{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T22:18:46Z","timestamp":1791929926555,"version":"4.3.4"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T00:00:00Z","timestamp":1771372800000},"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. Digit. Health"],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Predicting Parkinson's disease (PD) motor progression remains challenging despite advances in neuroimaging. Blood-based transcriptomic profiling offers a more accessible and cost-effective alternative. This study aimed to develop and validate a machine learning approach using blood-based transcriptomic data to predict 12-month motor severity in PD and to identify the transcriptomic features and biological pathways most strongly associated with progression.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      A Stacking Regressor ensemble model combining three gradient boosting algorithms (XGBoost, LightGBM, CatBoost) was developed using baseline Parkinson's Progression Markers Initiative (PPMI) data (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009390), integrating blood RNA sequencing (RNA-seq) and clinical features to predict 12-month UPDRS Part III scores. SHapley Additive exPlanations (SHAP) analysis was applied to identify key prognostic features, evaluating seven PD risk genes (SNCA, LRRK2, GBA, PRKN, PINK1, PARK7, VPS35) and pathway scores for mitochondrial dysfunction, neuroinflammation, and autophagy.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      On an independent test set (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u200978), the model achieved a Coefficient of Determination (R\u00b2) of 0.551 and Mean Absolute Error (MAE) of 6.01. SHAP analysis identified the baseline UPDRS\u2009\u00d7\u2009PINK1 interaction (UPDRS_BL\u2009\u00d7\u2009PINK1) as the most influential feature (mean |SHAP|\u2009=\u20090.283). Among transcriptomic features, VPS35 (mean |SHAP|\u2009=\u20090.010), GBA, and LRRK2 were most prominent. Mitochondrial dysfunction showed the highest pathway contribution (mean |SHAP|\u2009=\u20090.008).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The study establishes that machine learning integrating blood transcriptomics and clinical data effectively predicts motor progression in PD. Crucially, the interplay between initial clinical state and specific genetic backgrounds-particularly PINK1-is a more powerful prognostic indicator than any factor alone. This study provides systematic evidence that mitochondrial dysfunction is a dominant prognostic signal for disease progression, nominating key genes and pathways for future mechanistic and therapeutic investigation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fdgth.2026.1774436","type":"journal-article","created":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T06:54:48Z","timestamp":1771397688000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["An explainable ensemble machine learning model using baseline blood transcriptomics to predict Parkinson's disease motor progression"],"prefix":"10.3389","volume":"8","author":[{"given":"Yelda","family":"F\u0131rat","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Mudanya University","place":["Bursa, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,2,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"e50117","DOI":"10.2196\/50117","article-title":"Machine learning models for Parkinson disease: systematic review","volume":"12","author":"Tabashum","year":"2024","journal-title":"JMIR Med Inform"},{"key":"B2","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1038\/s41531-023-00581-2","article-title":"Identification of motor progression in Parkinson\u2019s disease using wearable sensors and machine learning","volume":"9","author":"Sotirakis","year":"2023","journal-title":"NPJ Parkinsons Dis"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1708","DOI":"10.1016\/j.clinph.2021.01.031","article-title":"Prediction of motor unified Parkinson\u2019s disease rating scale scores in patients with Parkinson\u2019s disease using surface electromyography","volume":"132","author":"Kleinholdermann","year":"2021","journal-title":"Clin Neurophysiol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"3486","DOI":"10.1109\/JBHI.2022.3157518","article-title":"Predicting UPDRS motor symptoms in individuals with Parkinson\u2019s disease from force plates using machine learning","volume":"26","author":"Exley","year":"2022","journal-title":"IEEE J Biomed Health Inform"},{"key":"B5","doi-asserted-by":"publisher","first-page":"734","DOI":"10.1038\/s43587-021-00088-6","article-title":"RNA sequencing of whole blood reveals early alterations in immune cells and gene expression in Parkinson\u2019s disease","volume":"1","author":"Craig","year":"2021","journal-title":"Nat Aging"},{"key":"B6","doi-asserted-by":"publisher","first-page":"21469","DOI":"10.1038\/s41598-022-25454-1","article-title":"Predictive modelling of Parkinson\u2019s disease progression based on RNA sequencing with densely connected deep recurrent neural networks","volume":"12","author":"Ahmed","year":"2022","journal-title":"Sci Rep"},{"key":"B7","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1038\/s43587-021-00042-6","article-title":"Deep sequencing of sncRNAs reveals hallmarks and regulatory modules of the transcriptome during Parkinson\u2019s disease progression","volume":"1","author":"Kern","year":"2021","journal-title":"Nat Aging"},{"key":"B8","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41531-022-00439-z","article-title":"Identification and prediction of Parkinson\u2019s disease subtypes and progression using machine learning in two cohorts","volume":"8","author":"Dadu","year":"2022","journal-title":"NPJ Parkinsons Dis"},{"key":"B9","doi-asserted-by":"publisher","first-page":"e70056","DOI":"10.1111\/cts.70056","article-title":"Practical guide to SHAP analysis: explaining supervised machine learning model predictions in drug development","volume":"17","author":"Ponce-Bobadilla","year":"2024","journal-title":"Clin Transl Sci"},{"key":"B10","doi-asserted-by":"publisher","first-page":"106584","DOI":"10.1016\/j.cmpb.2021.106584","article-title":"Explanation of machine learning models using shapley additive explanation and application for real data in hospital","volume":"214","author":"Nohara","year":"2022","journal-title":"Comput Methods Programs Biomed"},{"key":"B11","doi-asserted-by":"publisher","first-page":"16865","DOI":"10.1038\/s41598-023-44155-x","article-title":"The importance of interpreting machine learning models for blood glucose prediction in diabetes: an analysis using SHAP","volume":"13","author":"Prendin","year":"2023","journal-title":"Sci Rep"},{"key":"B12","doi-asserted-by":"publisher","first-page":"84486","DOI":"10.1109\/ACCESS.2022.3197671","article-title":"Explainable AI for healthcare 5.0: opportunities and challenges","volume":"10","author":"Saraswat","year":"2022","journal-title":"IEEE Access"},{"key":"B13","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1186\/s12874-022-01540-w","article-title":"Comparative analysis of explainable machine learning prediction models for hospital mortality","volume":"22","author":"Stenwig","year":"2022","journal-title":"BMC Med Res Methodol"},{"key":"B14","doi-asserted-by":"publisher","first-page":"2793361","DOI":"10.1155\/2022\/2793361","article-title":"Predicting Parkinson\u2019s disease progression: evaluation of ensemble methods in machine learning","volume":"2022","author":"Nilashi","year":"2022","journal-title":"J Healthc Eng"},{"key":"B15","first-page":"521","article-title":"Improving machine learning with ensemble learning on observational healthcare data","volume":"2023","author":"Naderalvojoud","year":"2024","journal-title":"AMIA Annu Symp Proc"},{"key":"B16","doi-asserted-by":"publisher","first-page":"10811","DOI":"10.3390\/ijerph182010811","article-title":"Deep ensemble learning approaches in healthcare to enhance the prediction and diagnosing performance: the workflows, deployments, and surveys on the statistical, image-based, and sequential datasets","volume":"18","author":"Nguyen","year":"2021","journal-title":"Int J Environ Res Public Health"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1177\/11795468221133611","article-title":"XGBoost, a novel explainable AI technique, in the prediction of myocardial infarction: a UK biobank cohort study","volume":"16","author":"Moore","year":"2022","journal-title":"Clin Med Insights Cardiol"},{"key":"B18","doi-asserted-by":"publisher","first-page":"100209","DOI":"10.1074\/jbc.REV120.014294","article-title":"Targeting mitophagy in Parkinson\u2019s disease","volume":"296","author":"Clark","year":"2021","journal-title":"J Biol Chem"},{"key":"B19","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1016\/j.neuron.2014.12.007","article-title":"The roles of PINK1, parkin, and mitochondrial fidelity in Parkinson\u2019s disease","volume":"85","author":"Pickrell","year":"2015","journal-title":"Neuron"},{"key":"B20","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1186\/s40478-020-01062-w","article-title":"PINK1\/PARKIN Signalling in neurodegeneration and neuroinflammation","volume":"8","author":"Quinn","year":"2020","journal-title":"Acta Neuropathol Commun"},{"key":"B21","doi-asserted-by":"publisher","first-page":"4368","DOI":"10.1093\/brain\/awac313","article-title":"DJ-1 is an essential downstream mediator in PINK1\/parkin-dependent mitophagy","volume":"145","author":"Imberechts","year":"2022","journal-title":"Brain"},{"key":"B22","article-title":"PPMI Database","volume-title":"MJFF.","year":"2024"},{"key":"B23","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1001\/archneurol.2009.295","article-title":"The clinically important difference on the unified Parkinson\u2019s disease rating scale","volume":"67","author":"Shulman","year":"2010","journal-title":"Arch Neurol"},{"key":"B24","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1002\/mdc3.12632","article-title":"Minimal clinically important difference for UPDRS-III in daily practice","volume":"5","author":"S\u00e1nchez-Ferro","year":"2018","journal-title":"Mov Disord Clin Pract"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.98.18_supplement.2585","article-title":"Estimating the meaningful within-patient change threshold for the MDS-UPDRS part III","volume":"37","author":"Zanigni","year":"2022","journal-title":"Mov Disord"},{"key":"B26","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1016\/B978-0-444-63233-3.00014-2","article-title":"Genetics of Parkinson disease","volume":"147","author":"Domingo","year":"2018","journal-title":"Handb Clin Neurol"},{"key":"B27","doi-asserted-by":"publisher","first-page":"763","DOI":"10.1002\/humu.21277","article-title":"Genetic etiology of Parkinson disease associated with mutations in the SNCA, PARK2, PINK1, PARK7, and LRRK2 genes: a mutation update","volume":"31","author":"Nuytemans","year":"2010","journal-title":"Hum Mutat"},{"key":"B28","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1093\/biomet\/87.4.954","article-title":"A new family of power transformations to improve normality or symmetry","volume":"4","author":"Yeo","year":"2000","journal-title":"Biometrika"},{"key":"B29","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1023\/B:MACH.0000015881.36452.6e","article-title":"Is combining classifiers with stacking better than selecting the best one?","volume":"54","author":"D\u017eeroski","year":"2004","journal-title":"Mach Learn"},{"key":"B30","author":"Lundberg","year":"2017"},{"key":"B31","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1016\/j.parkreldis.2021.02.026","article-title":"Predicting Parkinson\u2019s disease trajectory using clinical and neuroimaging baseline measures","volume":"85","author":"Nguyen","year":"2021","journal-title":"Parkinsonism Relat Disord"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1774436\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T06:54:51Z","timestamp":1771397691000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1774436\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,18]]},"references-count":31,"alternative-id":["10.3389\/fdgth.2026.1774436"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2026.1774436","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,18]]},"article-number":"1774436"}}