{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T14:50:05Z","timestamp":1785855005261,"version":"3.56.0"},"reference-count":44,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Modern lifestyle risk factors, like physical inactivity and poor nutrition, contribute to rising rates of obesity and chronic diseases like type 2 diabetes and heart disease. Particularly personalized interventions have been shown to be effective for long-term behavior change. Machine learning can be used to uncover insights without predefined hypotheses, revealing complex relationships and distinct population clusters. New data-driven approaches, such as the factor probabilistic distance clustering algorithm, provide opportunities to identify potentially meaningful clusters within large and complex datasets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to identify potential clusters and relevant variables among individuals with obesity using a data-driven and hypothesis-free machine learning approach.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We used cross-sectional data from individuals with abdominal obesity from The Maastricht Study. Data (2971 variables) included demographics, lifestyle, biomedical aspects, advanced phenotyping, and social factors (cohort 2010). The factor probabilistic distance clustering algorithm was applied in order to detect clusters within this high-dimensional data. To identify a subset of distinct, minimally redundant, predictive variables, we used the statistically equivalent signature algorithm. To describe the clusters, we applied measures of central tendency and variability, and we assessed the distinctiveness of the clusters through the emerged variables using the F test for continuous variables and the chi-square test for categorical variables at a confidence level of \u03b1=.001<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We identified 3 distinct clusters (including 4128\/9188, 44.93% of all data points) among individuals with obesity (n=4128). The most significant continuous variable for distinguishing cluster 1 (n=1458) from clusters 2 and 3 combined (n=2670) was the lower energy intake (mean 1684, SD 393 kcal\/day vs mean 2358, SD 635 kcal\/day; P&lt;.001). The most significant categorical variable was occupation (P&lt;.001). A significantly higher proportion (1236\/1458, 84.77%) in cluster 1 did not work compared to clusters 2 and 3 combined (1486\/2670, 55.66%; P&lt;.001). For cluster 2 (n=1521), the most significant continuous variable was a higher energy intake (mean 2755, SD 506.2 kcal\/day vs mean 1749, SD 375 kcal\/day; P&lt;.001). The most significant categorical variable was sex (P&lt;.001). A significantly higher proportion (997\/1521, 65.55%) in cluster 2 were male compared to the other 2 clusters (885\/2607, 33.95%; P&lt;.001). For cluster 3 (n=1149), the most significant continuous variable was overall higher cognitive functioning (mean 0.2349, SD 0.5702 vs mean \u20130.3088, SD 0.7212; P&lt;.001), and educational level was the most significant categorical variable (P&lt;.001). A significantly higher proportion (475\/1149, 41.34%) in cluster 3 received higher vocational or university education in comparison to clusters 1 and 2 combined (729\/2979, 24.47%; P&lt;.001).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study demonstrates that a hypothesis-free and fully data-driven approach can be used to identify distinguishable participant clusters in large and complex datasets and find relevant variables that differ within populations with obesity.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/64479","type":"journal-article","created":{"date-parts":[[2025,2,5]],"date-time":"2025-02-05T08:31:46Z","timestamp":1738744306000},"page":"e64479","source":"Crossref","is-referenced-by-count":2,"title":["Identification of Clusters in a Population With Obesity Using Machine Learning: Secondary Analysis of The Maastricht Study"],"prefix":"10.2196","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8356-2716","authenticated-orcid":false,"given":"Maik JM","family":"Beuken","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6543-6994","authenticated-orcid":false,"given":"Melanie","family":"Kleynen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3037-3428","authenticated-orcid":false,"given":"Susy","family":"Braun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0139-9298","authenticated-orcid":false,"given":"Kees","family":"Van Berkel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1468-8793","authenticated-orcid":false,"given":"Carla","family":"van der Kallen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1583-7391","authenticated-orcid":false,"given":"Annemarie","family":"Koster","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4333-4564","authenticated-orcid":false,"given":"Hans","family":"Bosma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8101-939X","authenticated-orcid":false,"given":"Tos TJM","family":"Berendschot","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1747-8452","authenticated-orcid":false,"given":"Alfons JHM","family":"Houben","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4896-758X","authenticated-orcid":false,"given":"Nicole","family":"Dukers-Muijrers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3984-2232","authenticated-orcid":false,"given":"Joop P","family":"van den Bergh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7750-8249","authenticated-orcid":false,"given":"Abraham A","family":"Kroon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"Maastricht Study Management","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6863-2096","authenticated-orcid":false,"given":"Iris M","family":"Kanera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,2,5]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwq211"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/su7010294"},{"key":"ref3","unstructured":"(RIVM) RvVeMMinisterie van Volksgezondheid, Welzijn en SportSustainable care and prevention (SPR 2019-2022)20192024-04-02https:\/\/www.rivm.nl\/en\/about-rivm\/knowledge-and-expertise\/strategic-programme-rivm\/2019-2022\/sustainable -care-and-prevention"},{"key":"ref4","unstructured":"EykelenboomMBoerJtenDJSanderman-NawijnEHoekstraJBogaardtLGouwensSBlokstraAKoopmanNWorden de ambities voor 2040 bereikt? Calculating the impact of the National Prevention Agreement ? subagreement on overweight Will the 2040 ambitions be reached?: Rijksinstituut voor Volksgezondheid en MilieuDoorrekening Impact Nationaal Preventieakkoord: Deelakkoord Overgewicht2024-01-17https:\/\/www.rivm.nl\/publicaties\/doorrekening-impact-nationaal-preventieakkoord-deelakkoord-overge wicht-worden-ambities"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1186\/s12966-022-01267-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1093\/nutrit\/nuw049"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.133.4.673"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/10810730.2013.768727"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s12160-012-9384-3"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph15122796"},{"key":"ref11","author":"Burk, H","year":"1996","journal-title":"Learning from Data: Artificial Intelligence and Statistics V"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2018.2864254"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-22398-4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.2196\/34274"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3014812.3014874"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1186\/s12889-024-17648-1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/s41366-020-0565-z"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11634-015-0219-5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10654-014-9889-0"},{"key":"ref20","unstructured":"Data dictionaryThe Maastricht Study20242023-04-15https:\/\/demaastrichtstudie.app\/data-dictionary\/"},{"key":"ref21","author":"Klein, S","year":"2016","journal-title":"Chapter 36 - Obesity"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btr597"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v045.i03"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11749-016-0481-7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1002\/sam.11348"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.camwa.2012.09.011"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-019-3110-0"},{"key":"ref28","unstructured":"MayerMmissRanger: fast imputation of missing values20232023-04-28https:\/\/cran.r-project.org\/web\/packages\/missRanger\/index.html"},{"key":"ref29","unstructured":"TortoraCVidalesNPalumboFKalraTMcNicholasPFPDclustering20222022-08-31https:\/\/CRAN.R-project.org\/package =FPDclustering"},{"key":"ref30","author":"Tortora, C","year":"2013","journal-title":"Factor PD-clustering"},{"key":"ref31","unstructured":"BizaKTsamardinosILaganiVAthineouGTsagrisMBorboudakisGMXM: feature selection (including multiple solutions) and Bayesian networks2023-01-12https:\/\/CRAN.R-project.org\/package=MXM"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v080.i07"},{"key":"ref33","unstructured":"MelvilleJLunADjekidelMHaoYEddelbuettelDuwot: the uniform manifold approximation and projection (UMAP) method for dimensionality reduction2022-08-22https:\/\/CRAN.R-project.org\/package=uwot"},{"key":"ref34","unstructured":"Huntington-KleinNvtable: variable table for variable documentation2023-04-29https:\/\/CRAN.R-project.org\/package=vtable"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-77286-6"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s42081-022-00179-7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s00357-008-9002-z"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s00180-024-01490-5"},{"key":"ref39","author":"Tortora, C","year":"2014","journal-title":"Analysis and Modeling of Complex Data in Behavioral and Social Sciences"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-010-9169-0"},{"key":"ref42","unstructured":"TsamardinosILaganiVPappasDDiscovering multiple, equivalent biomarker signatures2012Proc 7th Conf Hellenic Soc Comput Biol Bioinf2012 October 6Hellas"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-018-2023-7"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1038\/s41574-019-0310-7"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2025\/1\/e64479","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T13:57:20Z","timestamp":1785851840000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2025\/1\/e64479"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,5]]},"references-count":44,"URL":"https:\/\/doi.org\/10.2196\/64479","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.64479","asserted-by":"object"}]},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,5]]}}}