Related Experiment Video
Updated: Jun 27, 2026
07:35
A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
Published on: October 13, 2023
Quantifying the Functional Gap in Alkaptonuria Through Machine Learning and Clinical Data Integration
Anna Visibelli1, Rebecca Finetti1, Bianca Roncaglia1
1Department of Biotechnology, Chemistry and Pharmacy, University of Siena, 53100 Siena, Italy.
Bioengineering (Basel, Switzerland)
|June 26, 2026
Summary
Alkaptonuria (AKU) patients are functionally older than their chronological age, with a 15-year average functional age gap. This metric helps assess AKU
Area of Science:
- Rare inherited metabolic disorders
- Musculoskeletal health
- Biostatistics and data analysis
Background:
- Alkaptonuria (AKU) causes progressive musculoskeletal damage and chronic pain.
- Functional heterogeneity is a key characteristic of AKU patients.
- Quantifying functional variability is crucial for AKU management.
Purpose of the Study:
- Introduce and validate the functional age gap as a metric for AKU.
- Explore clinical predictors of functional age gap severity.
- Assess the utility of functional age gap in AKU patient assessment.
Main Methods:
- Utilized the ApreciseKUre database with 134 AKU patients.
- Calculated functional age using HAQ-DI and KOOS scores against normative data.
- Employed a bagging ensemble of decision trees and SHapley Additive exPlanations for analysis.
Main Results:
- 94.8% of AKU patients exhibited a positive functional age gap, averaging 15 years older.
- The predictive model showed moderate, stable classification performance (64%).
- Key predictors included age, AKUSSI spinal/joint pain, Schober test, and hip/knee activity.
Conclusions:
- The functional age gap is a valuable, interpretable metric for describing functional status in AKU.
- It serves as a hypothesis-generating tool for AKU research.
- Further validation in larger, longitudinal cohorts is needed for predictive utility.
