{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T23:16:03Z","timestamp":1792451763964,"version":"4.5.0"},"reference-count":52,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["31600862"],"award-info":[{"award-number":["31600862"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["31900710"],"award-info":[{"award-number":["31900710"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012337","name":"Nanhu Scholars Program for Young Scholars of Xinyang Normal University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012337","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Aging Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The timely identification of mild cognitive impairment (MCI) in Parkinson's disease (PD) is essential for early intervention and clinical management, yet it remains a challenge in practice.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We conducted an analysis of 3,154 clinical visits from 896 participants in the Parkinson's Progression Markers Initiative (PPMI) cohort. Participants were divided into two groups: cognitively normal (PD-NC, MoCA \u2265 26) and MCI (PD-MCI, 21 \u2264 MoCA \u2264 25). To ensure no visit-level information leakage, subject-level stratified sampling was employed to split the data into training (70%) and hold-out test (30%) sets. From an initial set of 12 routinely assessed clinical features, seven were selected using least absolute shrinkage and selection operator (LASSO) logistic regression: age, sex, years of education, disease duration, UPDRS-I, UPDRS-III, and Geriatric Depression Scale (GDS). Four machine learning models\u2014logistic regression (LR), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost)\u2014were trained using subject-level stratified 10-fold cross-validation with Bayesian optimization. Probabilistic outputs were dichotomized using three thresholding strategies: default 0.5, F1-score maximization, and Youden index maximization.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>On the independent test set, SVM achieved the highest overall performance with AUC-ROC of 0.7252 and AUC-PR of 0.5008. LR also performed competitively despite its simplicity. RF achieved the top performance in sensitivity, reaching 0.8150. Feature importance analysis consistently highlighted age, years of education, and disease duration as the most informative predictors for distinguishing PD-MCI. Additionally, more stringent site-level split validation yielded slightly decreased overall performance, with LR showing improved AUC-PR. Importantly, the core feature importance ranking remained largely consistent across validation strategies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study developed and validated robust machine learning models for PD-MCI classification using standard clinical assessments alone. Through subject-level or site-level stratified cross-validation combined with Bayesian optimization, we achieved rigorous model evaluation while minimizing overfitting risk. These findings demonstrate the potential for implementing data-driven, interpretable diagnostic tools to enhance early cognitive impairment screening in routine PD care.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnagi.2025.1687925","type":"journal-article","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T05:32:46Z","timestamp":1761111166000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Diagnostic classification of mild cognitive impairment in Parkinson's disease using subject-level stratified machine-learning analysis"],"prefix":"10.3389","volume":"17","author":[{"given":"Jing","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanfang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongfang","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,22]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1038\/s41572-021-00280-3","article-title":"Parkinson disease-associated cognitive impairment","volume":"7","author":"Aarsland","year":"2021","journal-title":"Nat. Rev. Dis. Primers"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1062","DOI":"10.1212\/WNL.0b013e3181f39d0e","article-title":"Mild cognitive impairment in Parkinson disease: a multicenter pooled analysis","volume":"75","author":"Aarsland","year":"2010","journal-title":"Neurology"},{"key":"B3","doi-asserted-by":"publisher","first-page":"2623","DOI":"10.1145\/3292500.3330701","article-title":"\u201cOptuna: a next-generation hyperparameter optimization framework,\u201d","author":"Akiba","year":"2019","journal-title":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery"},{"key":"B4","doi-asserted-by":"publisher","first-page":"e0303644","DOI":"10.1371\/journal.pone.0303644","article-title":"Machine learning for the detection and diagnosis of cognitive impairment in Parkinson's disease: a systematic review","volume":"19","author":"Altham","year":"2024","journal-title":"PLoS ONE"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1340","DOI":"10.1093\/bioinformatics\/btq134","article-title":"Permutation importance: a corrected feature importance measure","volume":"26","author":"Altmann","year":"2010","journal-title":"Bioinformatics"},{"key":"B6","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1186\/s12911-020-01332-6","article-title":"Explainability for artificial intelligence in healthcare: a multidisciplinary perspective","volume":"20","author":"Amann","year":"2020","journal-title":"BMC Med. Inform. Decis. Mak"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1010147","DOI":"10.3389\/fneur.2022.1010147","article-title":"Machine learning can predict mild cognitive impairment in Parkinson's disease","volume":"13","author":"Amboni","year":"2022","journal-title":"Front. Neurol"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1238065","DOI":"10.3389\/fnagi.2023.1238065","article-title":"An eXplainability artificial intelligence approach to brain connectivity in Alzheimer's disease","volume":"15","author":"Amoroso","year":"2023","journal-title":"Front. Aging Neurosci"},{"key":"B9","doi-asserted-by":"publisher","first-page":"4620","DOI":"10.1002\/hbm.22499","article-title":"Functional brain networks and cognitive deficits in Parkinson's disease","volume":"35","author":"Baggio","year":"2014","journal-title":"Hum. Brain Mapp"},{"key":"B10","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn"},{"key":"B11","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":"B12","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1145\/2939672.2939785","article-title":"\u201cXGBoost: a scalable tree boosting system,\u201d","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Chen","year":"2016"},{"key":"B13","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn"},{"key":"B14","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.ecolmodel.2008.05.015","article-title":"A comparison of the performance of threshold criteria for binary classification in terms of predicted prevalence and kappa","volume":"217","author":"Freeman","year":"2008","journal-title":"Ecol. Modell"},{"key":"B15","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1080\/13803395.2015.1087465","article-title":"Mild cognitive impairment in Parkinson's disease: diagnosis and progression to dementia","volume":"38","author":"Galtier","year":"2016","journal-title":"J. Clin. Exp. Neuropsychol"},{"key":"B16","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1002\/mds.27323","article-title":"Evolution of diagnostic criteria and assessments for Parkinson's disease mild cognitive impairment","volume":"33","author":"Goldman","year":"","journal-title":"Mov. Disord"},{"key":"B17","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1038\/s41531-018-0055-3","article-title":"Cognitive impairment in Parkinson's disease: a report from a multidisciplinary symposium on unmet needs and future directions to maintain cognitive health","volume":"4","author":"Goldman","year":"","journal-title":"NPJ Parkinsons Dis"},{"key":"B18","doi-asserted-by":"publisher","first-page":"2713","DOI":"10.1007\/s00415-020-09757-9","article-title":"Predictors of cognitive impairment in Parkinson's disease: a systematic review and meta-analysis of prospective cohort studies","volume":"268","author":"Guo","year":"2021","journal-title":"J. Neurol"},{"key":"B19","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1002\/mds.21956","article-title":"The Sydney multicenter study of Parkinson's disease: the inevitability of dementia at 20 years","volume":"23","author":"Hely","year":"2008","journal-title":"Mov. Disord"},{"key":"B20","doi-asserted-by":"crossref","DOI":"10.1002\/9781118548387","volume-title":"Applied logistic Regression","author":"Hosmer Jr","year":"2013"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1691","DOI":"10.3390\/diagnostics13101691","article-title":"Prediction of cognitive decline in Parkinson's disease using clinical and DAT SPECT imaging features, and hybrid machine learning systems","volume":"13","author":"Hosseinzadeh","year":"2023","journal-title":"Diagnostics"},{"key":"B22","doi-asserted-by":"publisher","first-page":"132","DOI":"10.14802\/jmd.22012","article-title":"Accuracy of machine learning using the Montreal Cognitive Assessment for the diagnosis of cognitive impairment in Parkinson's disease","volume":"15","author":"Jeon","year":"2022","journal-title":"J. Mov. Disord"},{"key":"B23","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1177\/0891988712464823","article-title":"Cognitive impairment in Parkinson disease: impact on quality of life, disability, and caregiver burden","volume":"25","author":"Leroi","year":"2012","journal-title":"J. Geriatr. Psychiatry Neurol"},{"key":"B24","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1002\/mds.24893","article-title":"Diagnostic criteria for mild cognitive impairment in Parkinson's disease: Movement Disorder Society Task Force guidelines","volume":"27","author":"Litvan","year":"2012","journal-title":"Mov. Disord"},{"key":"B25","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1016\/S1474-4422(17)30122-9","article-title":"Prediction of cognition in Parkinson's disease with a clinical-genetic score: a longitudinal analysis of nine cohorts","volume":"16","author":"Liu","year":"2017","journal-title":"Lancet Neurol"},{"key":"B26","article-title":"\u201cA unified approach to interpreting model predictions","author":"Lundberg","year":"2017"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1498756","DOI":"10.3389\/fnagi.2024.1498756","article-title":"Global, regional, national epidemiology and trends of Parkinson's disease from 1990 to 2021: findings from the Global Burden of Disease Study 2021","volume":"16","author":"Luo","year":"2025","journal-title":"Front. Aging Neurosci"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1460","DOI":"10.1002\/acn3.644","article-title":"The Parkinson's progression markers initiative (PPMI)-establishing a PD biomarker cohort","volume":"5","author":"Marek","year":"2018","journal-title":"Ann. Clin. Transl. Neurol"},{"key":"B29","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1016\/j.pneurobio.2011.09.005","article-title":"The Parkinson progression marker initiative (PPMI)","volume":"95","author":"Marek","year":"2011","journal-title":"Prog. Neurobiol"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1007\/s00415-018-8800-4","article-title":"Mild cognitive impairment in Parkinson's disease: the Parkinson's disease cognitive study (PACOS)","volume":"265","author":"Monastero","year":"2018","journal-title":"J. Neurol"},{"key":"B31","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1016\/j.jocn.2019.01.021","article-title":"The clinical characteristics and cognitive features of mild cognitive impairment in Parkinson's disease and the analysis of relevant factors","volume":"63","author":"Nie","year":"2019","journal-title":"J. Clin. Neurosci"},{"key":"B32","doi-asserted-by":"publisher","first-page":"e0286506","DOI":"10.1371\/journal.pone.0286506","article-title":"Deep-learning detection of mild cognitive impairment from sleep electroencephalography for patients with Parkinson's disease","volume":"18","author":"Parajuli","year":"2023","journal-title":"PLoS ONE"},{"key":"B33","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1212\/WNL.0000000000003634","article-title":"Natural course of mild cognitive impairment in Parkinson disease: a 5-year population-based study","volume":"88","author":"Pedersen","year":"2017","journal-title":"Neurology"},{"key":"B34","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. of Mach. Learn. Res"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/nrdp.2017.13","article-title":"Parkinson disease","volume":"3","author":"Poewe","year":"2017","journal-title":"Nat. Rev. Dis. Primers"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1591","DOI":"10.1002\/mds.26424","article-title":"MDS clinical diagnostic criteria for Parkinson's disease","volume":"30","author":"Postuma","year":"2015","journal-title":"Mov. Disord"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1985","DOI":"10.3390\/s23041985","article-title":"Identification of a gait pattern for detecting mild cognitive impairment in Parkinson's disease","volume":"23","author":"Russo","year":"2023","journal-title":"Sensors"},{"key":"B38","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/S1474-4422(16)30328-3","article-title":"Clinical variables and biomarkers in prediction of cognitive impairment in patients with newly diagnosed Parkinson's disease: a cohort study","volume":"16","author":"Schrag","year":"2017","journal-title":"Lancet Neurol"},{"key":"B39","article-title":"\u201cPractical Bayesian optimization of machine learning algorithms,\u201d","volume-title":"Advances in Neural Information Processing Systems 25","author":"Snoek","year":"2012"},{"key":"B40","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/j.parkreldis.2009.11.002","article-title":"Mild cognitive impairment in Parkinson's disease: subtypes and motor characteristics","volume":"16","author":"Sollinger","year":"2010","journal-title":"Parkinsonism Relat. Disord"},{"key":"B41","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1016\/S1474-4422(24)00038-3","article-title":"Global, regional, and national burden of disorders affecting the nervous system, 1990-2021: a systematic analysis for the Global Burden of Disease Study 2021","volume":"23","author":"Steinmetz","year":"2024","journal-title":"Lancet Neurol"},{"key":"B42","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1017\/S1355617702813248","article-title":"What is cognitive reserve? Theory and research application of the reserve concept","volume":"8","author":"Stern","year":"2002","journal-title":"J. Int. Neuropsychol. Soc"},{"key":"B43","doi-asserted-by":"publisher","first-page":"e080952","DOI":"10.1136\/bmj-2024-080952","article-title":"Projections for prevalence of Parkinson's disease and its driving factors in 195 countries and territories to 2050: modelling study of Global Burden of Disease Study 2021","volume":"388","author":"Su","year":"2025","journal-title":"BMJ"},{"key":"B44","doi-asserted-by":"publisher","first-page":"1550789","DOI":"10.3389\/fneur.2025.1550789","article-title":"Risk factors associated with severe progression of Parkinson's disease: random forest and logistic regression models","volume":"16","author":"Tan","year":"2025","journal-title":"Front. Neurol"},{"key":"B45","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the Lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J. R. Stat. Soci. Ser. B: Stat. Methodol"},{"key":"B46","doi-asserted-by":"publisher","first-page":"104407","DOI":"10.1016\/j.dsp.2024.104407","article-title":"An analysis of data leakage and generalizability in MRI based classification of Parkinson's disease using explainable 2D convolutional neural networks","volume":"147","author":"Veetil","year":"2024","journal-title":"Digit. Signal Process"},{"key":"B47","doi-asserted-by":"publisher","first-page":"36989","DOI":"10.31083\/JIN36989","article-title":"Executive dysfunction and prefrontal cortex dysregulation in early-onset Parkinson's disease: an fNIRS study","volume":"24","author":"Wang","year":"2025","journal-title":"J. Integr. Neurosci"},{"key":"B48","doi-asserted-by":"publisher","first-page":"e59649","DOI":"10.2196\/59649","article-title":"The role of machine learning in cognitive impairment in Parkinson disease: systematic review and meta-analysis","volume":"27","author":"Wu","year":"2025","journal-title":"J. Med. Internet Res"},{"key":"B49","doi-asserted-by":"publisher","first-page":"22544","DOI":"10.1038\/s41598-021-01681-w","article-title":"Effect of data leakage in brain MRI classification using 2D convolutional neural networks","volume":"11","author":"Yagis","year":"2021","journal-title":"Sci. Rep"},{"key":"B50","doi-asserted-by":"publisher","first-page":"e464","DOI":"10.1016\/S2666-7568(24)00094-1","article-title":"Temporal trends in the prevalence of Parkinson's disease from 1980 to 2023: a systematic review and meta-analysis","volume":"5","author":"Zhu","year":"2024","journal-title":"Lancet Healthy Longev"},{"key":"B51","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1038\/s41531-024-00828-6","article-title":"Multimodal neuroimaging-based prediction of Parkinson's disease with mild cognitive impairment using machine learning technique","volume":"10","author":"Zhu","year":"2024","journal-title":"npj Parkinsons Dis"},{"key":"B52","doi-asserted-by":"publisher","first-page":"577662","DOI":"10.1016\/j.jneuroim.2021.577662","article-title":"Association between plasma neurofilament light chain levels and cognitive function in patients with Parkinson's disease","volume":"358","author":"Zhu","year":"2021","journal-title":"J. Neuroimmunol"}],"container-title":["Frontiers in Aging Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2025.1687925\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T05:32:48Z","timestamp":1761111168000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2025.1687925\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":52,"alternative-id":["10.3389\/fnagi.2025.1687925"],"URL":"https:\/\/doi.org\/10.3389\/fnagi.2025.1687925","relation":{},"ISSN":["1663-4365"],"issn-type":[{"value":"1663-4365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,22]]},"article-number":"1687925"}}