{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T20:36:47Z","timestamp":1769200607854,"version":"3.49.0"},"reference-count":42,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/100004325","name":"AstraZeneca","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004325","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,8,18]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>To train and test a model predicting chronic kidney disease (CKD) using the Generalized Additive2 Model (GA2M), and compare it with other models being obtained with traditional or machine learning approaches.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials<\/jats:title>\n                  <jats:p>We adopted the Health Search Database (HSD) which is a representative longitudinal database containing electronic healthcare records of approximately 2 million adults.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>We selected all patients aged 15\u00a0years or older being active in HSD between January 1, 2018 and December 31, 2020 with no prior diagnosis of CKD. The following models were trained and tested using 20 candidate determinants for incident CKD: logistic regression, Random Forest, Gradient Boosting Machines (GBMs), GAM, and GA2M. Their prediction performances were compared by calculating Area Under Curve (AUC) and Average Precision (AP).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Comparing the predictive performances of the 7 models, the AUC and AP for GBM and GA2M showed the highest values which were equal to 88.9%, 88.8% and 21.8%, 21.1%, respectively. These 2 models outperformed the others including logistic regression. In contrast to GBMs, GA2M kept the interpretability of variable combinations, including interactions and nonlinearities assessment.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Discussion<\/jats:title>\n                  <jats:p>Although GA2M is slightly less performant than light GBM, it is not \u201cblack-box\u201d algorithm, so being simply interpretable using shape and heatmap functions. This evidence supports the fact machine learning techniques should be adopted in case of complex algorithms such as those predicting the risk of CKD.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>The GA2M was reliably performant in predicting CKD in primary care. A related decision support system might be therefore implemented.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocad097","type":"journal-article","created":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T06:55:16Z","timestamp":1687071316000},"page":"1494-1502","source":"Crossref","is-referenced-by-count":9,"title":["To predict the risk of chronic kidney disease (CKD) using Generalized Additive2 Models (GA2M)"],"prefix":"10.1093","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4342-9128","authenticated-orcid":false,"given":"Francesco","family":"Lapi","sequence":"first","affiliation":[{"name":"Health Search, Italian College of General Practitioners and Primary Care , Florence, Italy"}]},{"given":"Lorenzo","family":"Nuti","sequence":"additional","affiliation":[{"name":"Genomedics SRL , Florence, Italy"}]},{"given":"Ettore","family":"Marconi","sequence":"additional","affiliation":[{"name":"Health Search, Italian College of General Practitioners and Primary Care , Florence, Italy"}]},{"given":"Gerardo","family":"Medea","sequence":"additional","affiliation":[{"name":"Italian College of General Practitioners and Primary Care , Florence, Italy"}]},{"given":"Iacopo","family":"Cricelli","sequence":"additional","affiliation":[{"name":"Genomedics SRL , Florence, Italy"}]},{"given":"Matteo","family":"Papi","sequence":"additional","affiliation":[{"name":"AstraZeneca Italy, MIND , Milan, Italy"}]},{"given":"Marco","family":"Gorini","sequence":"additional","affiliation":[{"name":"AstraZeneca Italy, MIND , Milan, Italy"}]},{"given":"Matteo","family":"Fiorani","sequence":"additional","affiliation":[{"name":"Data Life SRL , Florence, Italy"}]},{"given":"Gaetano","family":"Piccinocchi","sequence":"additional","affiliation":[{"name":"Italian College of General Practitioners and Primary Care , Florence, Italy"}]},{"given":"Claudio","family":"Cricelli","sequence":"additional","affiliation":[{"name":"Italian College of General Practitioners and Primary Care , Florence, Italy"}]}],"member":"286","published-online":{"date-parts":[[2023,6,18]]},"reference":[{"issue":"7","key":"2023081808484484900_ocad097-B1","doi-asserted-by":"crossref","first-page":"e0158765","DOI":"10.1371\/journal.pone.0158765","article-title":"Global prevalence of chronic kidney disease\u2014a systematic review and meta-analysis","volume":"11","author":"Hill","year":"2016","journal-title":"PLoS One"},{"issue":"10225","key":"2023081808484484900_ocad097-B2","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1016\/S0140-6736(20)30045-3","article-title":"Global, regional, and national burden of chronic kidney disease, 1990\u20132017: a systematic analysis for the Global Burden of Disease Study 2017","volume":"395","author":"Bikbov","year":"2020","journal-title":"Lancet"},{"issue":"8","key":"2023081808484484900_ocad097-B3","doi-asserted-by":"crossref","first-page":"2057","DOI":"10.1007\/s40620-022-01353-6","article-title":"The Disease Awareness Innovation Network\u2019 for chronic kidney disease identification in general practice","volume":"35","author":"Pesce","year":"2022","journal-title":"J Nephrol"},{"issue":"3","key":"2023081808484484900_ocad097-B4","doi-asserted-by":"crossref","first-page":"60","DOI":"10.33590\/emj\/10063690","article-title":"Findings and implications of the REVEAL-CKD study investigating the global prevalence of undiagnosed stage G3 chronic kidney disease","volume":"7","author":"Tangri","year":"2022","journal-title":"EMJ"},{"issue":"1","key":"2023081808484484900_ocad097-B5","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.kint.2020.10.012","article-title":"The case for early identification and intervention of chronic kidney disease: conclusions from a Kidney Disease: Improving Global Outcomes (KDIGO) Controversies Conference","volume":"99","author":"Shlipak","year":"2021","journal-title":"Kidney Int"},{"issue":"5","key":"2023081808484484900_ocad097-B6","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1053\/j.ajkd.2014.01.416","article-title":"KDOQI US commentary on the 2012 KDIGO clinical practice guideline for the evaluation and management of CKD","volume":"63","author":"Inker","year":"2014","journal-title":"Am J Kidney Dis"},{"issue":"21","key":"2023081808484484900_ocad097-B7","doi-asserted-by":"crossref","first-page":"2104","DOI":"10.1001\/jama.2019.17379","article-title":"Development of risk prediction equations for incident chronic kidney disease","volume":"322","author":"Nelson","year":"2019","journal-title":"JAMA"},{"issue":"1","key":"2023081808484484900_ocad097-B8","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1186\/1471-2296-11-49","article-title":"Predicting the risk of chronic kidney disease in men and women in England and Wales: prospective derivation and external validation of the QKidney\u00ae scores","volume":"11","author":"Hippisley-Cox","year":"2010","journal-title":"BMC Fam Pract"},{"issue":"9","key":"2023081808484484900_ocad097-B9","doi-asserted-by":"crossref","first-page":"836","DOI":"10.1016\/j.amjmed.2010.05.010","article-title":"A prediction model for the risk of incident chronic kidney disease","volume":"123","author":"Chien","year":"2010","journal-title":"Am J Med"},{"issue":"1","key":"2023081808484484900_ocad097-B10","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1186\/s12882-021-02474-z","article-title":"Chronic kidney disease diagnosis using decision tree algorithms","volume":"22","author":"Ilyas","year":"2021","journal-title":"BMC Nephrol"},{"key":"2023081808484484900_ocad097-B11","doi-asserted-by":"crossref","first-page":"n2281","DOI":"10.1136\/bmj.n2281","article-title":"Risk of bias in studies on prediction models developed using supervised machine learning techniques: systematic review","volume":"375","author":"Andaur Navarro","year":"2021","journal-title":"BMJ"},{"issue":"10","key":"2023081808484484900_ocad097-B12","doi-asserted-by":"crossref","first-page":"1419","DOI":"10.1093\/jamia\/ocy068","article-title":"Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review","volume":"25","author":"Xiao","year":"2018","journal-title":"J Am Med Inform Assoc"},{"issue":"3","key":"2023081808484484900_ocad097-B13","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1016\/j.jclinepi.2012.06.020","article-title":"A systematic review finds prediction models for chronic kidney disease were poorly reported and often developed using inappropriate methods","volume":"66","author":"Collins","year":"2013","journal-title":"J Clin Epidemiol"},{"key":"2023081808484484900_ocad097-B14","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"},{"key":"2023081808484484900_ocad097-B15","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.jclinepi.2020.03.002","article-title":"Logistic regression was as good as machine learning for predicting major chronic diseases","volume":"122","author":"Nusinovici","year":"2020","journal-title":"J Clin Epidemiol"},{"key":"2023081808484484900_ocad097-B16","first-page":"623","article-title":"Accurate intelligible models with pairwise interactions","volume":"Part F128815","author":"Lou","year":"2013","journal-title":"Proc ACM SIGKDD Int Conf Knowl Discov Data Min"},{"key":"2023081808484484900_ocad097-B17","first-page":"1721","article-title":"Intelligible models for healthcare: predicting pneumonia risk and hospital 30-day readmission","volume":"August","author":"Caruana","year":"2015","journal-title":"Proc ACM SIGKDD Int Conf Knowl Discov Data Min"},{"key":"2023081808484484900_ocad097-B18","doi-asserted-by":"crossref","first-page":"814","DOI":"10.1007\/978-1-4419-9863-7_1197","article-title":"Generalized additive models","author":"Higdon","year":"2013","journal-title":"Encyclopedia of Systems Biology"},{"issue":"5","key":"2023081808484484900_ocad097-B19","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1177\/0333102419889351","article-title":"Epidemiology and determinants of chronic migraine: a real-world cohort study, with nested case-control analysis, in primary care in Italy","volume":"40","author":"Marconi","year":"2020","journal-title":"Cephalalgia"},{"issue":"1","key":"2023081808484484900_ocad097-B20","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1002\/ijc.30061","article-title":"Risk of prostate cancer in low-dose aspirin users: a retrospective cohort study","volume":"139","author":"Lapi","year":"2016","journal-title":"Int J Cancer"},{"key":"2023081808484484900_ocad097-B21","doi-asserted-by":"crossref","first-page":"692","DOI":"10.1055\/s-0040-1701483","article-title":"Derivation and validation of a prediction model for venous thromboembolism in primary care","volume":"120","author":"Dentali","year":"2020","journal-title":"Thromb Haemost"},{"issue":"6","key":"2023081808484484900_ocad097-B22","doi-asserted-by":"crossref","first-page":"884","DOI":"10.1016\/j.jval.2015.05.004","article-title":"Development and validation of a score for adjusting health care costs in general practice","volume":"18","author":"Lapi","year":"2015","journal-title":"Value Health"},{"issue":"9","key":"2023081808484484900_ocad097-B23","doi-asserted-by":"crossref","first-page":"1586","DOI":"10.2215\/CJN.10481013","article-title":"Risk of ESRD and death in patients with CKD not referred to a nephrologist. A 7-year prospective study","volume":"9","author":"Minutolo","year":"2014","journal-title":"Clin J Am Soc Nephrol"},{"issue":"5","key":"2023081808484484900_ocad097-B24","doi-asserted-by":"crossref","first-page":"e0127071","DOI":"10.1371\/journal.pone.0127071","article-title":"Independent role of underlying kidney disease on renal prognosis of patients with chronic kidney disease under nephrology care","volume":"10","author":"De Nicola","year":"2015","journal-title":"PLoS One"},{"issue":"3","key":"2023081808484484900_ocad097-B25","doi-asserted-by":"crossref","first-page":"444","DOI":"10.1053\/j.ajkd.2008.03.002","article-title":"Detection and awareness of moderate to advanced CKD by primary care practitioners: a cross-sectional study from Italy","volume":"52","author":"Minutolo","year":"2008","journal-title":"Am J Kidney Dis"},{"key":"2023081808484484900_ocad097-B26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2021\/1004767","article-title":"Diagnosis of chronic kidney disease using effective classification algorithms and recursive feature elimination techniques","volume":"2021","author":"Senan","year":"2021","journal-title":"J Healthc Eng"},{"issue":"2","key":"2023081808484484900_ocad097-B27","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1016\/j.jclinepi.2014.11.010","article-title":"Transparent reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): the TRIPOD statement","volume":"68","author":"Collins","year":"2015","journal-title":"J Clin Epidemiol"},{"key":"2023081808484484900_ocad097-B28","first-page":"51","article-title":"PROBAST: a tool to assess the risk of bias and applicability of prediction model studies","author":"Wolff","year":"2019"},{"key":"2023081808484484900_ocad097-B29","doi-asserted-by":"crossref","first-page":"715320","DOI":"10.3389\/fdata.2021.715320","article-title":"Weighting methods for rare event identification from imbalanced datasets","volume":"4","author":"He","year":"2021","journal-title":"Front Big Data"},{"key":"2023081808484484900_ocad097-B30","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1016\/j.jclinepi.2021.11.023","article-title":"Missing data is poorly handled and reported in prediction model studies using machine learning: a literature review","volume":"142","author":"Nijman","year":"2022","journal-title":"J Clin Epidemiol"},{"issue":"10","key":"2023081808484484900_ocad097-B31","doi-asserted-by":"crossref","first-page":"1087","DOI":"10.1016\/j.jclinepi.2006.01.014","article-title":"Review: a gentle introduction to imputation of missing values","volume":"59","author":"Donders","year":"2006","journal-title":"J Clin Epidemiol"},{"issue":"8","key":"2023081808484484900_ocad097-B32","doi-asserted-by":"crossref","first-page":"1244","DOI":"10.1093\/jamia\/ocaa096","article-title":"Fold-stratified cross-validation for unbiased and privacy-preserving federated learning","volume":"27","author":"Bey","year":"2020","journal-title":"J Am Med Inform Assoc"},{"key":"2023081808484484900_ocad097-B33","article-title":". 3rd ed. Hoboken, NJ: Wiley; 2019","author":"Little"},{"issue":"1","key":"2023081808484484900_ocad097-B34","doi-asserted-by":"crossref","first-page":"55","DOI":"10.7326\/M14-0697","article-title":"Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): the TRIPOD statement","volume":"162","author":"Collins","year":"2015","journal-title":"Ann Intern Med"},{"issue":"1","key":"2023081808484484900_ocad097-B35","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1097\/EDE.0b013e3181c30fb2","article-title":"Assessing the performance of prediction models: a framework for traditional and novel measures","volume":"21","author":"Steyerberg","year":"2010","journal-title":"Epidemiology"},{"key":"2023081808484484900_ocad097-B36","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1007\/978-0-387-39940-9_482","article-title":"Average precision","author":"Zhang","year":"2009","journal-title":"Encyclopedia of Database Systems"},{"issue":"11","key":"2023081808484484900_ocad097-B37","doi-asserted-by":"crossref","first-page":"1127","DOI":"10.1093\/oxfordjournals.aje.a009592","article-title":"Slopes of a receiver operating characteristic curve and likelihood ratios for a diagnostic test","volume":"148","author":"Choi","year":"1998","journal-title":"Am J Epidemiol"},{"key":"2023081808484484900_ocad097-B38","author":"Sox","year":"2013"},{"key":"2023081808484484900_ocad097-B39","first-page":"1","article-title":"Statistical comparisons of classifiers over multiple data sets","volume":"7","author":"Demsar","year":"2006","journal-title":"J Mach Learn Res"},{"key":"2023081808484484900_ocad097-B40","first-page":"1","article-title":"Clinically applicable machine learning approaches to identify attributes of chronic kidney disease (CKD) for use in low-cost diagnostic screening","volume":"9","author":"Rashed-Al-Mahfuz","year":"2021","journal-title":"IEEE J Transl Eng Health Med"},{"key":"2023081808484484900_ocad097-B41","author":"X Report Health Search","year":"2017"},{"issue":"1","key":"2023081808484484900_ocad097-B42","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1002\/sim.8766","article-title":"Minimum sample size for external validation of a clinical prediction model with a continuous outcome","volume":"40","author":"Archer","year":"2021","journal-title":"Stat Med"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/30\/9\/1494\/51141555\/ocad097.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/30\/9\/1494\/51141555\/ocad097.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T10:36:05Z","timestamp":1692354965000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/30\/9\/1494\/7200061"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":42,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2023,6,18]]},"published-print":{"date-parts":[[2023,8,18]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocad097","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,9,1]]},"published":{"date-parts":[[2023,6,18]]}}}