{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T16:36:03Z","timestamp":1773160563338,"version":"3.50.1"},"reference-count":27,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T00:00:00Z","timestamp":1666137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100020639","name":"Bayerische Staatsministerium f\u00fcr Wirtschaft, Landesentwicklung und Energie","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020639","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Pharmacol."],"abstract":"<jats:p><jats:bold>Background:<\/jats:bold> In chronically ill patients, medication adherence during implementation can be crucial for treatment success and can decrease health costs. In some populations, regression models do not show this relationship. We aim to estimate subgroup-specific and personalized effects to identify target groups for interventions.<\/jats:p><jats:p><jats:bold>Methods:<\/jats:bold> We defined three cohorts of patients with type 1 diabetes (n = 12,713), type 2 diabetes (n = 85,162) and hyperlipidemia (n = 117,485) from German claims data between 2012 and 2015. We estimated the association of adherence during implementation in the first year (proportion of days covered) and mean total costs in the three following years, controlled for sex, age, Charlson\u2019s Comorbidity Index, initial total costs, severity of the disease and surrogates for health behavior. We fitted three different types of models on training data: 1) linear regression models for the overall conditional associations between adherence and costs, 2) model-based trees to identify subgroups of patients with heterogeneous adherence effects, and 3) model-based random forests to estimate personalized adherence effects. To assess the performance of the latter, we conditionally re-estimated the personalized effects using test data, the fixed structure of the forests, and fixed effect estimates of the remaining covariates.<\/jats:p><jats:p><jats:bold>Results:<\/jats:bold> 1) our simple linear regression model estimated a positive adherence effect, that is an increase in total costs of 10.73 Euro per PDC-point and year for diabetes type 1, 3.92 Euro for diabetes type 2 and 1.92 Euro for hyperlipidemia (all <jats:italic>p<\/jats:italic> \u2264 0.001). 2) The model-based tree detected subgroups with negative estimated adherence effects for diabetes type 2 (-1.69 Euro, 24.4% of cohort) and hyperlipidemia (-0.11 Euro, 36.1% and -5.50 Euro, 5.3%). 3) Our model-based random forest estimated personalized adherence effects with a significant proportion (4.2%\u201324.1%) of negative effects (up to -8.31 Euro). The precision of these estimates was high for diabetes type 2 and hyperlipidemia patients.<\/jats:p><jats:p><jats:bold>Discussion:<\/jats:bold> Our approach shows that tree-based models can identify patients with different adherence effects and the precision of personalized effects is measurable. Identified patients can form target groups for adherence-promotion interventions. The method can also be applied to other outcomes such as hospitalization risk to maximize positive health effects of an intervention.<\/jats:p>","DOI":"10.3389\/fphar.2022.1001038","type":"journal-article","created":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T17:51:20Z","timestamp":1666201880000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Identification of target groups and individuals for adherence interventions using tree-based prediction models"],"prefix":"10.3389","volume":"13","author":[{"given":"Johannes","family":"Wendl","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Simon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Kistler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jana","family":"Hapfelmeier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonius","family":"Schneider","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Hapfelmeier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2022,10,19]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1016\/0021-9681(87)90171-8","article-title":"A new method of classifying prognostic comorbidity in longitudinal studies: Development and validation","volume":"40","author":"Charlson","year":"1987","journal-title":"J. Chronic Dis."},{"key":"B2","doi-asserted-by":"publisher","first-page":"e016982","DOI":"10.1136\/bmjopen-2017-016982","article-title":"Economic impact of medication non-adherence by disease groups: A systematic review","volume":"8","author":"Cutler","year":"2018","journal-title":"BMJ Open"},{"key":"B3","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/s0895-4356(01)00457-7","article-title":"Treatment adherence in chronic disease","volume":"54","author":"Dunbar-Jacob","year":"2001","journal-title":"J. Clin. Epidemiol."},{"key":"B4","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4020-5614-7_3443","article-title":"Target group","volume-title":"Encyclopedia of public health","author":"Fuchs","year":"2008"},{"key":"B5","doi-asserted-by":"publisher","first-page":"7037230","DOI":"10.1155\/2019\/7037230","article-title":"A simulation study comparing different statistical approaches for the identification of predictive biomarkers","volume":"2019","author":"Haller","year":"2019","journal-title":"Comput. Math. Methods Med."},{"key":"B6","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The elements of statistical learning: Data mining, inference, and prediction","author":"Hastie","year":"2009"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1080\/10618600.2021.1872581","article-title":"Predictive distribution modeling using transformation forests","volume":"30","author":"Hothorn","year":"2021","journal-title":"J. Comput. Graph. Statistics"},{"key":"B8","doi-asserted-by":"publisher","first-page":"35","DOI":"10.2147\/RMHP.S19801","article-title":"Adherence and health care costs","volume":"7","author":"Iuga","year":"2014","journal-title":"Risk Manag. Healthc. Policy"},{"key":"B9","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-0716-1418-1","volume-title":"An introduction to statistical learning: With applications in R","author":"James","year":"2021"},{"key":"B10","doi-asserted-by":"publisher","first-page":"CD000011","DOI":"10.1002\/14651858.CD000011.pub4","article-title":"Interventions for enhancing medication adherence","volume":"11","author":"Nieuwlaat","year":"2014","journal-title":"Cochrane Database Syst. Rev."},{"key":"B11","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1093\/aje\/kwq433","article-title":"Phil hider, jean-marie januel, and vijaya SundararajanUpdating and validating the Charlson comorbidity Index and score for risk adjustment in hospital discharge abstracts using data from 6 countries","volume":"173","author":"Quan","year":"2011","journal-title":"Am. J. Epidemiol."},{"key":"B12","doi-asserted-by":"publisher","first-page":"1130","DOI":"10.1097\/01.mlr.0000182534.19832.83","article-title":"Coding algorithms for defining comorbidities in icd-9-Cm and icd-10 administrative data","volume":"43","author":"Quan","year":"2005","journal-title":"Med. Care"},{"key":"B13","volume-title":"R: A language and environment for statistical computing","year":"2019"},{"key":"B14","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1377\/hlthaff.2009.1087","article-title":"Medication adherence leads to lower health care use and costs despite increased drug spending","volume":"30","author":"Roebuck","year":"2011","journal-title":"Health Aff."},{"key":"B15","doi-asserted-by":"publisher","first-page":"1586","DOI":"10.1377\/hlthaff.2015.0335","article-title":"Increased use of prescription drugs reduces medical costs in Medicaid populations","volume":"34","author":"Roebuck","year":"2015","journal-title":"Health Aff."},{"key":"B16","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1515\/ijb-2015-0032","article-title":"Model-based recursive partitioning for subgroup Analyses","volume":"12","author":"Seibold","year":"2016","journal-title":"Int. J. Biostat."},{"key":"B17","doi-asserted-by":"publisher","first-page":"3104","DOI":"10.1177\/0962280217693034","article-title":"Individual treatment effect prediction for amyotrophic lateral sclerosis patients","volume":"27","author":"Seibold","year":"2018","journal-title":"Stat. Methods Med. Res."},{"key":"B18","doi-asserted-by":"publisher","first-page":"546","DOI":"10.1007\/s11606-010-1609-1","article-title":"Healthy user and related biases in observational studies of preventive interventions: A primer for physicians","volume":"26","author":"Shrank","year":"2011","journal-title":"J. Gen. Intern. Med."},{"key":"B19","doi-asserted-by":"crossref","DOI":"10.1201\/b21973","volume-title":"Flexible regression and smoothing: Using gamlss in R","author":"Stasinopoulos","year":"2017"},{"key":"B20","unstructured":"Angaben zur Krankenversicherung 2019 (Ergebnisse des Mikrozensus)2020"},{"key":"B21","unstructured":"Genesis-online2022"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1364","DOI":"10.1111\/1475-6773.12170","article-title":"Incident user cohorts for assessing medication cost-offsets","volume":"49","author":"Stuart","year":"2014","journal-title":"Health Serv. Res."},{"key":"B23","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1007\/s10865-016-9727-9","article-title":"Getting less of what you want: Reductions in statistical power and increased bias when categorizing medication adherence data","volume":"39","author":"Tueller","year":"2016","journal-title":"J. Behav. Med."},{"key":"B24","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1111\/j.1365-2125.2012.04167.x","article-title":"A new taxonomy for describing and defining adherence to medications","volume":"73","author":"Vrijens","year":"2012","journal-title":"Br. J. Clin. Pharmacol."},{"key":"B25","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1111\/j.1740-9713.2015.00798.x","article-title":"What next for randomised clinical trials?","volume":"12","author":"Weisberg","year":"2015","journal-title":"Significance"},{"key":"B26","volume-title":"ATC classification Index with ddds, 2022","year":"2021"},{"key":"B27","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1198\/106186008X319331","article-title":"Model-based recursive partitioning","volume":"17","author":"Zeileis","year":"2008","journal-title":"J. Comput. Graph. Statistics"}],"container-title":["Frontiers in Pharmacology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2022.1001038\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T17:51:31Z","timestamp":1666201891000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2022.1001038\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,19]]},"references-count":27,"alternative-id":["10.3389\/fphar.2022.1001038"],"URL":"https:\/\/doi.org\/10.3389\/fphar.2022.1001038","relation":{},"ISSN":["1663-9812"],"issn-type":[{"value":"1663-9812","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,19]]},"article-number":"1001038"}}