An explainable ensemble machine learning model using baseline blood transcriptomics to predict Parkinson’s disease motor progression

Simple item page
dc.authorid0009-0003-8365-1000
dc.contributor.authorFırat, Yelda
dc.contributor.authorid41749
dc.date.accessioned2026-06-16T07:34:13Z
dc.date.available2026-06-16T07:34:13Z
dc.date.issued2026-02
dc.departmentFakülteler, Mühendislik, Mimarlık ve Tasarım Fakültesi, Bilgisayar Mühendisliği Bölümü
dc.descriptionEmerging Sources Citation Index (ESCI)
dc.description.abstractIntroduction: 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. Methods: 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 = 390), 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. Results: On an independent test set (n = 78), the model achieved a Coefficient of Determination (R & sup2;) of 0.551 and Mean Absolute Error (MAE) of 6.01. SHAP analysis identified the baseline UPDRS & times; PINK1 interaction (UPDRS_BL & times; PINK1) as the most influential feature (mean |SHAP| = 0.283). Among transcriptomic features, VPS35 (mean |SHAP| = 0.010), GBA, and LRRK2 were most prominent. Mitochondrial dysfunction showed the highest pathway contribution (mean |SHAP| = 0.008). Discussion: 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.
dc.identifier.citationFırat, Y. (2026). An explainable ensemble machine learning model using baseline blood transcriptomics to predict Parkinson's disease motor progression. FRONTIERS IN DIGITAL HEALTH, 8, 1-9. https://doi.org/10.3389/fdgth.2026.1774436
dc.identifier.doi10.3389/fdgth.2026.1774436
dc.identifier.eissn2673-253X
dc.identifier.endpage9
dc.identifier.startpage1
dc.identifier.urihttps://dspace.mudanya.edu.tr/handle/20.500.14362/430
dc.identifier.volume8
dc.identifier.wosWOS:001705989400001
dc.identifier.wosqualityQ1
dc.institutionauthorFırat, Yelda
dc.language.isoen
dc.publisherFRONTIERS MEDIA SA
dc.relation.journalFRONTIERS IN DIGITAL HEALTH
dc.relation.publicationcategoryMakale- Uluslararası- Hakemli Dergi- Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectmitochondrial dysfunction
dc.subjectParkinson’s disease
dc.subjectPPMI
dc.subjectRNA-seq
dc.subjectSHAP
dc.titleAn explainable ensemble machine learning model using baseline blood transcriptomics to predict Parkinson’s disease motor progression
dc.typeMakale
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
An explainable ensemble machine learning model using baseline blood transcriptomics to predict Parkinson’s disease motor progression.pdf
Size:
1.08 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.8 KB
Format:
Item-specific license agreed to upon submission
Description:
Download
Collections
Bilgisayar Mühendisliği Bölümü Koleksiyonu