Quantifying the Functional Gap in Alkaptonuria Through Machine Learning and Clinical Data Integration

Alkaptonuria (AKU) is a rare inherited metabolic disorder characterized by progressive musculoskeletal damage, chronic pain, and functional heterogeneity. To better quantify this variability, we introduced the concept of the functional age gap, defined as the difference between chronological age and a data-derived estimate of functional age. The study included 134 patients with AKU from the ApreciseKUre database. Functional age was calculated by mapping Health Assessment Questionnaire Disability Index (HAQ-DI) and Knee Injury and Osteoarthritis Outcome Score (KOOS) values to age-referenced normative data. Most patients (94.8%) showed a positive functional age gap, with a mean difference of 15 years, which indicates a functionally older profile than expected for their chronological age. A bagging ensemble of decision trees was then used to explore relationships between clinical variables and functional age gap severity. The model achieved moderate but stable classification performance across repeated stratified cross-validation (64%), consistent with an exploratory analysis in a small rare-disease cohort. SHapley Additive exPlanations analysis identified age, AKUSSI spinal pain, AKUSSI joint pain, Schober test, and hip and knee activity as the most influential predictors. These findings support the functional age gap as an interpretable, hypothesis-generating descriptive metric for functional assessment in AKU, while its predictive utility for individual patient stratification will require validation in larger and longitudinal cohorts.