{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:13:09Z","timestamp":1784297589875,"version":"3.55.0"},"reference-count":61,"publisher":"JMIR Publications Inc.","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>A primary goal of precision medicine is to identify patient subgroups and infer their underlying disease processes with the aim of designing targeted interventions. Although several studies have identified patient subgroups, there is a considerable gap between the identification of patient subgroups and their modeling and interpretation for clinical applications.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to develop and evaluate a novel analytical framework for modeling and interpreting patient subgroups (MIPS) using a 3-step modeling approach: visual analytical modeling to automatically identify patient subgroups and their co-occurring comorbidities and determine their statistical significance and clinical interpretability; classification modeling to classify patients into subgroups and measure its accuracy; and prediction modeling to predict a patient\u2019s risk of an adverse outcome and compare its accuracy with and without patient subgroup information.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The MIPS framework was developed using bipartite networks to identify patient subgroups based on frequently co-occurring high-risk comorbidities, multinomial logistic regression to classify patients into subgroups, and hierarchical logistic regression to predict the risk of an adverse outcome using subgroup membership compared with standard logistic regression without subgroup membership. The MIPS framework was evaluated for 3 hospital readmission conditions: chronic obstructive pulmonary disease (COPD), congestive heart failure (CHF), and total hip arthroplasty\/total knee arthroplasty (THA\/TKA) (COPD: n=29,016; CHF: n=51,550; THA\/TKA: n=16,498). For each condition, we extracted cases defined as patients readmitted within 30 days of hospital discharge. Controls were defined as patients not readmitted within 90 days of discharge, matched by age, sex, race, and Medicaid eligibility.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In each condition, the visual analytical model identified patient subgroups that were statistically significant (Q=0.17, 0.17, 0.31; P&lt;.001, &lt;.001, &lt;.05), significantly replicated (Rand Index=0.92, 0.94, 0.89; P&lt;.001, &lt;.001, &lt;.01), and clinically meaningful to clinicians. In each condition, the classification model had high accuracy in classifying patients into subgroups (mean accuracy=99.6%, 99.34%, 99.86%). In 2 conditions (COPD and THA\/TKA), the hierarchical prediction model had a small but statistically significant improvement in discriminating between readmitted and not readmitted patients as measured by net reclassification improvement (0.059, 0.11) but not as measured by the C-statistic or integrated discrimination improvement.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Although the visual analytical models identified statistically and clinically significant patient subgroups, the results pinpoint the need to analyze subgroups at different levels of granularity for improving the interpretability of intra- and intercluster associations. The high accuracy of the classification models reflects the strong separation of patient subgroups, despite the size and density of the data sets. Finally, the small improvement in predictive accuracy suggests that comorbidities alone were not strong predictors of hospital readmission, and the need for more sophisticated subgroup modeling methods. Such advances could improve the interpretability and predictive accuracy of patient subgroup models for reducing the risk of hospital readmission, and beyond.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/37239","type":"journal-article","created":{"date-parts":[[2022,5,2]],"date-time":"2022-05-02T02:43:26Z","timestamp":1651459406000},"page":"e37239","source":"Crossref","is-referenced-by-count":12,"title":["A Framework for Modeling and Interpreting Patient Subgroups Applied to Hospital Readmission: Visual Analytical Approach"],"prefix":"10.2196","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9282-8838","authenticated-orcid":false,"given":"Suresh K","family":"Bhavnani","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6161-0978","authenticated-orcid":false,"given":"Weibin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2079-8684","authenticated-orcid":false,"given":"Shyam","family":"Visweswaran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7460-7281","authenticated-orcid":false,"given":"Mukaila","family":"Raji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1927-0927","authenticated-orcid":false,"given":"Yong-Fang","family":"Kuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2022,12,7]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2010.03.032"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/clpt.2008.65"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1158\/1078-0432.CCR-04-2421"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.191367098"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jaci.2010.11.015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.200711-1754OC"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jaci.2010.11.037"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa0805435"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1403290"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMp1500523"},{"key":"ref11","first-page":"112","volume":"2021","author":"Bhavnani, SK","year":"2021","journal-title":"AMIA Jt Summits Transl Sci Proc"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.2337\/dc15-0509"},{"issue":"3","key":"ref13","first-page":"1","volume":"28","author":"Baker, JJ","year":"2002","journal-title":"J Health Care Finance"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/sim.4289"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2004.11.015"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-21606-5","author":"Hastie, T","year":"2001","journal-title":"The Elements of Statistical Learning: Data Mining, Inference, and Prediction"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1002\/9781118906545","author":"Abu-jamous, B","year":"2015","journal-title":"Integrative Cluster Analysis in Bioinformatics"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5888\/pcd10.120137"},{"key":"ref19","first-page":"1","author":"Aryal, S","year":"2013","journal-title":"European Respiratory Monograph: COPD and Comorbidity"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0063285"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-15-333"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X09991567"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0083783"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15020-3_10"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1093\/acprof:oso\/9780199206650.001.0001","author":"Newman, ME","year":"2010","journal-title":"Networks: An Introduction"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2015\/02\/p02003"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms11062"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2196\/13567"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1002\/spe.4380211102"},{"key":"ref30","author":"Dang, B","year":"2016","journal-title":"AMIA Jt Summits Transl Sci Proc"},{"key":"ref31","first-page":"21","volume":"2017","author":"Bhavnani, SK","year":"2017","journal-title":"AMIA Jt Summits Transl Sci Proc"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-10-S9-S3"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3414\/ME09-01-0083"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1186\/1756-0500-3-296"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2011.09.006"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2011-000745"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1002\/pmic.201400451"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1515\/jpm-2017-0126"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMsa0803563"},{"key":"ref40","unstructured":"Report to Congress: Promoting Greater Efficiency in MedicareMedPac (Medicare Payment Advisory Commission)200762021-11-30https:\/\/www.ruralhealthinfo.org\/assets\/4544-19961\/Jun07_EntireReport.pdf"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1097\/00005650-199710000-00006"},{"key":"ref42","unstructured":"2015 Condition-specific measures updates and specifications report: Hospital-level 30-day risk-standardized readmission measures on acute myocardial infarction, heart failure, pneumonia, chronic obstructive pulmonary disease, and stokeCenters for Medicare & Medicaid Services20154202021-11-30http:\/\/www.cms.gov\/Medicare\/Quality-Initiatives-Patient-Assessment-Instruments\/HospitalQualityInits\/Measure-Methodology.html"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCOUTCOMES.108.802686"},{"key":"ref44","unstructured":"2015 Procedure-specific readmission measures updates and specifications report: elective primary total hip arthroplasty and\/or total knee arthroplasty, and isolated coronary artery bypass graft surgeryCenters for Medicare & Medicaid Services201504202021-11-30http:\/\/www.cms.gov\/Medicare\/Quality-Initiatives-Patient-Assessment-Instruments\/HospitalQualityInits\/Measure-Methodology.html"},{"key":"ref45","unstructured":"Using SAS\u00ae to Perform Individual Matching in Design of Case-Control StudiesSAS20102020-05-05https:\/\/support.sas.com\/resources\/papers\/proceedings10\/061-2010.pdf"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.2307\/2284239"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1513\/AnnalsATS.201310-358OC"},{"key":"ref48","unstructured":"GrossoLMCurtisJPLinZGearyLLVellankySOladeleCHospital-level 30-day all-cause risk-standardized readmission rate following elective primary total hip arthroplasty (THA) and\/or total knee arthroplasty (TKA)Yale New Haven Health Services Corporation\/Center for Outcomes Research & Evaluation20122022-06-08https:\/\/www.cms.gov\/Medicare\/Quality-Initiatives-Patient-Assessment-Instruments\/HospitalQualityInits\/Measure-Methodology"},{"key":"ref49","unstructured":"Medicare Enrollment ChartsChronic Conditions Data Warehouse20223292022-06-08https:\/\/www2.ccwdata.org\/web\/guest\/medicare-charts\/medicare-enrollment-charts#a1_coverage_trend"},{"key":"ref50","unstructured":"2020 profile of older AmericansAdministration for Community Living202152022-03-29https:\/\/acl.gov\/sites\/default\/files\/Aging%20and%20Disability%20in%20America\/2020ProfileOlderAmericans.Final_.pdf"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9681(87)90171-8"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1097\/00005650-199801000-00004"},{"key":"ref53","unstructured":"2017 Condition-specific measures updates and specifications report: Hospital-level 30-day risk-standardized readmission measures on acute myocardial infarction, heart failure, pneumonia, chronic obstructive pulmonary disease, and strokeCenters for Medicare & Medicaid Services20172017-05-31https:\/\/www.cms.gov\/Medicare\/Quality-Initiatives-Patient-Assessment-Instruments\/HospitalQualityInits\/Measure-Methodology.html"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2021.16901"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1200\/CCI.17.00067"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0197238"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3390\/e20090625"},{"key":"ref58","unstructured":"DhillonISSraSGeneralized nonnegative matrix approximations with Bregman divergencesProceedings of the 18th International Conference on Neural Information Processing Systems2005NIPS '05December 5-8, 2005Vancouver, Canada28390"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11886-018-1074-8"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1177\/0021886318794606"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1111\/cts.12266"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2022\/12\/e37239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:01:04Z","timestamp":1782842464000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2022\/12\/e37239"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,7]]},"references-count":61,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2022]]}},"URL":"https:\/\/doi.org\/10.2196\/37239","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2022.02.27.22271534","asserted-by":"object"}]},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,7]]}}}