Quantifying the Uncertainty and Risk Contributions of Activities of Daily Living Features in Dementia Prediction.

Activities of daily living (ADL) features contain important prognostic signals for future dementia and improve prediction model performance. However, assessing their contributions to predictive performance alone is insufficient to demonstrate how consistently and reliably individual ADL features contribute to dementia progression. To develop trustworthy and clinically actionable predictions using ADL features, it is crucial to quantify the prediction uncertainty associated with these features. This study introduces an uncertainty-aware framework combining credibility scores to quantify the uncertainty of the prediction model. Then, we measure the SHapley Additive exPlanations-based contributions of five-year impairment in each ADL to the predicted risk and model uncertainty. To address age-specific ADL patterns, we analyzed the contributions across different age groups. Our finding demonstrates that ADL impairments driving prediction probability are not necessarily those that drive prediction reliability. In particular, we categorize the ADL features into four sections namely "red flags", "golden signals", "noisy predictors" and "safety signals" for each group, based on their contribution (positive/negative) in dementia prediction and uncertainty quantification. This approach moves dementia detection beyond opaque probability scores toward a transparent and credible workflow for clinical application.