many particle swarm optimization variants. And the superior electric field distribution in mTMS can be obtained by NMSPSO to optimize the current configuration of the double layer coil array.
       
  • A NOVEL METHOD OF MOTOR IMAGERY CLASSIFICATION USING EEG SIGNAL
    • Abstract: Publication date: Available online 31 December 2019Source: Artificial Intelligence in MedicineAuthor(s): Venkatachalam K., Devipriya A., Maniraj J., Sivaram M., Ambikapathy A., S Amiri Iraj A subject of extensive research interest in the Brain Computer Interfaces (BCIs) niche is motor imagery (MI), where users imagine limb movements to control the system. This interest is owed to the immense potential for its applicability in gaming, neuro-prosthetics and neuro-rehabilitation, where the user’s thoughts of imagined movements need to be decoded. Electroencephalography (EEG) equipment is commonly used for keeping track of cerebrum movement in BCI systems. The EEG signals are recognized by feature extraction and classification. The current research proposes a Hybrid-KELM (Kernel Extreme Learning Machine) method based on PCA (Principal Component Analysis) and FLD (Fisher's Linear Discriminant) for MI BCI classification of EEG data. The performance and results of the method are demonstrated using BCI competition dataset III, and compared with those of contemporary methods. The proposed method generated an accuracy of 96.54%.
       
  • Semantic Segmentation with DenseNets for Carotid Artery Ultrasound Plaque
           Segmentation and CIMT estimation
    • Abstract: Publication date: Available online 31 December 2019Source: Artificial Intelligence in MedicineAuthor(s): Maria del Mar Vila, Beatriz Remeseiro, Maria Grau, Roberto Elosua, Àngels Betriu, Elvira Fernandez-Giraldez, Laura Igual Background and ObjectiveThe measurement of Carotid Intima Media Thickness (CIMT) in ultrasound images can be used to detect the presence of atherosclerotic plaques. Usually, the CIMT estimation strategy is semi-automatic, since it requires: 1) a manual examination of the ultrasound image for the localization of a Region Of Interest (ROI), a fast and useful operation when only a small number of images need to be measured; and 2) an automatic delineation of the CIM region within the ROI. The existing efforts for automating the process have replicated the same two-step structure, resulting in two consecutive independent approaches. In this work, we propose a fully automatic single-step approach based on semantic segmentation that allows us to segment the plaque and to estimate the CIMT in a fast and useful manner for large data sets of images.MethodsOur single-step approach is based on Densely Connected Convolutional Neural Networks (DenseNets) for semantic segmentation of the whole image. It has two remarkable characteristics: (1) it avoids ROI definition, and (2) it captures multi-scale contextual information in the complete image interpretation, due to the concatenation of feature maps carried out in DenseNets. Once the input image is segmented, a straightforward method for CIMT estimation and plaque detection is applied.ResultsThe proposed method has been validated with a large data set (REGICOR) of more than 8,000 images, corresponding to two territories of the Carotid Artery: Common Carotid Artery (CCA) and Bulb. Among them, a subset of 331 images has been used to evaluate the performance of semantic segmentation (≈90% for train, ≈10% for test). The experimental results demonstrated that our method outperforms other deep models and shallow approaches found in the literature. In particular, our CIMT estimation reaches a correlation coefficient of 0.81, and a CIMT mean error of 0.02 mm and 0.06 mm in CCA and Bulb images, respectively. Furthermore, the accuracy for plaque detection is 96.45% and 78.09% in CCA and Bulb, respectively. To test the generalization power, the method has also been tested with another data set (NEFRONA) that includes images acquired with different equipment.ConclusionsThe validation carried out demonstrates that the proposed method is accurate and objective for both plaque detection and CIMT measurement. Moreover, the robustness and generalization capacity of the method have been proven with two different data sets.
       
  • Topic-informed neural approach for biomedical event extraction
    • Abstract: Publication date: Available online 30 December 2019Source: Artificial Intelligence in MedicineAuthor(s): Junchi Zhang, Mengchi Liu, Yue Zhang As a crucial step of biological event extraction, event trigger identification has attracted much attention in recent years. Deep representation methods, which have the superiorities of less feature engineering and end-to-end training, show better performance than statistical methods. While most deep learning methods have been done on sentence-level event extraction, there are few works taking document context into account, losing potentially informative knowledge that is beneficial for trigger detection. In this paper, we propose a variational neural approach for biomedical event extraction, which can take advantage of latent topics underlying documents. By adopting a joint modeling manner of topics and events, our model is able to produce more meaningful and event-indicative words compare to prior topic models. In addition, we introduce a language model embeddings to capture context-dependent features. Experimental results show that our approach outperforms various baselines in a commonly used multi-level event extraction corpus.
       
  • Medical Knowledge Embedding Based on Recursive Neural Network for
           Multi-Disease Diagnosis
    • Abstract: Publication date: Available online 28 November 2019Source: Artificial Intelligence in MedicineAuthor(s): Jingchi Jiang, Huanzheng Wang, Jing Xie, Xitong Guo, Yi Guan, Qiubin Yu The representation of knowledge based on first-order logic captures the richness of natural language and supports multiple probabilistic inference models. Although symbolic representation enables quantitative reasoning with statistical probability, it is difficult to utilize with machine learning models as they perform numerical operations. In contrast, knowledge embedding (i.e., high-dimensional and continuous vectors) is a feasible approach to complex reasoning that can not only retain the semantic information of knowledge, but also establish the quantifiable relationship among embeddings. In this paper, we propose a recursive neural knowledge network (RNKN), which combines medical knowledge based on first-order logic with a recursive neural network for multi-disease diagnosis. After the RNKN is efficiently trained using manually annotated Chinese Electronic Medical Records (CEMRs), diagnosis-oriented knowledge embeddings and weight matrixes are learned. The experimental results confirm that the diagnostic accuracy of the RNKN is superior to those of four machine learning models, four classical neural networks and Markov logic network. The results also demonstrate that the more explicit the evidence extracted from CEMRs, the better the performance. The RNKN gradually reveals the interpretation of knowledge embeddings as the number of training epochs increases.
       
  • A multi-context CNN ensemble for small lesion detection
    • Abstract: Publication date: Available online 13 November 2019Source: Artificial Intelligence in MedicineAuthor(s): B. Savelli, A. Bria, M. Molinara, C. Marrocco, F. Tortorella In this paper, we propose a novel method for the detection of small lesions in digital medical images. Our approach is based on a multi-context ensemble of convolutional neural networks (CNNs), aiming at learning different levels of image spatial context and improving detection performance. The main innovation behind the proposed method is the use of multiple-depth CNNs, individually trained on image patches of different dimensions and then combined together. In this way, the final ensemble is able to find and locate abnormalities on the images by exploiting both the local features and the surrounding context of a lesion. Experiments were focused on two well-known medical detection problems that have been recently faced with CNNs: microcalcification detection on full-field digital mammograms and microaneurysm detection on ocular fundus images. To this end, we used two publicly available datasets, INbreast and E-ophtha. Statistically significantly better detection performance were obtained by the proposed ensemble with respect to other approaches in the literature, demonstrating its effectiveness in the detection of small abnormalities.
       
  • Multi-resolution Convolutional Networks for Chest X-Ray Radiograph Based
           Lung Nodule Detection
    • Abstract: Publication date: Available online 28 October 2019Source: Artificial Intelligence in MedicineAuthor(s): Xuechen Li, Linlin Shen, Xinpeng Xie, Shiyun Huang, Zhien Xie, Xian Hong, Juan Yu Lung cancer is the leading cause of cancer death worldwide. Early detection of lung cancer is helpful to provide the best possible clinical treatment for patients. Due to the limited number of radiologist and the huge number of chest x-ray radiographs (CXR) available for observation, a computer-aided detection scheme should be developed to assist radiologists in decision-making. While deep learning showed state-of-the-art performance in several computer vision applications, it has not been used for lung nodule detection on CXR. In this paper, a deep learning-based lung nodule detection method was proposed. We employed patch-based multi-resolution convolutional networks to extract the features and employed four different fusion methods for classification. The proposed method shows much better performance and is much more robust than those previously reported researches. For publicly available Japanese Society of Radiological Technology (JSRT) database, more than 99% of lung nodules can be detected when the false positives per image (FPs/image) was 0.2. The FAUC and R-CPM of the proposed method were 0.982 and 0.987, respectively. The proposed approach has the potential of applications in clinical practice.
       
 
JournalTOCs
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Email: journaltocs@hw.ac.uk
Tel: +00 44 (0)131 4513762
 


Your IP address: 3.230.76.196
 
Home (Search)
API
About JournalTOCs
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-