{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:24:52Z","timestamp":1772040292363,"version":"3.50.1"},"reference-count":94,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Medical Informatics"],"published-print":{"date-parts":[[2021,9]]},"DOI":"10.1016\/j.ijmedinf.2021.104510","type":"journal-article","created":{"date-parts":[[2021,6,2]],"date-time":"2021-06-02T13:04:55Z","timestamp":1622639095000},"page":"104510","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":241,"special_numbering":"C","title":["The need to separate the wheat from the chaff in medical informatics"],"prefix":"10.1016","volume":"153","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4065-3415","authenticated-orcid":false,"given":"Federico","family":"Cabitza","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0027-5157","authenticated-orcid":false,"given":"Andrea","family":"Campagner","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"20","key":"10.1016\/j.ijmedinf.2021.104510_bib0005","doi-asserted-by":"crossref","first-page":"1920","DOI":"10.1161\/CIRCULATIONAHA.115.001593","article-title":"Machine learning in medicine","volume":"132","author":"Deo","year":"2015","journal-title":"Circulation"},{"issue":"1","key":"10.1016\/j.ijmedinf.2021.104510_bib0010","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41746-017-0012-2","article-title":"Artificial intelligence powers digital medicine","volume":"1","author":"Fogel","year":"2018","journal-title":"NPJ Digit. Med."},{"issue":"14","key":"10.1016\/j.ijmedinf.2021.104510_bib0015","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1056\/NEJMra1814259","article-title":"Machine learning in medicine","volume":"380","author":"Rajkomar","year":"2019","journal-title":"N. Engl. J. Med."},{"issue":"8","key":"10.1016\/j.ijmedinf.2021.104510_bib0020","doi-asserted-by":"crossref","first-page":"e19918","DOI":"10.2196\/19918","article-title":"Is artificial intelligence better than human clinicians in predicting patient outcomes?","volume":"22","author":"Lee","year":"2020","journal-title":"J. Med. Internet Res."},{"issue":"3","key":"10.1016\/j.ijmedinf.2021.104510_bib0025","doi-asserted-by":"crossref","first-page":"e10010","DOI":"10.2196\/10010","article-title":"Artificial intelligence versus clinicians in disease diagnosis: systematic review","volume":"7","author":"Shen","year":"2019","journal-title":"JMIR Med. Inform."},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0030","series-title":"Learning About Machine Learning: The Promise and Pitfalls of Big Data and the Electronic Health Record","author":"Deo","year":"2016"},{"issue":"6","key":"10.1016\/j.ijmedinf.2021.104510_bib0035","doi-asserted-by":"crossref","first-page":"e271","DOI":"10.1016\/S2589-7500(19)30123-2","article-title":"A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis","volume":"1","author":"Liu","year":"2019","journal-title":"Lancet Digit. Health"},{"issue":"3","key":"10.1016\/j.ijmedinf.2021.104510_bib0040","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1038\/s42256-021-00307-0","article-title":"Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans","volume":"3","author":"Roberts","year":"2021","journal-title":"Nat. Mach. Intell."},{"issue":"1","key":"10.1016\/j.ijmedinf.2021.104510_bib0045","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41746-021-00438-z","article-title":"Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis","volume":"4","author":"Aggarwal","year":"2021","journal-title":"NPJ Digit. Med."},{"issue":"1","key":"10.1016\/j.ijmedinf.2021.104510_bib0050","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12916-020-01754-z","article-title":"Going on up to the spirit in AI: will new reporting guidelines for clinical trials of AI interventions improve their rigour?","volume":"18","author":"Wicks","year":"2020","journal-title":"BMC Med."},{"issue":"10181","key":"10.1016\/j.ijmedinf.2021.104510_bib0055","doi-asserted-by":"crossref","first-page":"1577","DOI":"10.1016\/S0140-6736(19)30037-6","article-title":"Reporting of artificial intelligence prediction models","volume":"393","author":"Collins","year":"2019","journal-title":"Lancet"},{"issue":"1","key":"10.1016\/j.ijmedinf.2021.104510_bib0060","first-page":"1","article-title":"The reproducibility crisis in the age of digital medicine","volume":"2","author":"Stupple","year":"2019","journal-title":"NPJ Digit. Med."},{"issue":"8","key":"10.1016\/j.ijmedinf.2021.104510_bib0065","doi-asserted-by":"crossref","first-page":"963","DOI":"10.1093\/jamia\/ocy028","article-title":"Does health informatics have a replication crisis?","volume":"25","author":"Coiera","year":"2018","journal-title":"J. Am. Med. Inform. Assoc."},{"issue":"6377","key":"10.1016\/j.ijmedinf.2021.104510_bib0070","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1126\/science.359.6377.725","article-title":"Artificial intelligence faces reproducibility crisis","volume":"359","author":"Hutson","year":"2018","journal-title":"Science"},{"issue":"4","key":"10.1016\/j.ijmedinf.2021.104510_bib0075","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1001\/jama.2019.20866","article-title":"Challenges to the reproducibility of machine learning models in health care","volume":"323","author":"Beam","year":"2020","journal-title":"JAMA"},{"issue":"8","key":"10.1016\/j.ijmedinf.2021.104510_bib0080","doi-asserted-by":"crossref","first-page":"e124","DOI":"10.1371\/journal.pmed.0020124","article-title":"Why most published research findings are false","volume":"2","author":"Ioannidis","year":"2005","journal-title":"PLoS Med."},{"issue":"11","key":"10.1016\/j.ijmedinf.2021.104510_bib0085","doi-asserted-by":"crossref","first-page":"4014","DOI":"10.3390\/app10114014","article-title":"The elephant in the machine: proposing a new metric of data reliability and its application to a medical case to assess classification reliability","volume":"10","author":"Cabitza","year":"2020","journal-title":"Appl. Sci."},{"issue":"11","key":"10.1016\/j.ijmedinf.2021.104510_bib0090","doi-asserted-by":"crossref","first-page":"1544","DOI":"10.1001\/jamainternmed.2018.3763","article-title":"Potential biases in machine learning algorithms using electronic health record data","volume":"178","author":"Gianfrancesco","year":"2018","journal-title":"JAMA Intern. Med."},{"issue":"1","key":"10.1016\/j.ijmedinf.2021.104510_bib0095","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/sdata.2016.35","article-title":"Mimic-III, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci. Data"},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0100","doi-asserted-by":"crossref","first-page":"12","DOI":"10.3389\/fninf.2013.00012","article-title":"Toward open sharing of task-based fmri data: the openfmri project","volume":"7","author":"Poldrack","year":"2013","journal-title":"Front. Neuroinform."},{"issue":"3","key":"10.1016\/j.ijmedinf.2021.104510_bib0105","doi-asserted-by":"crossref","first-page":"036501","DOI":"10.1117\/1.JMI.5.3.036501","article-title":"Deeplesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning","volume":"5","author":"Yan","year":"2018","journal-title":"J. Med. Imaging"},{"issue":"1","key":"10.1016\/j.ijmedinf.2021.104510_bib0110","doi-asserted-by":"crossref","first-page":"3","DOI":"10.23876\/j.krcp.2017.36.1.3","article-title":"Medical big data: promise and challenges","volume":"36","author":"Lee","year":"2017","journal-title":"Kidney Res. Clin. Pract."},{"issue":"9","key":"10.1016\/j.ijmedinf.2021.104510_bib0115","doi-asserted-by":"crossref","first-page":"e489","DOI":"10.1016\/S2589-7500(20)30186-2","article-title":"The myth of generalisability in clinical research and machine learning in health care","volume":"2","author":"Futoma","year":"2020","journal-title":"Lancet Digit. Health"},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0120","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.jclinepi.2019.02.004","article-title":"A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models","volume":"110","author":"Christodoulou","year":"2019","journal-title":"J. Clin. Epidemiol."},{"issue":"1","key":"10.1016\/j.ijmedinf.2021.104510_bib0125","doi-asserted-by":"crossref","DOI":"10.1136\/bmjhci-2020-100251","article-title":"Clinician checklist for assessing suitability of machine learning applications in healthcare","volume":"28","author":"Scott","year":"2021","journal-title":"BMJ Health Care Inform."},{"issue":"141","key":"10.1016\/j.ijmedinf.2021.104510_bib0130","doi-asserted-by":"crossref","first-page":"20170387","DOI":"10.1098\/rsif.2017.0387","article-title":"Opportunities and obstacles for deep learning in biology and medicine","volume":"15","author":"Ching","year":"2018","journal-title":"J. R. Soc. Interface"},{"issue":"1","key":"10.1016\/j.ijmedinf.2021.104510_bib0135","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12916-019-1426-2","article-title":"Key challenges for delivering clinical impact with artificial intelligence","volume":"17","author":"Kelly","year":"2019","journal-title":"BMC Med."},{"issue":"6","key":"10.1016\/j.ijmedinf.2021.104510_bib0140","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1001\/jama.2017.7797","article-title":"Unintended consequences of machine learning in medicine","volume":"318","author":"Cabitza","year":"2017","journal-title":"JAMA"},{"issue":"7","key":"10.1016\/j.ijmedinf.2021.104510_bib0145","doi-asserted-by":"crossref","DOI":"10.1373\/clinchem.2017.274860","article-title":"Harmonization: its time has come","volume":"63","author":"Miller","year":"2017","journal-title":"Clin. Chem."},{"issue":"1","key":"10.1016\/j.ijmedinf.2021.104510_bib0150","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1515\/cclm-2019-0658","article-title":"Systematic review and meta-analysis of within-subject and between-subject biological variation estimates of 20 haematological parameters","volume":"58","author":"Coskun","year":"2020","journal-title":"Clin. Chem. Lab. Med. (CCLM)"},{"issue":"1","key":"10.1016\/j.ijmedinf.2021.104510_bib0155","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12911-017-0443-3","article-title":"Imbalanced target prediction with pattern discovery on clinical data repositories","volume":"17","author":"Chan","year":"2017","journal-title":"BMC Med. Inform. Decis. Mak."},{"issue":"11","key":"10.1016\/j.ijmedinf.2021.104510_bib0160","doi-asserted-by":"crossref","first-page":"e0224365","DOI":"10.1371\/journal.pone.0224365","article-title":"Machine learning algorithm validation with a limited sample size","volume":"14","author":"Vabalas","year":"2019","journal-title":"PLOS ONE"},{"issue":"1","key":"10.1016\/j.ijmedinf.2021.104510_bib0165","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.artmed.2013.01.003","article-title":"Missing data in medical databases: impute, delete or classify?","volume":"58","author":"Cismondi","year":"2013","journal-title":"Artif. Intell. Med."},{"issue":"1","key":"10.1016\/j.ijmedinf.2021.104510_bib0170","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1111\/j.1600-0587.2012.07348.x","article-title":"Collinearity: a review of methods to deal with it and a simulation study evaluating their performance","volume":"36","author":"Dormann","year":"2013","journal-title":"Ecography"},{"issue":"2","key":"10.1016\/j.ijmedinf.2021.104510_bib0175","first-page":"345","article-title":"From development to deployment: dataset shift, causality, and shift-stable models in health AI","volume":"21","author":"Subbaswamy","year":"2020","journal-title":"Biostatistics"},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0180","article-title":"Accounting for variance in machine learning benchmarks","volume":"3","author":"Bouthillier","year":"2021","journal-title":"Proc. Mach. Learn. Syst."},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0185","doi-asserted-by":"crossref","first-page":"101822","DOI":"10.1016\/j.artmed.2020.101822","article-title":"Automated machine learning: review of the state-of-the-art and opportunities for healthcare","volume":"104","author":"Waring","year":"2020","journal-title":"Artif. Intell. Med."},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0190","article-title":"Machine learning and artificial intelligence research for patient benefit: 20 critical questions on transparency, replicability, ethics, and effectiveness","volume":"368","author":"Vollmer","year":"2020","journal-title":"BMJ"},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0195","doi-asserted-by":"crossref","DOI":"10.1111\/ceo.13943","article-title":"Reporting guidelines for artificial intelligence in healthcare research","author":"Ibrahim","year":"2021","journal-title":"Clin. Exp. Ophthalmol."},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0200","article-title":"Guidelines for clinical trial protocols for interventions involving artificial intelligence: the spirit-AI extension","volume":"370","author":"Rivera","year":"2020","journal-title":"BMJ"},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0205","article-title":"Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the consort-AI extension","volume":"370","author":"Liu","year":"2020","journal-title":"BMJ"},{"issue":"9","key":"10.1016\/j.ijmedinf.2021.104510_bib0210","doi-asserted-by":"crossref","first-page":"1320","DOI":"10.1038\/s41591-020-1041-y","article-title":"Minimum information about clinical artificial intelligence modeling: the mi-claim checklist","volume":"26","author":"Norgeot","year":"2020","journal-title":"Nat. Med."},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0215","series-title":"ITU\/WHO Focus Group on Artificial Intelligence for Health (FG-AI4H) \u2013 Meeting K, Vol. K","article-title":"Good practices for health applications of machine learning: considerations for manufacturers and regulators","author":"Johner","year":"2021"},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0220","series-title":"Machine Learning for Health","first-page":"280","article-title":"Ml4h auditing: from paper to practice","author":"Oala","year":"2020"},{"issue":"1","key":"10.1016\/j.ijmedinf.2021.104510_bib0225","doi-asserted-by":"crossref","first-page":"51","DOI":"10.7326\/M18-1376","article-title":"Probast: a tool to assess the risk of bias and applicability of prediction model studies","volume":"170","author":"Wolff","year":"2019","journal-title":"Ann. Intern. Med."},{"issue":"2","key":"10.1016\/j.ijmedinf.2021.104510_bib0230","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1161\/CIRCULATIONAHA.114.014508","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (tripod) the tripod statement","volume":"131","author":"Collins","year":"2015","journal-title":"Circulation"},{"issue":"10205","key":"10.1016\/j.ijmedinf.2021.104510_bib0235","doi-asserted-by":"crossref","first-page":"1225","DOI":"10.1016\/S0140-6736(19)31819-7","article-title":"Extension of the consort and spirit statements","volume":"394","author":"Liu","year":"2019","journal-title":"Lancet"},{"issue":"6","key":"10.1016\/j.ijmedinf.2021.104510_bib0240","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1038\/s41591-020-0941-1","article-title":"Developing specific reporting guidelines for diagnostic accuracy studies assessing ai interventions: the stard-AI steering group","volume":"26","author":"Sounderajah","year":"2020","journal-title":"Nat. Med."},{"issue":"12","key":"10.1016\/j.ijmedinf.2021.104510_bib0245","doi-asserted-by":"crossref","first-page":"2011","DOI":"10.1093\/jamia\/ocaa088","article-title":"Minimar (minimum information for medical AI reporting): developing reporting standards for artificial intelligence in health care","volume":"27","author":"Hernandez-Boussard","year":"2020","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0250","series-title":"Proceedings of the 4th International Conference on the Practical Applications of Knowledge Discovery and Data Mining, vol. 1","article-title":"Crisp-dm: towards a standard process model for data mining","author":"Wirth","year":"2000"},{"issue":"3","key":"10.1016\/j.ijmedinf.2021.104510_bib0255","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1097\/01.ede.0000158224.50593.e3","article-title":"The cross-sectional cohort study: an underutilized design","volume":"16","author":"Hudson","year":"2005","journal-title":"Epidemiology"},{"issue":"3","key":"10.1016\/j.ijmedinf.2021.104510_bib0260","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/j.jcin.2008.01.008","article-title":"Randomized clinical trials and observational studies: guidelines for assessing respective strengths and limitations","volume":"1","author":"Hannan","year":"2008","journal-title":"JACC Cardiovasc. Interv."},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0265","series-title":"Content Analysis: An Introduction to Its Methodology","author":"Krippendorff","year":"2018"},{"issue":"5","key":"10.1016\/j.ijmedinf.2021.104510_bib0270","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1037\/h0031619","article-title":"Measuring nominal scale agreement among many raters","volume":"76","author":"Fleiss","year":"1971","journal-title":"Psychol. Bull."},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0275","series-title":"The Delphi Method","author":"Linstone","year":"1975"},{"issue":"4","key":"10.1016\/j.ijmedinf.2021.104510_bib0280","doi-asserted-by":"crossref","first-page":"624","DOI":"10.1373\/49.4.624","article-title":"Loinc, a universal standard for identifying laboratory observations: a 5-year update","volume":"49","author":"McDonald","year":"2003","journal-title":"Clin. Chem."},{"issue":"6","key":"10.1016\/j.ijmedinf.2021.104510_bib0285","doi-asserted-by":"crossref","first-page":"1003","DOI":"10.1097\/j.pain.0000000000000160","article-title":"A classification of chronic pain for icd-11","volume":"156","author":"Treede","year":"2015","journal-title":"Pain"},{"issue":"1","key":"10.1016\/j.ijmedinf.2021.104510_bib0290","first-page":"1","article-title":"Forty years of snomed: a literature review","volume":"8","author":"Cornet","year":"2008","journal-title":"BMC Med. Inform. Decis. Mak."},{"issue":"8","key":"10.1016\/j.ijmedinf.2021.104510_bib0295","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2013-002847","article-title":"Comparison of imputation methods for missing laboratory data in medicine","volume":"3","author":"Waljee","year":"2013","journal-title":"BMJ Open"},{"issue":"12","key":"10.1016\/j.ijmedinf.2021.104510_bib0300","doi-asserted-by":"crossref","first-page":"2976","DOI":"10.1016\/j.csda.2010.03.004","article-title":"Measuring the prediction error. a comparison of cross-validation, bootstrap and covariance penalty methods","volume":"54","author":"Borra","year":"2010","journal-title":"Comput. Stat. Data Anal."},{"issue":"4","key":"10.1016\/j.ijmedinf.2021.104510_bib0305","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2382577.2382579","article-title":"Leakage in data mining: formulation, detection, and avoidance","volume":"6","author":"Kaufman","year":"2012","journal-title":"ACM Trans. Knowl. Discov. Data (TKDD)"},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0310","series-title":"Improving Reproducibility in Machine Learning Research (a Report From the Neurips 2019 Reproducibility Program)","author":"Pineau","year":"2020"},{"issue":"1","key":"10.1016\/j.ijmedinf.2021.104510_bib0315","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12916-019-1466-7","article-title":"Calibration: the achilles heel of predictive analytics","volume":"17","author":"Van Calster","year":"2019","journal-title":"BMC Med."},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0320","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.jclinepi.2015.04.005","article-title":"Prediction models need appropriate internal, internal-external, and external validation","volume":"69","author":"Steyerberg","year":"2016","journal-title":"J. Clin. Epidemiol."},{"issue":"4","key":"10.1016\/j.ijmedinf.2021.104510_bib0325","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1016\/j.carj.2019.06.002","article-title":"Sample-size determination methodologies for machine learning in medical imaging research: a systematic review","volume":"70","author":"Balki","year":"2019","journal-title":"Can. Assoc. Radiol. J."},{"issue":"1","key":"10.1016\/j.ijmedinf.2021.104510_bib0330","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12911-020-01224-9","article-title":"As if sand were stone. New concepts and metrics to probe the ground on which to build trustable AI","volume":"20","author":"Cabitza","year":"2020","journal-title":"BMC Med. Inform. Decis. Mak."},{"issue":"9","key":"10.1016\/j.ijmedinf.2021.104510_bib0335","doi-asserted-by":"crossref","first-page":"826","DOI":"10.1016\/S0895-4356(03)00207-5","article-title":"External validation is necessary in prediction research: a clinical example","volume":"56","author":"Bleeker","year":"2003","journal-title":"J. Clin. Epidemiol."},{"issue":"8","key":"10.1016\/j.ijmedinf.2021.104510_bib0340","doi-asserted-by":"crossref","first-page":"e0237009","DOI":"10.1371\/journal.pone.0237009","article-title":"The data representativeness criterion: predicting the performance of supervised classification based on data set similarity","volume":"15","author":"Schat","year":"2020","journal-title":"PLOS ONE"},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0345","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.jclinepi.2021.02.011","article-title":"External validation of clinical prediction models: simulation-based sample size calculations were more reliable than rules-of-thumb","volume":"135","author":"Snell","year":"2021","journal-title":"J. Clin. Epidemiol."},{"issue":"8","key":"10.1016\/j.ijmedinf.2021.104510_bib0350","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1016\/j.jclinepi.2015.02.010","article-title":"The precision-recall curve overcame the optimism of the receiver operating characteristic curve in rare diseases","volume":"68","author":"Ozenne","year":"2015","journal-title":"J. Clin. Epidemiol."},{"issue":"1","key":"10.1016\/j.ijmedinf.2021.104510_bib0355","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13040-021-00244-z","article-title":"The matthews correlation coefficient (mcc) is more reliable than balanced accuracy, bookmaker informedness, and markedness in two-class confusion matrix evaluation","volume":"14","author":"Chicco","year":"2021","journal-title":"BioData Min."},{"issue":"1","key":"10.1016\/j.ijmedinf.2021.104510_bib0360","first-page":"27","article-title":"Internal versus external cluster validation indexes","volume":"5","author":"Rend\u00f3n","year":"2011","journal-title":"Int. J. Comput. Commun."},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0365","series-title":"2005 IEEE Engineering in Medicine and Biology 27th Annual Conference","first-page":"7186","article-title":"Evaluation of segmentation algorithms for medical imaging","author":"Fenster","year":"2006"},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0370","series-title":"International Conference on Learning Representations","article-title":"Measuring the reliability of reinforcement learning algorithms","author":"Chan","year":"2020"},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0375","first-page":"1","article-title":"Statistical comparisons of classifiers over multiple data sets","volume":"7","author":"Dem\u0161ar","year":"2006","journal-title":"J. Mach. Learn. Res."},{"issue":"D7","key":"10.1016\/j.ijmedinf.2021.104510_bib0380","doi-asserted-by":"crossref","first-page":"7183","DOI":"10.1029\/2000JD900719","article-title":"Summarizing multiple aspects of model performance in a single diagram","volume":"106","author":"Taylor","year":"2001","journal-title":"J. Geophys. Res. Atmos."},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0385","article-title":"Net benefit approaches to the evaluation of prediction models, molecular markers, and diagnostic tests","volume":"352","author":"Vickers","year":"2016","journal-title":"BMJ"},{"issue":"6","key":"10.1016\/j.ijmedinf.2021.104510_bib0390","doi-asserted-by":"crossref","first-page":"796","DOI":"10.1016\/j.eururo.2018.08.038","article-title":"Reporting and interpreting decision curve analysis: a guide for investigators","volume":"74","author":"Van Calster","year":"2018","journal-title":"Eur. Urol."},{"issue":"1","key":"10.1016\/j.ijmedinf.2021.104510_bib0395","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12916-019-1425-3","article-title":"Three myths about risk thresholds for prediction models","volume":"17","author":"Wynants","year":"2019","journal-title":"BMC Med."},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0400","first-page":"1","article-title":"The importance of interpretability and visualization in machine learning for applications in medicine and health care","author":"Vellido","year":"2019","journal-title":"Neural Comput. Appl."},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0405","first-page":"9269","article-title":"The many Shapley values for model explanation","author":"Sundararajan","year":"2020","journal-title":"International Conference on Machine Learning"},{"issue":"4","key":"10.1016\/j.ijmedinf.2021.104510_bib0410","doi-asserted-by":"crossref","first-page":"e1312","DOI":"10.1002\/widm.1312","article-title":"Causability and explainability of artificial intelligence in medicine","volume":"9","author":"Holzinger","year":"2019","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0415","first-page":"1","article-title":"Measuring the quality of explanations: the system causability scale (scs)","author":"Holzinger","year":"2020","journal-title":"KI-K\u00fcnstliche Intell."},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0420","series-title":"Metrics for Explainable AI: Challenges and Prospects","author":"Hoffman","year":"2018"},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0425","first-page":"269","article-title":"The fidelity of global surrogates in interpretable machine learning","volume":"2020","author":"Schwartzenberg","year":"2020","journal-title":"BNAIC\/BeneLearn"},{"issue":"11","key":"10.1016\/j.ijmedinf.2021.104510_bib0430","doi-asserted-by":"crossref","first-page":"e1002689","DOI":"10.1371\/journal.pmed.1002689","article-title":"Machine learning in medicine: addressing ethical challenges","volume":"15","author":"Vayena","year":"2018","journal-title":"PLOS Med."},{"issue":"12","key":"10.1016\/j.ijmedinf.2021.104510_bib0435","doi-asserted-by":"crossref","first-page":"866","DOI":"10.7326\/M18-1990","article-title":"Ensuring fairness in machine learning to advance health equity","volume":"169","author":"Rajkomar","year":"2018","journal-title":"Ann. Intern. Med."},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0440","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1145\/3368555.3384468","article-title":"Hidden stratification causes clinically meaningful failures in machine learning for medical imaging","author":"Oakden-Rayner","year":"2020","journal-title":"Proceedings of the ACM Conference on Health, Inference, and Learning"},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0445","series-title":"The AI Gambit-Leveraging Artificial Intelligence to Combat Climate Change: Opportunities, Challenges, and Recommendations","author":"Cowls","year":"2021"},{"issue":"12","key":"10.1016\/j.ijmedinf.2021.104510_bib0450","doi-asserted-by":"crossref","first-page":"1651","DOI":"10.1093\/jamia\/ocz130","article-title":"Predictive analytics in health care: how can we know it works?","volume":"26","author":"Van Calster","year":"2019","journal-title":"J. Am. Med. Inform. Assoc."},{"issue":"2","key":"10.1016\/j.ijmedinf.2021.104510_bib0455","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1177\/0272989X9101100203","article-title":"The efficacy of diagnostic imaging","volume":"11","author":"Fryback","year":"1991","journal-title":"Med. Decis. Mak."},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0460","first-page":"1","article-title":"Artificial intelligence in radiology: 100 commercially available products and their scientific evidence","author":"van Leeuwen","year":"2021","journal-title":"Eur. Radiol."},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0465","series-title":"Technology Readiness Levels for Machine Learning Systems","author":"Lavin","year":"2021"},{"key":"10.1016\/j.ijmedinf.2021.104510_bib0470","first-page":"1002","article-title":"Comparison of prediction model performance updating protocols: using a data-driven testing procedure to guide updating","author":"Davis","year":"2019","journal-title":"AMIA Annual Symposium Proceedings, Vol. 2019"}],"container-title":["International Journal of Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1386505621001362?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1386505621001362?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T02:58:29Z","timestamp":1761361109000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1386505621001362"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9]]},"references-count":94,"alternative-id":["S1386505621001362"],"URL":"https:\/\/doi.org\/10.1016\/j.ijmedinf.2021.104510","relation":{},"ISSN":["1386-5056"],"issn-type":[{"value":"1386-5056","type":"print"}],"subject":[],"published":{"date-parts":[[2021,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"The need to separate the wheat from the chaff in medical informatics","name":"articletitle","label":"Article Title"},{"value":"International Journal of Medical Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ijmedinf.2021.104510","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"simple-article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2021 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"104510"}}