bims-arihec Biomed News
on Artificial intelligence in healthcare
Issue of 2020‒04‒05
sixteen papers selected by
Céline Bélanger
Cogniges Inc.


  1. Syst Med (New Rochelle). 2020 ;3(1): 22-35
    Kurnat-Thoma E, Baranova A, Baird P, Brodsky E, Butte AJ, Cheema AK, Cheng F, Dutta S, Grant C, Giordano J, Maitland-van der Zee AH, Fridsma DB, Jarrin R, Kann MG, Keeney J, Loscalzo J, Madhavan G, Maron BA, McBride DK, McKean M, Mun SK, Palmer JC, Patel B, Parakh K, Pariser AR, Pristipino C, Radstake TRDJ, Rajasimha HK, Rouse WB, Rozman D, Saleh A, Schmidt HHHW, Schultz N, Sethi T, Silverman EK, Skopac J, Svab I, Trujillo S, Valentine JE, Verma D, West BJ, Vasudevan S.
      The First International Conference in Systems and Network Medicine gathered together 200 global thought leaders, scientists, clinicians, academicians, industry and government experts, medical and graduate students, postdoctoral scholars and policymakers. Held at Georgetown University Conference Center in Washington D.C. on September 11-13, 2019, the event featured a day of pre-conference lectures and hands-on bioinformatic computational workshops followed by two days of deep and diverse scientific talks, panel discussions with eminent thought leaders, and scientific poster presentations. Topics ranged from: Systems and Network Medicine in Clinical Practice; the role of -omics technologies in Health Care; the role of Education and Ethics in Clinical Practice, Systems Thinking, and Rare Diseases; and the role of Artificial Intelligence in Medicine. The conference served as a unique nexus for interdisciplinary discovery and dialogue and fostered formation of new insights and possibilities for health care systems advances.
    Keywords:  artificial intelligence; big data; ethical legal social implications (ELSI); international conference; network medicine; regulatory and health policy; systems
    DOI:  https://doi.org/10.1089/sysm.2020.0001
  2. Curr Pharm Des. 2020 Mar 30.
    Ao C, Jin S, Ding H, Zou Q, Yu L.
      With the continuous development of artificial intelligence (AI) technology, big datasupported AI technology with considerable computer and learning capacity has been applied in diagnosing different types of diseases. This study reviews the application of expert system, neural network, and deep learning used by AI technology in disease diagnosis. This paper also gives a glimpse of the intelligent diagnosis and treatment of digestive system diseases, respiratory system diseases, and osteoporosis by AI technology.
    Keywords:  Artificial Intelligence; Deep Learning; Disease Diagnosis; Expert System; Neural Network
    DOI:  https://doi.org/10.2174/1381612826666200331091156
  3. JMIR Med Inform. 2020 Mar 31. 8(3): e17984
    Spasic I, Nenadic G.
      BACKGROUND: Clinical narratives represent the main form of communication within health care, providing a personalized account of patient history and assessments, and offering rich information for clinical decision making. Natural language processing (NLP) has repeatedly demonstrated its feasibility to unlock evidence buried in clinical narratives. Machine learning can facilitate rapid development of NLP tools by leveraging large amounts of text data.OBJECTIVE: The main aim of this study was to provide systematic evidence on the properties of text data used to train machine learning approaches to clinical NLP. We also investigated the types of NLP tasks that have been supported by machine learning and how they can be applied in clinical practice.
    METHODS: Our methodology was based on the guidelines for performing systematic reviews. In August 2018, we used PubMed, a multifaceted interface, to perform a literature search against MEDLINE. We identified 110 relevant studies and extracted information about text data used to support machine learning, NLP tasks supported, and their clinical applications. The data properties considered included their size, provenance, collection methods, annotation, and any relevant statistics.
    RESULTS: The majority of datasets used to train machine learning models included only hundreds or thousands of documents. Only 10 studies used tens of thousands of documents, with a handful of studies utilizing more. Relatively small datasets were utilized for training even when much larger datasets were available. The main reason for such poor data utilization is the annotation bottleneck faced by supervised machine learning algorithms. Active learning was explored to iteratively sample a subset of data for manual annotation as a strategy for minimizing the annotation effort while maximizing the predictive performance of the model. Supervised learning was successfully used where clinical codes integrated with free-text notes into electronic health records were utilized as class labels. Similarly, distant supervision was used to utilize an existing knowledge base to automatically annotate raw text. Where manual annotation was unavoidable, crowdsourcing was explored, but it remains unsuitable because of the sensitive nature of data considered. Besides the small volume, training data were typically sourced from a small number of institutions, thus offering no hard evidence about the transferability of machine learning models. The majority of studies focused on text classification. Most commonly, the classification results were used to support phenotyping, prognosis, care improvement, resource management, and surveillance.
    CONCLUSIONS: We identified the data annotation bottleneck as one of the key obstacles to machine learning approaches in clinical NLP. Active learning and distant supervision were explored as a way of saving the annotation efforts. Future research in this field would benefit from alternatives such as data augmentation and transfer learning, or unsupervised learning, which do not require data annotation.
    Keywords:  machine learning; medical informatics; medical informatics applications; natural language processing
    DOI:  https://doi.org/10.2196/17984
  4. OMICS. 2020 Mar 31.
    Ozer ME, Sarica PO, Arga KY.
      Artificial intelligence, machine learning, health care robots, and algorithms for clinical decision-making are currently being sought after in diverse fields of clinical medicine and bioengineering. The field of personalized medicine stands to benefit from new technologies so as to harness the omics big data, for example, to individualize and accelerate cancer diagnostics and therapeutics in particular. In this overarching context, breast cancer is one of the most common malignancies worldwide with multiple underlying molecular etiologies and each subtype displaying diverse clinical outcomes. Disease stratification for breast cancer is, therefore, vital to its effective and individualized clinical care. The support vector machine (SVM) is a rising machine learning approach that offers robust classification of high-dimensional big data into small numbers of data points (support vectors), achieving differentiation of subgroups in a short amount of time. Considering the rapid timelines required for both diagnosis and treatment of most aggressive cancers, this new machine learning technique has important clinical and public applications and implications for high-throughput data analysis and contextualization. This expert review describes and examines, first, the SVM models employed to forecast breast cancer subtypes using diverse systems science data, including transcriptomics, epigenetics, proteomics, and radiomics, as well as biological pathway, clinical, pathological, and biochemical data. Then, we compare the performance of the present SVM and other diagnostic and therapeutic prediction models across the data types. We conclude by emphasizing that data integration is a critical bottleneck in systems science, cancer research and development, and health care innovation and that SVM and machine learning approaches offer new solutions and ways forward in biomedical, bioengineering, and clinical applications.
    Keywords:  Support Vector Machines; algorithms and clinical decision-making; breast cancer; health care robots; machine learning; personalized medicine
    DOI:  https://doi.org/10.1089/omi.2020.0001
  5. Therap Adv Gastroenterol. 2020 ;13 1756284820910659
    Ozawa T, Ishihara S, Fujishiro M, Kumagai Y, Shichijo S, Tada T.
      Background: Recently the American Society for Gastrointestinal Endoscopy addressed the 'resect and discard' strategy, determining that accurate in vivo differentiation of colorectal polyps (CP) is necessary. Previous studies have suggested a promising application of artificial intelligence (AI), using deep learning in object recognition. Therefore, we aimed to construct an AI system that can accurately detect and classify CP using stored still images during colonoscopy.Methods: We used a deep convolutional neural network (CNN) architecture called Single Shot MultiBox Detector. We trained the CNN using 16,418 images from 4752 CPs and 4013 images of normal colorectums, and subsequently validated the performance of the trained CNN in 7077 colonoscopy images, including 1172 CP images from 309 various types of CP. Diagnostic speed and yields for the detection and classification of CP were evaluated as a measure of performance of the trained CNN.
    Results: The processing time of the CNN was 20 ms per frame. The trained CNN detected 1246 CP with a sensitivity of 92% and a positive predictive value (PPV) of 86%. The sensitivity and PPV were 90% and 83%, respectively, for the white light images, and 97% and 98% for the narrow band images. Among the correctly detected polyps, 83% of the CP were accurately classified through images. Furthermore, 97% of adenomas were precisely identified under the white light imaging.
    Conclusions: Our CNN showed promise in being able to detect and classify CP through endoscopic images, highlighting its high potential for future application as an AI-based CP diagnosis support system for colonoscopy.
    Keywords:  artificial intelligence; classification; colon; colorectal; convolutional neural network; detection; diagnosis; polyp
    DOI:  https://doi.org/10.1177/1756284820910659
  6. Gastrointest Endosc. 2020 Mar 30. pii: S0016-5107(20)34034-7. [Epub ahead of print]
    Mori Y, Kudo SE, East JE, Rastogi A, Bretthauer M, Misawa M, Sekiguchi M, Matsuda T, Saito Y, Ikematsu H, Hotta K, Ohtsuka K, Kudo T, Mori K.
      BACKGROUND AND AIMS: Artificial intelligence (AI) is being implemented into colonoscopy practice, but no study has investigated whether AI is cost-saving. We quantified the cost reduction from using AI as an aid in the optical diagnosis of colorectal polyps.METHODS: This study is an add-on analysis of a clinical trial that investigated the performance of AI for differentiating colorectal polyps (ie, neoplastic versus non-neoplastic). We included all patients with diminutive (≤5 mm) rectosigmoid polyp for analyses. The average colonoscopy cost was compared for 2 scenarios: (1) a diagnose-and-leave strategy supported by the AI prediction (ie, diminutive rectosigmoid polyps were not removed when predicted as non-neoplastic), and (2) a resect-all-polyps strategy. Gross annual costs for colonoscopies were also calculated based on numbers and reimbursement of colonoscopies conducted under public health insurances in 4 countries.
    RESULTS: Overall, 207 patients with 250 diminutive rectosigmoid polyps (104 neoplastic, 144 non-neoplastic, and 2 indeterminate) were included. AI correctly differentiated neoplastic polyps with 93.3% sensitivity, 95.2% specificity, and 95.2% negative predictive value. Thus, 105 polyps were removed whereas 145 were left under the diagnose-and-leave strategy, which was estimated to reduce the average colonoscopy cost and the gross annual reimbursement for colonoscopies by 18.9% and 149.2 million dollars in Japan, 6.9% and 12.3 million dollars in England, 7.6% and 1.1 million dollars in Norway, and 10.9% and 85.2 million dollars in the United States, respectively, compared to the resect-all-polyps strategy.
    CONCLUSIONS: The use of AI to enable the diagnose-and-leave strategy results in substantial cost reductions for colonoscopy.
    Keywords:  Cost effectiveness; computer-aided detection; computer-aided diagnosis; endocytoscopy; optical biopsy
    DOI:  https://doi.org/10.1016/j.gie.2020.03.3759
  7. Diagnostics (Basel). 2020 Apr 01. pii: E198. [Epub ahead of print]10(4):
    Mashamba-Thompson TP, Crayton ED.
      The novel coronavirus disease 19 (COVID-19) is rapidly spreading with a rising death toll and transmission rate reported in high income countries rather than in low income countries. The overburdened healthcare systems and poor disease surveillance systems in resource-limited settings may struggle to cope with this COVID-19 outbreak and this calls for a tailored strategic response for these settings. Here, we recommend a low cost blockchain and artificial intelligence-coupled self-testing and tracking systems for COVID-19 and other emerging infectious diseases. Prompt deployment and appropriate implementation of the proposed system have the potential to curb the transmissions of COVID-19 and the related mortalities, particularly in settings with poor access to laboratory infrastructure.
    Keywords:  artificial intelligence; blockchain; novel coronavirus disease-19; self-testing
    DOI:  https://doi.org/10.3390/diagnostics10040198
  8. Curr Hematol Malig Rep. 2020 Apr 01.
    Radakovich N, Nagy M, Nazha A.
      PURPOSE OF REVIEW: Artificial intelligence (AI), and in particular its subcategory machine learning, is finding an increasing number of applications in medicine, driven in large part by an abundance of data and powerful, accessible tools that have made AI accessible to a larger circle of investigators.RECENT FINDINGS: AI has been employed in the analysis of hematopathological, radiographic, laboratory, genomic, pharmacological, and chemical data to better inform diagnosis, prognosis, treatment planning, and foundational knowledge related to benign and malignant hematology. As more widespread implementation of clinical AI nears, attention has also turned to the effects this will have on other areas in medicine. AI offers many promising tools to clinicians broadly, and specifically in the practice of hematology. Ongoing research into its various applications will likely result in an increasing utilization of AI by a broader swath of clinicians.
    Keywords:  Artificial intelligence; Deep learning; Hematology; Machine learning
    DOI:  https://doi.org/10.1007/s11899-020-00575-4
  9. Curr Opin Nephrol Hypertens. 2020 May;29(3): 319-326
    Chan L, Vaid A, Nadkarni GN.
      PURPOSE OF REVIEW: The universal adoption of electronic health records, improvement in technology, and the availability of continuous monitoring has generated large quantities of healthcare data. Machine learning is increasingly adopted by nephrology researchers to analyze this data in order to improve the care of their patients.RECENT FINDINGS: In this review, we provide a broad overview of the different types of machine learning algorithms currently available and how researchers have applied these methods in nephrology research. Current applications have included prediction of acute kidney injury and chronic kidney disease along with progression of kidney disease. Researchers have demonstrated the ability of machine learning to read kidney biopsy samples, identify patient outcomes from unstructured data, and identify subtypes in complex diseases. We end with a discussion on the ethics and potential pitfalls of machine learning.
    SUMMARY: Machine learning provides researchers with the ability to analyze data that were previously inaccessible. While still burgeoning, several studies show promising results, which will enable researchers to perform larger scale studies and clinicians the ability to provide more personalized care. However, we must ensure that implementation aids providers and does not lead to harm to patients.
    DOI:  https://doi.org/10.1097/MNH.0000000000000604
  10. Clin Epigenetics. 2020 Apr 03. 12(1): 51
    Rauschert S, Raubenheimer K, Melton PE, Huang RC.
      BACKGROUND: Machine learning is a sub-field of artificial intelligence, which utilises large data sets to make predictions for future events. Although most algorithms used in machine learning were developed as far back as the 1950s, the advent of big data in combination with dramatically increased computing power has spurred renewed interest in this technology over the last two decades.MAIN BODY: Within the medical field, machine learning is promising in the development of assistive clinical tools for detection of e.g. cancers and prediction of disease. Recent advances in deep learning technologies, a sub-discipline of machine learning that requires less user input but more data and processing power, has provided even greater promise in assisting physicians to achieve accurate diagnoses. Within the fields of genetics and its sub-field epigenetics, both prime examples of complex data, machine learning methods are on the rise, as the field of personalised medicine is aiming for treatment of the individual based on their genetic and epigenetic profiles.
    CONCLUSION: We now have an ever-growing number of reported epigenetic alterations in disease, and this offers a chance to increase sensitivity and specificity of future diagnostics and therapies. Currently, there are limited studies using machine learning applied to epigenetics. They pertain to a wide variety of disease states and have used mostly supervised machine learning methods.
    DOI:  https://doi.org/10.1186/s13148-020-00842-4
  11. JMIR Ment Health. 2020 Apr 01. 7(4): e13174
    Kalantarian H, Jedoui K, Dunlap K, Schwartz J, Washington P, Husic A, Tariq Q, Ning M, Kline A, Wall DP.
      BACKGROUND: Autism spectrum disorder (ASD) is a developmental disorder characterized by deficits in social communication and interaction, and restricted and repetitive behaviors and interests. The incidence of ASD has increased in recent years; it is now estimated that approximately 1 in 40 children in the United States are affected. Due in part to increasing prevalence, access to treatment has become constrained. Hope lies in mobile solutions that provide therapy through artificial intelligence (AI) approaches, including facial and emotion detection AI models developed by mainstream cloud providers, available directly to consumers. However, these solutions may not be sufficiently trained for use in pediatric populations.OBJECTIVE: Emotion classifiers available off-the-shelf to the general public through Microsoft, Amazon, Google, and Sighthound are well-suited to the pediatric population, and could be used for developing mobile therapies targeting aspects of social communication and interaction, perhaps accelerating innovation in this space. This study aimed to test these classifiers directly with image data from children with parent-reported ASD recruited through crowdsourcing.
    METHODS: We used a mobile game called Guess What? that challenges a child to act out a series of prompts displayed on the screen of the smartphone held on the forehead of his or her care provider. The game is intended to be a fun and engaging way for the child and parent to interact socially, for example, the parent attempting to guess what emotion the child is acting out (eg, surprised, scared, or disgusted). During a 90-second game session, as many as 50 prompts are shown while the child acts, and the video records the actions and expressions of the child. Due in part to the fun nature of the game, it is a viable way to remotely engage pediatric populations, including the autism population through crowdsourcing. We recruited 21 children with ASD to play the game and gathered 2602 emotive frames following their game sessions. These data were used to evaluate the accuracy and performance of four state-of-the-art facial emotion classifiers to develop an understanding of the feasibility of these platforms for pediatric research.
    RESULTS: All classifiers performed poorly for every evaluated emotion except happy. None of the classifiers correctly labeled over 60.18% (1566/2602) of the evaluated frames. Moreover, none of the classifiers correctly identified more than 11% (6/51) of the angry frames and 14% (10/69) of the disgust frames.
    CONCLUSIONS: The findings suggest that commercial emotion classifiers may be insufficiently trained for use in digital approaches to autism treatment and treatment tracking. Secure, privacy-preserving methods to increase labeled training data are needed to boost the models' performance before they can be used in AI-enabled approaches to social therapy of the kind that is common in autism treatments.
    Keywords:  affect; artificial intelligence; autism; digital data; digital health; emotion; mHealth; machine learning; mobile app; mobile phone
    DOI:  https://doi.org/10.2196/13174
  12. J Invest Dermatol. 2020 Mar 27. pii: S0022-202X(20)31201-X. [Epub ahead of print]
    Young AT, Xiong M, Pfau J, Keiser MJ, Wei ML.
      Artificial intelligence (AI) is becoming increasingly important in dermatology, with studies reporting accuracy matching or exceeding dermatologists for the diagnosis of skin lesions from clinical and dermoscopic images. However, real-world clinical validation is currently lacking. We review dermatological applications of deep learning, the leading AI technology for image analysis, and discuss its current capabilities, potential failure modes, and challenges surrounding performance assessment and interpretability. We address three primary applications: (1) teledermatology, including triage for referral to dermatologists, (2) augmenting clinical assessment during face-to-face visits, and (3) dermatopathology. We discuss equity and ethical issues related to future clinical adoption and recommend specific standardization of metrics for reporting model performance.
    Keywords:  AI models; Deep learning; Image analysis; Melanoma
    DOI:  https://doi.org/10.1016/j.jid.2020.02.026
  13. J Laryngol Otol. 2020 Apr 01. 1-4
    Parmar P, Habib AR, Mendis D, Daniel A, Duvnjak M, Ho J, Smith M, Roshan D, Wong E, Singh N.
      OBJECTIVE: Convolutional neural networks are a subclass of deep learning or artificial intelligence that are predominantly used for image analysis and classification. This proof-of-concept study attempts to train a convolutional neural network algorithm that can reliably determine if the middle turbinate is pneumatised (concha bullosa) on coronal sinus computed tomography images.METHOD: Consecutive high-resolution computed tomography scans of the paranasal sinuses were retrospectively collected between January 2016 and December 2018 at a tertiary rhinology hospital in Australia. The classification layer of Inception-V3 was retrained in Python using a transfer learning method to interpret the computed tomography images. Segmentation analysis was also performed in an attempt to increase diagnostic accuracy.
    RESULTS: The trained convolutional neural network was found to have diagnostic accuracy of 81 per cent (95 per cent confidence interval: 73.0-89.0 per cent) with an area under the curve of 0.93.
    CONCLUSION: A trained convolutional neural network algorithm appears to successfully identify pneumatisation of the middle turbinate with high accuracy. Further studies can be pursued to test its ability in other clinically important anatomical variants in otolaryngology and rhinology.
    Keywords:  Artificial Intelligence; Deep Learning; Sinusitis; Surgery; Turbinates
    DOI:  https://doi.org/10.1017/S0022215120000444
  14. Can J Cardiol. 2020 Apr;pii: S0828-282X(19)31269-3. [Epub ahead of print]36(4): 577-583
    Iannattone PA, Zhao X, VanHouten J, Garg A, Huynh T.
      BACKGROUND: Machine learning (ML) encompasses a wide variety of methods by which artificial intelligence learns to perform tasks when exposed to data. Although detection of myocardial infarction has been facilitated with introduction of troponins, the diagnosis of acute coronary syndromes (ACS) without myocardial damage (without elevation of serum troponin) remains subjective, and its accuracy remains highly dependent on clinical skills of the health care professionals. Application of a ML algorithm may expedite management of ACS for either early discharge or early initiation of ACS management. We aim to summarize the published studies of ML for diagnosis of ACS.METHODS: We searched electronic databases, including PubMed, Embase, and Web of Science from inception up to January 13, 2019, for studies that evaluated ML algorithms for the diagnosis of ACS in patients presenting with chest pain. We then used random-effects bivariate meta-analysis models to summarize the studies.
    RESULTS: We retained 9 studies that evaluated ML in a total of 6292 patients. The prevalence of ACS in the evaluated cohorts ranged from relatively rare (7%) to common (57%). The pooled sensitivity and specificity were 0.95 and 0.90, respectively. The positive predictive values ranged from 0.64 to 1.0, and the negative predictive values ranged from 0.91 to 1.0. The positive and negative likelihood ratios ranged from 1.6 to 33.0 and 0.01 to 0.13, respectively.
    CONCLUSIONS: The excellent sensitivity, negative likelihood ratio, and negative predictive values suggest that ML may be useful as an initial triage tool for ruling out ACS.
    DOI:  https://doi.org/10.1016/j.cjca.2019.09.013
  15. Clin Infect Dis. 2020 Apr 04. pii: ciaa383. [Epub ahead of print]
    Rawson TM, Hernandez B, Moore LSP, Herrero P, Charani E, Ming D, Wilson RC, Blandy O, Sriskandan S, Gilchrist M, Toumazou C, Georgiou P, Holmes AH.
      BACKGROUND: A locally developed Case-Based Reasoning (CBR) algorithm, designed to augment antimicrobial prescribing in secondary care was evaluated.METHODS: Prescribing recommendations made by a CBR algorithm were compared to decisions made by physicians in clinical practice. Comparisons were examined in two patient populations. Firstly, in patients with confirmed Escherichia coli blood stream infections ('E.coli patients'), and secondly in ward-based patients presenting with a range of potential infections ('ward patients'). Prescribing recommendations were compared against the Antimicrobial Spectrum Index (ASI) and the WHO Essential Medicine List Access, Watch, Reserve (AWaRe) classification system. Appropriateness of a prescription was defined as the spectrum of the prescription covering the known, or most-likely organism antimicrobial sensitivity profile.
    RESULTS: In total, 224 patients (145 E.coli patients and 79 ward patients) were included. Mean (SD) age was 66 (18) years with 108/224 (48%) female gender. The CBR recommendations were appropriate in 202/224 (90%) compared to 186/224 (83%) in practice (OR: 1.24 95%CI:0.392-3.936;p=0.71). CBR recommendations had a smaller ASI compared to practice with a median (range) of 6 (0-13) compared to 8 (0-12) (p<0.01). CBR recommendations were more likely to be classified as Access class antimicrobials compared to physicians' prescriptions at 110/224 (49%) vs. 79/224 (35%) (OR: 1.77 95%CI:1.212-2.588 p<0.01). Results were similar for E.coli and ward patients on subgroup analysis.
    CONCLUSIONS: A CBR-driven decision support system provided appropriate recommendations within a narrower spectrum compared to current clinical practice. Future work must investigate the impact of this intervention on prescribing behaviours more broadly and patient outcomes.
    Keywords:  Antimicrobial Stewardship; Artificial intelligence; Case-based Reasoning; Clinical Decision Support Systems; Machine Learning; Sepsis
    DOI:  https://doi.org/10.1093/cid/ciaa383
  16. Diagn Interv Imaging. 2020 Mar 31. pii: S2211-5684(20)30083-8. [Epub ahead of print]
    Lassau N, Bousaid I, Chouzenoux E, Lamarque JP, Charmettant B, Azoulay M, Cotton F, Khalil A, Lucidarme O, Pigneur F, Benaceur Y, Sadate A, Lederlin M, Laurent F, Chassagnon G, Ernst O, Ferreti G, Diascorn Y, Brillet PY, Creze M, Cassagnes L, Caramella C, Loubet A, Dallongeville A, Abassebay N, Ohana M, Banaste N, Cadi M, Behr J, Boussel L, Fournier L, Zins M, Beregi JP, Luciani A, Cotten A, Meder JF.
      PURPOSE: The second edition of the artificial intelligence (AI) data challenge was organized by the French Society of Radiology with the aim to: (i), work on relevant public health issues; (ii), build large, multicentre, high quality databases; and (iii), include three-dimensional (3D) information and prognostic questions.MATERIALS AND METHODS: Relevant clinical questions were proposed by French subspecialty colleges of radiology. Their feasibility was assessed by experts in the field of AI. A dedicated platform was set up for inclusion centers to safely upload their anonymized examinations in compliance with general data protection regulation. The quality of the database was checked by experts weekly with annotations performed by radiologists. Multidisciplinary teams competed between September 11th and October 13th 2019.
    RESULTS: Three questions were selected using different imaging and evaluation modalities, including: pulmonary nodule detection and classification from 3D computed tomography (CT), prediction of expanded disability status scale in multiple sclerosis using 3D magnetic resonance imaging (MRI) and segmentation of muscular surface for sarcopenia estimation from two-dimensional CT. A total of 4347 examinations were gathered of which only 6% were excluded. Three independent databases from 24 individual centers were created. A total of 143 participants were split into 20 multidisciplinary teams.
    CONCLUSION: Three data challenges with over 1200 general data protection regulation compliant CT or MRI examinations each were organized. Future challenges should be made with more complex situations combining histopathological or genetic information to resemble real life situations faced by radiologists in routine practice.
    Keywords:  Artificial intelligence (AI); Computed tomography (CT); Deep learning; Machine learning; Magnetic resonance imaging (MRI)
    DOI:  https://doi.org/10.1016/j.diii.2020.03.006