{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T10:50:57Z","timestamp":1782989457155,"version":"3.54.5"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686684","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6,29]]},"abstract":"<jats:p>Although clustering is widely used to explore phenotypic heterogeneity in Parkinson\u2019s disease (PD), reported subtype solutions often show limited reproducibility. We investigated whether reducing the number of features or samples in a typical clinical PD dataset more strongly affects clustering stability. We used baseline PD data from the Parkinson\u2019s Progression Markers Initiative. We applied K-means, Gaussian mixture models (GMM), and DBSCAN under systematic feature and sample reduction (40 %, 60 %, 80 %, and 100 %). We assessed cluster stability using the Adjusted Rand Index (ARI) relative to feature-matched reference solutions and the pairwise ARI across repeated runs. Sample reduction had the clearest effect on agreement with the reference solution across methods, whereas feature reduction mainly affected run-to-run reproducibility. K-means was the most robust method. Feature reduction lowered reproducibility in GMM, and changes in noise assignment affected DBSCAN. Therefore, reference-solution kstability may depend more on cohort size than features.<\/jats:p>","DOI":"10.3233\/shti260877","type":"book-chapter","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T10:01:48Z","timestamp":1782986508000},"source":"Crossref","is-referenced-by-count":0,"title":["Feature Reduction or Sample Reduction? A Stability Analysis of Parkinson\u2019s Disease Clustering"],"prefix":"10.3233","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3559-8661","authenticated-orcid":false,"given":"Leonie","family":"Ramin","sequence":"first","affiliation":[{"name":"Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School, Hannover Medical School, Hannover, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8178-5118","authenticated-orcid":false,"given":"Dominik","family":"Wolff","sequence":"additional","affiliation":[{"name":"Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School, Hannover Medical School, Hannover, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"7437","container-title":["Studies in Health Technology and Informatics","Health Sciences Informatics Leads and Empowers the Digital Health Transformation"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/SHTI260877","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T10:01:49Z","timestamp":1782986509000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/SHTI260877"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,29]]},"ISBN":["9781643686684"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/shti260877","relation":{},"ISSN":["0926-9630","1879-8365"],"issn-type":[{"value":"0926-9630","type":"print"},{"value":"1879-8365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,29]]}}}