{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T16:35:33Z","timestamp":1792600533235,"version":"4.5.0"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"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. Aging Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Parkinson\u2019s disease (PD)-related cognitive impairment (PD-CI) is a common and impactful complication of PD, yet current predictive models often rely on specialized resources, lack interpretability, or have limited cross-population validation. This study aimed to develop an interpretable machine learning framework for PD-CI detection using only routine clinical data, addressing unmet needs in accessible and generalizable PD care.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We analyzed 1,279 participants from the Parkinson\u2019s Progression Markers Initiative (PPMI) as the discovery cohort and 197 patients from an independent validation cohort. PD-CI was defined by a Montreal Cognitive Assessment (MoCA) score \u226426 and Unified Parkinson\u2019s Disease Rating Scale Part I (UPDRS-I) score \u22651. Twenty-one clinical features\u2014encompassing hematological parameters, metabolic markers, and demographics\u2014were preprocessed with synthetic minority over-sampling. Four machine learning models were trained and optimized via nested 5-fold cross-validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The Random Forest algorithm achieved superior performance in the discovery cohort (AUC = 0.83), outperforming CatBoost (AUC = 0.82), XGBoost (AUC = 0.79), and neural networks (AUC = 0.66). External validation of the framework preserved 71.57% accuracy. SHAP interpretability analysis identified age, neutrophil-to-lymphocyte ratio (NLR), and serum uric acid as critical predictors, revealing synergistic risk effects between elevated inflammation markers and reduced antioxidant levels.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>This framework demonstrates diagnostic accuracy comparable to advanced neuroimaging while utilizing readily available clinical data, enhancing accessibility in resource-limited settings. It highlights neuroinflammation and oxidative stress as key mechanistic drivers of PD-CI, advancing pathophysiological understanding. Multicenter validation confirms the model\u2019s robustness across ethnic populations, supporting its utility as a clinically actionable tool for PD-CI screening and monitoring.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnagi.2025.1688653","type":"journal-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T06:31:15Z","timestamp":1762842675000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Interpretable machine learning for cognitive impairment prediction in Parkinson\u2019s disease: a multicenter validation study with SHAP analysis"],"prefix":"10.3389","volume":"17","author":[{"given":"Ziyuan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junqiang","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,11,11]]},"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. Prim."},{"key":"B2","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1038\/nrneurol.2017.27","article-title":"Cognitive decline in Parkinson disease.","volume":"13","author":"Aarsland","year":"2017","journal-title":"Nat. Rev. Neurol."},{"key":"B3","doi-asserted-by":"publisher","first-page":"102285","DOI":"10.1016\/j.arr.2024.102285","article-title":"Parkinson\u2019s disease diagnosis using deep learning: A bibliometric analysis and literature review.","volume":"96","author":"Abumalloh","year":"2024","journal-title":"Ageing Res. Rev."},{"key":"B4","doi-asserted-by":"publisher","first-page":"13193","DOI":"10.1038\/s41598-023-37644-6","article-title":"Machine learning-based prediction of longitudinal cognitive decline in early Parkinson\u2019s disease using multimodal features.","volume":"13","author":"Almgren","year":"2023","journal-title":"Sci. Rep."},{"key":"B5","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1002\/mds.27902","article-title":"Prevalence and clinical aspects of mild cognitive impairment in Parkinson\u2019s disease: A meta-analysis.","volume":"35","author":"Baiano","year":"2020","journal-title":"Mov. Disord."},{"key":"B6","doi-asserted-by":"publisher","first-page":"101681","DOI":"10.1016\/j.arr.2022.101681","article-title":"Role of platelet in Parkinson\u2019s disease: Insights into pathophysiology & theranostic solutions.","volume":"80","author":"Beura","year":"2022","journal-title":"Ageing Res. Rev."},{"key":"B7","doi-asserted-by":"publisher","first-page":"2284","DOI":"10.1016\/S0140-6736(21)00218-X","article-title":"Parkinson\u2019s disease.","volume":"397","author":"Bloem","year":"2021","journal-title":"Lancet"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1331","DOI":"10.3233\/JAD-2010-1330","article-title":"Uric acid as a CNS antioxidant.","volume":"19","author":"Bowman","year":"2010","journal-title":"J. Alzheimers Dis."},{"key":"B9","doi-asserted-by":"publisher","first-page":"5216","DOI":"10.1109\/JBHI.2023.3292452","article-title":"EEG-Based Parkinson\u2019s disease recognition via attention-based sparse graph convolutional neural network.","volume":"27","author":"Chang","year":"2023","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"B10","doi-asserted-by":"publisher","first-page":"775","DOI":"10.3233\/JPD-191900","article-title":"The association between type 2 diabetes mellitus and Parkinson\u2019s disease.","volume":"10","author":"Cheong","year":"2020","journal-title":"J. Parkinsons Dis."},{"key":"B11","doi-asserted-by":"publisher","first-page":"1458184","DOI":"10.3389\/fneur.2024.1458184","article-title":"Protective role of serum albumin in dementia: A prospective study from United Kingdom biobank.","volume":"15","author":"Cui","year":"2024","journal-title":"Front. Neurol."},{"key":"B12","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1002\/mds.29298","article-title":"Type 2 diabetes and Parkinson\u2019s disease: A focused review of current concepts.","volume":"38","author":"Cullinane","year":"2023","journal-title":"Mov. Disord."},{"key":"B13","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-69765-9_5","article-title":"Tree-Based methods","volume-title":"High-Dimensional data analysis in cancer research","author":"Cutler","year":"2009"},{"key":"B14","doi-asserted-by":"publisher","first-page":"3717","DOI":"10.1093\/brain\/awaa269","article-title":"CD8 T cell nigral infiltration precedes synucleinopathy in early stages of Parkinson\u2019s disease.","volume":"143","author":"Galiano-Landeira","year":"2020","journal-title":"Brain"},{"key":"B15","doi-asserted-by":"publisher","first-page":"239","DOI":"10.3233\/JAD-181131","article-title":"Serum potassium is associated with cognitive decline in patients with lewy body dementia.","volume":"68","author":"Giil","year":"2019","journal-title":"J. Alzheimers Dis."},{"key":"B16","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1016\/j.parkreldis.2014.02.023","article-title":"Serum uric acid and risk of dementia in Parkinson\u2019s disease.","volume":"20","author":"Gonz\u00e1lez-Aramburu","year":"2014","journal-title":"Parkinson. Relat. Disord."},{"key":"B17","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1186\/s12883-023-03380-7","article-title":"Neutrophil to lymphocyte ratio in parkinson\u2019s disease: A systematic review and meta-analysis.","volume":"23","author":"Hosseini","year":"2023","journal-title":"BMC Neurol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1007\/s11357-016-9871-8","article-title":"Serum uric acid level and association with cognitive impairment and dementia: Systematic review and meta-analysis.","volume":"38","author":"Khan","year":"2016","journal-title":"Age"},{"key":"B19","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1016\/j.tins.2023.07.005","article-title":"The systemic immune response in Parkinson\u2019s disease: Focus on the peripheral immune component.","volume":"46","author":"Lauritsen","year":"2023","journal-title":"Trends Neurosci."},{"key":"B20","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1186\/s12944-021-01462-4","article-title":"Compared with the monocyte to high-density lipoprotein ratio (MHR) and the neutrophil to lymphocyte ratio (NLR), the neutrophil to high-density lipoprotein ratio (NHR) is more valuable for assessing the inflammatory process in Parkinson\u2019s disease.","volume":"20","author":"Liu","year":"2021","journal-title":"Lipids Health Dis."},{"key":"B21","doi-asserted-by":"publisher","first-page":"2301","DOI":"10.1002\/acn3.52144","article-title":"Neutrophil-to-lymphocyte ratio and longitudinal cognitive performance in Parkinson\u2019s disease.","volume":"11","author":"Lucero","year":"2024","journal-title":"Ann. Clin. Transl. Neurol."},{"key":"B22","doi-asserted-by":"publisher","first-page":"2426","DOI":"10.1002\/mds.28685","article-title":"Peripheral immune profile and neutrophil-to-lymphocyte ratio in Parkinson\u2019s disease.","volume":"36","author":"Mu\u00f1oz-Delgado","year":"2021","journal-title":"Mov. Disord."},{"key":"B23","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1111\/j.1532-5415.2005.53221.x","article-title":"The montreal cognitive assessment, MoCA: A brief screening tool for mild cognitive impairment.","volume":"53","author":"Nasreddine","year":"2005","journal-title":"J. Am. Geriatr. Soc."},{"key":"B24","doi-asserted-by":"publisher","first-page":"1711","DOI":"10.1002\/mds.27815","article-title":"Alterations in blood monocyte functions in Parkinson\u2019s disease.","volume":"34","author":"Nissen","year":"2019","journal-title":"Mov. Disord."},{"key":"B25","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1016\/S1474-4422(16)00070-3","article-title":"CSF and blood biomarkers for the diagnosis of Alzheimer\u2019s disease: A systematic review and meta-analysis.","volume":"15","author":"Olsson","year":"2016","journal-title":"Lancet Neurol."},{"key":"B26","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","year":"2011","journal-title":"Prog. Neurobiol."},{"key":"B27","doi-asserted-by":"publisher","first-page":"1591","DOI":"10.1002\/mds.26424","article-title":"MDS clinical diagnostic criteria for Parkinson\u2019s disease.","volume":"30","author":"Postuma","year":"2015","journal-title":"Mov. Disord."},{"key":"B28","doi-asserted-by":"publisher","first-page":"168","DOI":"10.31083\/j.jin2309168","article-title":"Relationships between serum lipid, uric acid levels and mild cognitive impairment in Parkinson\u2019s disease and multiple system atrophy.","volume":"23","author":"Ren","year":"2024","journal-title":"J. Integr. Neurosci."},{"key":"B29","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s41514-024-00177-x","article-title":"Predicting poor performance on cognitive tests among older adults using wearable device data and machine learning: A feasibility study.","volume":"10","author":"Sakal","year":"2024","journal-title":"NPJ Aging"},{"key":"B30","doi-asserted-by":"publisher","first-page":"e00598","DOI":"10.1002\/brb3.598","article-title":"Serum uric acid levels in Parkinson\u2019s disease and related disorders.","volume":"7","author":"Sakuta","year":"2017","journal-title":"Brain Behav."},{"key":"B31","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1002\/ana.26410","article-title":"Plasma MIA, CRP, and albumin predict cognitive decline in Parkinson\u2019s disease.","volume":"92","author":"Shen","year":"2022","journal-title":"Ann. Neurol."},{"key":"B32","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1016\/j.envres.2014.07.024","article-title":"Organochlorine chemicals and neurodegeneration among elderly subjects in Costa Rica.","volume":"134","author":"Steenland","year":"2014","journal-title":"Environ. Res"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1003","DOI":"10.3233\/JPD-201988","article-title":"Serum uric acid levels and non-motor symptoms in Parkinson\u2019s disease.","volume":"10","author":"van Wamelen","year":"2020","journal-title":"J. Parkinsons Dis."},{"key":"B34","doi-asserted-by":"publisher","first-page":"111188","DOI":"10.1016\/j.exger.2020.111188","article-title":"Principal component analysis of routine blood test results with Parkinson\u2019s disease: A case-control study.","volume":"144","author":"Wang","year":"2021","journal-title":"Exp. Gerontol."},{"key":"B35","doi-asserted-by":"publisher","first-page":"2191","DOI":"10.1001\/jama.2013.281053","article-title":"World medical association declaration of helsinki: Ethical principles for medical research involving human subjects.","volume":"310","year":"2013","journal-title":"JAMA"},{"key":"B36","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1016\/j.neuro.2021.12.001","article-title":"Analysis of serum levels of organochlorine pesticides and related factors in Parkinson\u2019s disease.","volume":"88","author":"Xu","year":"2022","journal-title":"Neurotoxicology"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1363","DOI":"10.1002\/mds.29417","article-title":"Summing MDS-UPDRS Parts 1 + 2 (Non-motor and Motor Experience of Daily Living): The Patient\u2019s Voice.","volume":"38","author":"Zou","year":"2023","journal-title":"Mov. Disord."}],"container-title":["Frontiers in Aging Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2025.1688653\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T06:31:16Z","timestamp":1762842676000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2025.1688653\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,11]]},"references-count":37,"alternative-id":["10.3389\/fnagi.2025.1688653"],"URL":"https:\/\/doi.org\/10.3389\/fnagi.2025.1688653","relation":{},"ISSN":["1663-4365"],"issn-type":[{"value":"1663-4365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,11]]},"article-number":"1688653"}}