{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:06:18Z","timestamp":1782846378993,"version":"3.54.5"},"reference-count":36,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec sec-type=\"background\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Autosomal dominant polycystic kidney disease (ADPKD), characterized by progressive cyst growth and renal decline, is the leading genetic cause of end\u2010stage renal disease.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"objective\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aims to develop and validate machine learning (ML) models for predicting the risk of progression to dialysis in patients with ADPKD using a nationwide administrative database. Early identification of high-risk patients is critical for timely monitoring.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"methods\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective cohort study used data from Taiwan\u2019s National Health Insurance Research Database (2007\u20102018) to identify newly diagnosed patients with ADPKD. Six ML algorithms, including logistic regression, random forest, and extreme gradient boosting (XGBoost), were employed to predict progression to dialysis. Models were developed using 10-fold cross-validation, with the Synthetic Minority Oversampling Technique applied within training folds to address class imbalance. An ensemble-based feature selection strategy was implemented to identify the most robust predictors and optimize final model performance. Model evaluation was conducted using a strict temporal split.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"results\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The study included 1856 patients with ADPKD, of whom 302 (16.27%) progressed to dialysis. Multivariable Cox regression identified several significant risk factors, including age 66 years and older (hazard ratio [HR] 4.63, 95% CI 2.71\u20107.92;\n                      <jats:italic>P<\/jats:italic>\n                      &lt;.001), anemia (HR 4.33, 95% CI 3.25\u20105.78;\n                      <jats:italic>P<\/jats:italic>\n                      &lt;.001), congestive heart failure (HR 1.81, 95% CI 1.29\u20102.54;\n                      <jats:italic>P<\/jats:italic>\n                      &lt;.001), and acute kidney injury (HR 1.69, 95% CI 1.19\u20102.41;\n                      <jats:italic>P<\/jats:italic>\n                      =.003). Among the ML models, the XGBoost model, using an optimized set of 27 features, demonstrated the highest predictive performance on the held-out temporal test set (accuracy 98.3%; area under the curve 0.955;\n                      <jats:italic>F<\/jats:italic>\n                      <jats:sub>1<\/jats:sub>\n                      -score 0.800; Brier score 0.022). The top predictors in the XGBoost model largely aligned with age, comorbidity burden, anemia, and cardiovascular disease markers. Medication use (eg, anticoagulants, loop diuretics, febuxostat) was also among the most influential predictors; however, medication-related predictors should be interpreted as proxies for disease complexity rather than direct risk modulators.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"conclusions\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>ML models can predict dialysis risk in patients with ADPKD using administrative data with temporal validation. This approach may support risk stratification by helping identify individuals at higher predicted risk who may warrant closer monitoring and further specialist evaluation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/80343","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T18:56:01Z","timestamp":1773687361000},"page":"e80343-e80343","source":"Crossref","is-referenced-by-count":0,"title":["Machine Learning Prediction of Progression to Dialysis in Patients With Polycystic Kidney Disease: Population-Based Retrospective Cohort Study"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4048-4444","authenticated-orcid":false,"given":"Cheng-Hao","family":"Chang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8278-0033","authenticated-orcid":false,"given":"Mingchih","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3561-4689","authenticated-orcid":false,"given":"Ming-Hsien","family":"Tsai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0872-8664","authenticated-orcid":false,"given":"Yen-Chun","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3534-1978","authenticated-orcid":false,"given":"Hung-Hsiang","family":"Liou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2854-8361","authenticated-orcid":false,"given":"Ben-Chang","family":"Shia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9463-3826","authenticated-orcid":false,"given":"Chingying","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1302-1885","authenticated-orcid":false,"given":"Yu-Wei","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"key":"R1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.med.60.101707.125712","article-title":"Polycystic kidney disease","volume":"60","author":"Harris","journal-title":"Annu Rev Med"},{"issue":"2S","key":"R2","doi-asserted-by":"publisher","first-page":"S1","DOI":"10.1016\/j.kint.2024.07.009","article-title":"KDIGO 2025 clinical practice guideline for the evaluation, management, and treatment of autosomal dominant polycystic kidney disease (ADPKD)","volume":"107","author":"Kidney Disease: Improving Global Outcomes (KDIGO) ADPKD Work Group","journal-title":"Kidney Int"},{"issue":"4","key":"R3","doi-asserted-by":"publisher","first-page":"244","DOI":"10.7326\/0003-4819-139-4-200308190-00006","article-title":"Progression of chronic kidney disease: the role of blood pressure control, proteinuria, and angiotensin-converting enzyme inhibition: a patient-level meta-analysis","volume":"139","author":"Jafar","journal-title":"Ann Intern Med"},{"issue":"10","key":"R4","doi-asserted-by":"publisher","first-page":"975","DOI":"10.1056\/NEJMc1500332","article-title":"Blood pressure in early autosomal dominant polycystic kidney disease","volume":"372","author":"Benck","journal-title":"N Engl J Med"},{"issue":"4","key":"R5","doi-asserted-by":"publisher","first-page":"989","DOI":"10.1016\/j.kint.2020.04.053","article-title":"Salt, but not protein intake, is associated with accelerated disease progression in autosomal dominant polycystic kidney disease","volume":"98","author":"Kramers","journal-title":"Kidney Int"},{"issue":"6","key":"R6","doi-asserted-by":"publisher","first-page":"908","DOI":"10.2215\/CJN.16871020","article-title":"Overweight and obesity and progression of ADPKD","volume":"16","author":"Nowak","journal-title":"Clin J Am Soc Nephrol"},{"issue":"25","key":"R7","doi-asserted-by":"publisher","first-page":"2407","DOI":"10.1056\/NEJMoa1205511","article-title":"Tolvaptan in patients with autosomal dominant polycystic kidney disease","volume":"367","author":"Torres","journal-title":"N Engl J Med"},{"issue":"6","key":"R8","doi-asserted-by":"publisher","first-page":"2462","DOI":"10.1073\/pnas.1011498108","article-title":"Activating AMP-activated protein kinase (AMPK) slows renal cystogenesis","volume":"108","author":"Takiar","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"1","key":"R9","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1016\/j.atherosclerosis.2010.07.053","article-title":"Effect of atorvastatin on kidney function in chronic kidney disease: a randomised double-blind placebo-controlled trial","volume":"213","author":"Fassett","journal-title":"Atherosclerosis"},{"issue":"1","key":"R10","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1681\/ASN.2013101138","article-title":"Imaging classification of autosomal dominant polycystic kidney disease: a simple model for selecting patients for clinical trials","volume":"26","author":"Irazabal","journal-title":"J Am Soc Nephrol"},{"issue":"3","key":"R11","doi-asserted-by":"publisher","first-page":"942","DOI":"10.1681\/ASN.2015010016","article-title":"The PROPKD score: a new algorithm to predict renal survival in autosomal dominant polycystic kidney disease","volume":"27","author":"Cornec-Le Gall","journal-title":"J Am Soc Nephrol"},{"issue":"6","key":"R12","doi-asserted-by":"publisher","first-page":"911","DOI":"10.1053\/j.ajkd.2018.01.051","article-title":"Artificial intelligence can predict GFR decline during the course of ADPKD","volume":"71","author":"Niel","journal-title":"Am J Kidney Dis"},{"issue":"6","key":"R13","doi-asserted-by":"publisher","first-page":"1802","DOI":"10.1016\/j.ekir.2024.04.002","article-title":"Deep learning-based automated imaging classification of ADPKD","volume":"9","author":"Kim","journal-title":"Kidney Int Rep"},{"issue":"1","key":"R14","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-01779-0","article-title":"Automatic segmentation of kidneys using deep learning for total kidney volume quantification in autosomal dominant polycystic kidney disease","volume":"7","author":"Sharma","journal-title":"Sci Rep"},{"issue":"2","key":"R15","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.ekir.2023.10.029","article-title":"An artificial intelligence generated automated algorithm to measure total kidney volume in ADPKD","volume":"9","author":"Taylor","journal-title":"Kidney Int Rep"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.4178\/epih.e2018062","article-title":"Data resource profile: the National Health Insurance Research Database (NHIRD)","volume":"40","author":"Lin","journal-title":"Epidemiol Health"},{"issue":"2","key":"R17","doi-asserted-by":"publisher","first-page":"612","DOI":"10.1093\/ckj\/sfz184","article-title":"Diagnostic accuracy of administrative codes for autosomal dominant polycystic kidney disease in clinic patients with cystic kidney disease","volume":"14","author":"Kalatharan","journal-title":"Clin Kidney J"},{"key":"R18","doi-asserted-by":"publisher","DOI":"10.1186\/1472-6963-13-152","article-title":"Comparisons of medical utilizations and categorical diagnoses of emergency visits between the elderly with catastrophic illness certificates and those without","volume":"13","author":"Nan-Ping","journal-title":"BMC Health Serv Res"},{"issue":"6","key":"R19","doi-asserted-by":"publisher","first-page":"1312","DOI":"10.1002\/cpt.1722","article-title":"Association of statin and its lipophilicity with cardiovascular events in patients receiving chronic dialysis","volume":"107","author":"Wang","journal-title":"Clin Pharmacol Ther"},{"key":"R20","doi-asserted-by":"crossref","unstructured":"Hastie T Tibshirani R Friedman J . The Elements of Statistical Learning. Springer; 2009. [doi: 10.1007\/978-0-387-84858-7] ISBN: 978-0-387-84857-0","DOI":"10.1007\/978-0-387-84858-7"},{"key":"R21","unstructured":"Prokhorenkova L Gusev G Vorobev A Dorogush AV Gulin A . CatBoost: unbiased boosting with categorical features. Presented at: 32nd Conference on Neural Information Processing Systems (NeurIPS 2018); Dec 3-8, 2018; Montr\u00e9al, QC. URL: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2018\/file\/14491b756b3a51daac41c24863285549-Paper.pdf [Accessed 24-02-2026]"},{"issue":"1","key":"R22","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1007\/s10479-023-05691-x","article-title":"A framework to predict second primary lung cancer patients by using ensemble models","volume":"348","author":"Huang","journal-title":"Ann Oper Res"},{"issue":"1","key":"R23","doi-asserted-by":"publisher","DOI":"10.1186\/s12913-025-12218-6","article-title":"Machine learning-driven prediction of medical expenses in triple-vessel PCI patients using feature selection","volume":"25","author":"Chen","journal-title":"BMC Health Serv Res"},{"issue":"12","key":"R24","doi-asserted-by":"publisher","first-page":"2194","DOI":"10.1093\/ndt\/gft513","article-title":"Mechanisms and management of hypertension in autosomal dominant polycystic kidney disease","volume":"29","author":"Rahbari-Oskoui","journal-title":"Nephrol Dial Transplant"},{"issue":"4","key":"R25","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1159\/000343281","article-title":"Prevalence of cardiovascular events in patients with autosomal dominant polycystic kidney disease","volume":"36","author":"Helal","journal-title":"Am J Nephrol"},{"issue":"2","key":"R26","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1053\/j.ackd.2010.01.001","article-title":"Hypertension in autosomal dominant polycystic kidney disease","volume":"17","author":"Chapman","journal-title":"Adv Chronic Kidney Dis"},{"issue":"24","key":"R27","doi-asserted-by":"publisher","first-page":"2255","DOI":"10.1056\/NEJMoa1402685","article-title":"Blood pressure in early autosomal dominant polycystic kidney disease","volume":"371","author":"Schrier","journal-title":"N Engl J Med"},{"issue":"7","key":"R28","doi-asserted-by":"publisher","first-page":"980","DOI":"10.1093\/gerona\/glx229","article-title":"Measuring frailty in Medicare data: development and validation of a claims-based frailty index","volume":"73","author":"Kim","journal-title":"J Gerontol A Biol Sci Med Sci"},{"issue":"1","key":"R29","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-024-03649-9","article-title":"Representation of multimorbidity and frailty in the development and validation of kidney failure prognostic prediction models: a systematic review","volume":"22","author":"Walker","journal-title":"BMC Med"},{"key":"R30","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2022.837232","article-title":"Machine learning improves upon clinicians\u2019 prediction of end stage kidney disease","volume":"9","author":"Chuah","journal-title":"Front Med"},{"key":"R31","volume":"2024","author":"Li","journal-title":"AMIA Annu Symp Proc"},{"issue":"6","key":"R32","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1007\/s10157-020-01856-1","article-title":"Association between anemia and renal prognosis in autosomal dominant polycystic kidney disease: a retrospective study","volume":"24","author":"Ushio","journal-title":"Clin Exp Nephrol"},{"issue":"3","key":"R33","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1097\/MNH.0000000000000491","article-title":"Clinical evidence that treatment of metabolic acidosis slows the progression of chronic kidney disease","volume":"28","author":"Goraya","journal-title":"Curr Opin Nephrol Hypertens"},{"issue":"24","key":"R34","doi-asserted-by":"publisher","first-page":"2267","DOI":"10.1056\/NEJMoa1402686","article-title":"Angiotensin blockade in late autosomal dominant polycystic kidney disease","volume":"371","author":"Torres","journal-title":"N Engl J Med"},{"issue":"1","key":"R35","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1159\/000474961","article-title":"Treatment of persistent gross hematuria with tranexamic acid in autosomal dominant polycystic kidney disease","volume":"42","author":"Yao","journal-title":"Kidney Blood Press Res"},{"key":"R36","unstructured":"National health informatics project of the MOHW. Ministry of Health and Welfare. URL: https:\/\/dep.mohw.gov.tw\/DOS\/mp-113.html [Accessed 27-02-2026]"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e80343","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:13:47Z","timestamp":1782843227000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e80343"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":36,"URL":"https:\/\/doi.org\/10.2196\/80343","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,16]]},"article-number":"v14i2Se80343"}}