AI-PROGNOSIS_D3.4 / Final report on predictive modelling for PD

Executive summary The deliverable D3.4 is an update of D3.2 and the final version of predictive modelling for PD. The report provides an overview of all methodologies, findings and future directions of the AI-PROGNOSIS predictive models for Parkinson’s disease (PD). Identically to D3.2, the deliverable builds upon multimodal datasets and focuses on three main pillars of prognostic modelling: a) estimation of the risk of developing PD, b) estimation of progression in PD, and c) estimation of response to medication. Further, genetic analysis of Polygenic Risk Score (PRS) constituted a foundational component to quantify genetic susceptibility, in terms of both disease risk and progression, and inform the predictive models. The final version of predictive modelling for PD focuses on three key objectives, i.e., improving model performance, evaluating results against independent datasets, and ensuring the trustworthiness and explainability of the modelling outcomes. Therefore, these efforts pave the way to improve the reliability and clinical utility of predictive models for PD. This leads to more accurate and generalizable predictions, ensuring confidence among