{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T06:38:29Z","timestamp":1763707109769,"version":"3.45.0"},"reference-count":54,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T00:00:00Z","timestamp":1763683200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Parkinson's Disease (PD) is a neurodegenerative disorder with high heterogeneity in clinical symptoms, progression course, treatment response, and genetic factors. Thus, PD subtyping aims to enhance understanding of disease mechanisms and helps to facilitate targeted interventions or treatment regimens. Data-driven PD subtyping is typically done using cluster analysis. Still, such studies face difficulty from widespread adoption in clinical practice due to the following issues: (i) results are quite sensitive to study design, and actual subtype rules are not reasonably interpretable; (ii) results are not robustly replicable across multiple datasets, and most studies focus on a single dataset. This paper aims to identify novel PD subtypes using an interpretable decision-tree-based method that is robustly reproducible in an independent PD cohort. We first train a decision tree classifier on an LRRK2 dataset to determine whether a patient has early onset or late onset PD. By tracing back from the leaves of the learned decision tree subtyping rules are established. The independent MDS dataset is used for external validation, after mapping features between the two datasets. We finally obtained six novel subtypes that are clinically consistent and sufficiently large across both training and external validation datasets. Finally, a clinical characterization study showed that the following clinical features may be the most important diagnostic markers for our six detected subtypes: (i) persistent asymmetry affecting the side of onset most, (ii) clinical course of 10 years or more, and (iii) postural instability not caused by other dysfunction. The subtypes identified in our study may provide relevant guidance for prognosis and therapeutic strategies. An early onset subtype (E4) can be linked to a comparatively favorable prognosis. In contrast, the mixed onset subtypes (M3 and M7) may predict faster functional decline, suggesting that patients in these groups could benefit from intensified supportive measures. One late onset subtype (L1) seems to have a more benign course, while the other two (L2 and L4) are connected with predictors of reduced quality of life and increased care dependency.<\/jats:p>","DOI":"10.3389\/frai.2025.1668206","type":"journal-article","created":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T06:28:49Z","timestamp":1763706529000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Decision tree-based approach to robust Parkinson's disease subtyping using clinical data of the Michael J. Fox Foundation LRRK2 cross-sectional study"],"prefix":"10.3389","volume":"8","author":[{"given":"Soumyadeep","family":"Roy","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefanie","family":"Kr\u00e4he","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Marschollek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Helge","family":"Frieling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Niloy","family":"Ganguly","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dominik","family":"Wolff","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,11,21]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1436","DOI":"10.1212\/01.wnl.0000183359.50822.f2","article-title":"Progression of motor impairment and disability in Parkinson disease: a population-based study","volume":"65","author":"Alves","year":"2005","journal-title":"Neurology"},{"key":"B2","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1001\/jama.2019.22360","article-title":"Diagnosis and treatment of Parkinson disease: a review","volume":"323","author":"Armstrong","year":"2020","journal-title":"JAMA"},{"key":"B3","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1590\/S1980-57642008DN10100010","article-title":"Brazilian version of the frontal assessment battery (FAB): preliminary data on administration to healthy elderly","volume":"1","author":"Beato","year":"2007","journal-title":"Dement. Neuropsychol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1590\/S0004-282X2007000100003","article-title":"Early-onset Parkinson's disease and depression","volume":"65","author":"Bertucci Filho","year":"2007","journal-title":"Arq. Neuropsiquiatr"},{"key":"B5","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1038\/s41531-021-00228-0","article-title":"Comprehensive subtyping of Parkinson's disease patients with similarity fusion: a case study with biofind data","volume":"7","author":"Brendel","year":"2021","journal-title":"NPJ Parkinsons Dis"},{"key":"B6","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1007\/978-3-642-37456-2_14","article-title":"\u201cDensity-based clustering based on hierarchical density estimates,\u201d","author":"Campello","year":"2013","journal-title":"Advances in Knowledge Discovery and Data Mining"},{"key":"B7","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1016\/S1474-4422(06)70373-8","article-title":"Non-motor symptoms of Parkinson's disease: diagnosis and management","volume":"5","author":"Chaudhuri","year":"2006","journal-title":"Lancet Neurol"},{"key":"B8","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1002\/mds.27862","article-title":"The movement disorder society nonmotor rating scale: initial validation study","volume":"35","author":"Chaudhuri","year":"2020","journal-title":"Mov. Disord"},{"key":"B9","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41531-022-00439-z","article-title":"Identification and prediction of Parkinson's disease subtypes and progression using machine learning in two cohorts","volume":"8","author":"Dadu","year":"2022","journal-title":"NPJ Parkinsons Dis"},{"key":"B10","doi-asserted-by":"publisher","first-page":"107208","DOI":"10.1016\/j.parkreldis.2024.107208","article-title":"Parkinson's disease subtypes: approaches and clinical implications","volume":"130","author":"Deng","year":"2024","journal-title":"Parkinsonism Relat. Disord"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1007\/s11910-017-0738-x","article-title":"Subtypes of Parkinson's disease: what do they tell us about disease progression?","author":"Fereshtehnejad","year":"2017","journal-title":"Curr. Neurol. Neurosci. Rep"},{"key":"B12","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1001\/jamaneurol.2015.0703","article-title":"New clinical subtypes of parkinson disease and their longitudinal progression: a prospective cohort comparison with other phenotypes","volume":"72","author":"Fereshtehnejad","year":"2015","journal-title":"JAMA Neurol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1959","DOI":"10.1093\/brain\/awx118","article-title":"Clinical criteria for subtyping Parkinson's disease: biomarkers and longitudinal progression","volume":"140","author":"Fereshtehnejad","year":"2017","journal-title":"Brain"},{"key":"B14","doi-asserted-by":"publisher","first-page":"972","DOI":"10.1126\/science.1136800","article-title":"Clustering by passing messages between data points","volume":"315","author":"Frey","year":"2007","journal-title":"Science"},{"key":"B15","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1038\/s41531-024-00712-3","article-title":"Progression subtypes in Parkinson's disease identified by a data-driven multi cohort analysis","volume":"10","author":"H\u00e4hnel","year":"2024","journal-title":"npj Parkinsons Dis"},{"key":"B16","doi-asserted-by":"publisher","first-page":"982","DOI":"10.1002\/mds.21477","article-title":"Prevalence and clinical features of common lrrk2 mutations in Australians with Parkinson's disease","volume":"22","author":"Huang","year":"2007","journal-title":"Mov. Disord"},{"key":"B17","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1016\/S1474-4422(08)70116-9","article-title":"Lrrk2 gly2019ser penetrance in Arab-Berber patients from Tunisia: a case-control genetic study","volume":"7","author":"Hulihan","year":"2008","journal-title":"Lancet Neurol"},{"key":"B18","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1002\/mds.21180","article-title":"Screening for lrrk2 g2019s and clinical comparison of Tunisian and north American caucasian Parkinson's disease families","volume":"22","author":"Ishihara","year":"2007","journal-title":"Mov. Disord"},{"key":"B19","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.parkreldis.2018.07.015","article-title":"Very old onset Parkinsonism: a clinical-pathological study","volume":"57","author":"Jellinger","year":"2018","journal-title":"Parkinsonism Relat. Disord"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1755","DOI":"10.1093\/brain\/awq059","article-title":"Relationships between age and late progression of Parkinson's disease: a clinico-pathological study","volume":"133","author":"Kempster","year":"2010","journal-title":"Brain"},{"key":"B21","first-page":"31","volume-title":"Clinical Features of LRRK2 Carriers with Parkinson's Disease","author":"Kestenbaum","year":"2017"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0233296","article-title":"Identifying and predicting Parkinson's disease subtypes through trajectory clustering via bipartite networks","volume":"15","author":"Krishnagopal","year":"2020","journal-title":"PLOS ONE"},{"key":"B23","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1186\/s12881-017-0432-5","article-title":"Using kasp technique to screen lrrk2 g2019s mutation in a large Tunisian cohort","volume":"18","author":"Landoulsi","year":"2017","journal-title":"BMC Med. Genet"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1279","DOI":"10.1136\/jnnp-2018-318337","article-title":"Developing and validating Parkinson's disease subtypes and their motor and cognitive progression","volume":"89","author":"Lawton","year":"2018","journal-title":"J. Neurol. Neurosurg. Psychiatry"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1550","DOI":"10.1212\/01.wnl.0000338460.89796.06","article-title":"Is the common lrrk2 g2019s mutation related to dyskinesias in North African Parkinson disease?","volume":"71","author":"Lesage","year":"2008","journal-title":"Neurology"},{"key":"B26","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1056\/NEJMc055540","article-title":"Lrrk2 g2019s as a cause of Parkinson's disease in north African Arabs","volume":"354","author":"Lesage","year":"2006","journal-title":"N. Engl. J. Med"},{"key":"B27","doi-asserted-by":"publisher","first-page":"784","DOI":"10.1002\/ana.20636","article-title":"G2019s lrrk2 mutation in French and north African families with Parkinson's disease","volume":"58","author":"Lesage","year":"2005","journal-title":"Ann. Neurol"},{"key":"B28","doi-asserted-by":"publisher","first-page":"100246","DOI":"10.1016\/j.ynirp.2025.100246","article-title":"Unsupervised subtyping of motor dysfunction of Parkinson's disease and its structural brain imaging correlates","volume":"5","author":"Lin","year":"2025","journal-title":"NeuroImage Rep"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1854","DOI":"10.1002\/mds.28238","article-title":"Age at onset of lrrk2 p. gly2019ser is related to environmental and lifestyle factors","volume":"35","author":"L\u00fcth","year":"2020","journal-title":"Mov. Disord"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41531-020-00144-9","article-title":"Multimodal phenotypic axes of Parkinson's disease","volume":"7","author":"Markello","year":"2021","journal-title":"npj Parkinsons Dis"},{"key":"B31","doi-asserted-by":"publisher","first-page":"869","DOI":"10.1002\/mdc3.13523","article-title":"Age cutoff for early-onset Parkinson's disease: recommendations from the international Parkinson and movement disorder society task force on early onset Parkinson's disease","volume":"9","author":"Mehanna","year":"2022","journal-title":"Mov. Disord. Clin. Pract"},{"key":"B32","doi-asserted-by":"publisher","first-page":"395","DOI":"10.3233\/JPD-202472","article-title":"Parkinson's disease subtypes: critical appraisal and recommendations","volume":"11","author":"Mestre","year":"2021","journal-title":"J. Parkinsons Dis"},{"key":"B33","unstructured":"Michael\n              J.\n            \n          \n          Lrrk2 Cohort Consortium by the Michael J. Fox Foundation for Parkinson's Research\n          \n          2023"},{"key":"B34","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1186\/s12984-025-01648-2","article-title":"Using machine learning to identify Parkinson's disease severity subtypes with multimodal data","volume":"22","author":"Park","year":"2025","journal-title":"J. NeuroEng. Rehabil"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1130","DOI":"10.14336\/AD.2019.0112","article-title":"Subtyping of Parkinson's disease - where are we up to?","volume":"10","author":"Qian","year":"2019","journal-title":"Aging Dis"},{"key":"B36","unstructured":"Parkinson disease subtyping: are we there yet?\n          \n          \n            \n              Ramirez-Zamora\n              A.\n            \n          \n          \n          2022"},{"key":"B37","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1080\/01621459.1971.10482356","article-title":"Objective criteria for the evaluation of clustering methods","volume":"66","author":"Rand","year":"1971","journal-title":"J. Am. Stat. Assoc"},{"key":"B38","doi-asserted-by":"publisher","first-page":"23645","DOI":"10.1038\/s41598-021-03118-w","article-title":"Identifying Parkinson's disease subtypes with motor and non-motor symptoms via model-based multi-partition clustering","volume":"11","author":"Rodriguez-Sanchez","year":"2021","journal-title":"Sci. Rep"},{"key":"B39","doi-asserted-by":"publisher","first-page":"49","DOI":"10.2147\/PPA.S11841","article-title":"Patient considerations in early management of Parkinson's disease: focus on extended-release pramipexole","volume":"6","author":"Salawu","year":"2012","journal-title":"Patient Prefer. Adherence"},{"key":"B40","doi-asserted-by":"publisher","first-page":"684","DOI":"10.1002\/mds.27414","article-title":"Targeted therapies for Parkinson's disease: from genetics to the clinic","volume":"33","author":"Sardi","year":"2018","journal-title":"Mov. Disord"},{"key":"B41","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.parkreldis.2011.10.009","article-title":"Cognitive dysfunction in Tunisian lrrk2 associated Parkinson's disease","volume":"18","author":"Sassi","year":"2012","journal-title":"Parkinsonism Relat. Disord"},{"key":"B42","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/S1474-4422(06)70411-2","article-title":"Epidemiological, clinical, and genetic characteristics of early-onset parkinsonism","volume":"5","author":"Schrag","year":"2006","journal-title":"Lancet Neurol"},{"key":"B43","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.parkreldis.2022.05.012","article-title":"Prevalence of ten lrrk2 variants in Parkinson's disease: a comprehensive review","volume":"98","author":"Simpson","year":"2022","journal-title":"Parkinsonism Relat. Disord"},{"key":"B44","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.parkreldis.2016.04.027","article-title":"How stable are Parkinson's disease subtypes in de novo patients: analysis of the PPMI cohort?","volume":"28","author":"Simuni","year":"2016","journal-title":"Parkinsonism Relat. Disord"},{"key":"B45","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1093\/bioinformatics\/btr597","article-title":"MissForest\u2014non-parametric missing value imputation for mixed-type data","volume":"28","author":"Stekhoven","year":"2011","journal-title":"Bioinformatics"},{"key":"B46","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1038\/s41746-024-01175-9","article-title":"Identification of Parkinson's disease pace subtypes and repurposing treatments through integrative analyses of multimodal data","volume":"7","author":"Su","year":"2024","journal-title":"NPJ Digit. Med"},{"key":"B47","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1016\/j.neulet.2005.04.103","article-title":"The g2019s lrrk2 mutation is uncommon in an Asian cohort of Parkinson's disease patients","volume":"384","author":"Tan","year":"2005","journal-title":"Neurosci. Lett"},{"key":"B48","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1002\/mds.27027","article-title":"Personalized medicine in Parkinson's disease: time to be precise","volume":"32","author":"Titova","year":"2017","journal-title":"Mov. Disord"},{"key":"B49","doi-asserted-by":"publisher","first-page":"1125","DOI":"10.1016\/j.neurobiolaging.2013.11.015","article-title":"A comparative study of Parkinson's disease and leucine-rich repeat kinase 2 p. g2019s parkinsonism","volume":"35","author":"Trinh","year":"2014","journal-title":"Neurobiol. Aging"},{"key":"B50","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1002\/mds.23346","article-title":"Clinical subtypes of Parkinson's disease","volume":"26","author":"van Rooden","year":"2011","journal-title":"Mov. Disord"},{"key":"B51","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.parkreldis.2021.05.016","article-title":"The inconsistency and instability of Parkinson's disease motor subtypes","volume":"88","author":"Von Coelln","year":"2021","journal-title":"Parkinsonism Relat. Disord"},{"key":"B52","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1177\/1077558709350885","article-title":"State adoption of nursing home pay-for-performance","volume":"67","author":"Werner","year":"2010","journal-title":"Med. Care Res. Rev"},{"key":"B53","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1002\/mds.23469","article-title":"The motor phenotype of Parkinson's disease in relation to age at onset","volume":"26","author":"Wickremaratchi","year":"2011","journal-title":"Mov. Disord"},{"key":"B54","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-018-37545-z","article-title":"Data-driven subtyping of Parkinson's disease using longitudinal clinical records: a cohort study","volume":"9","author":"Zhang","year":"2019","journal-title":"Sci. Rep"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1668206\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T06:28:52Z","timestamp":1763706532000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1668206\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,21]]},"references-count":54,"alternative-id":["10.3389\/frai.2025.1668206"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1668206","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,21]]},"article-number":"1668206"}}