# Improving Generalizability of Hip Fracture Risk Prediction via Domain Adaptation Across Multiple Cohorts

arXiv: https://arxiv.org/abs/2602.17962 · HTML: https://mlsanity.com/paper/2602.17962/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 24 references that are in the map.
- First posted on arXiv 20 Feb 2026.

## Builds on (most cited first, 4 of 4)

- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)](https://mlsanity.com/paper/2003.12206/) (2020)
- [A Review of Challenges and Opportunities in Machine Learning for Health](https://mlsanity.com/paper/1806.00388/) (2018)
- [An Advanced Two-Stage Model with High Sensitivity and Generalizability for Prediction of Hip Fracture Risk Using Multiple Datasets](https://mlsanity.com/paper/2510.15179/) (2025)

## Abstract (arXiv)

Clinical risk prediction models often fail to be generalized across cohorts because underlying data distributions differ by clinical site, region, demographics, and measurement protocols. This limitation is particularly pronounced in hip fracture risk prediction, where the performance of models trained on one cohort (the source cohort) can degrade substantially when deployed in other cohorts (target cohorts). We used a shared set of clinical and DXA-derived features across three large cohorts - the Study of Osteoporotic Fractures (SOF), the Osteoporotic Fractures in Men Study (MrOS), and the UK Biobank (UKB), to systematically evaluate the performance of three domain adaptation methods - Maximum Mean Discrepancy (MMD), Correlation Alignment (CORAL), and Domain - Adversarial Neural Networks (DANN) and their combinations. For a source cohort with males only and a source cohort with females only, domain-adaptation methods consistently showed improved performance than the no-adaptation baseline (source-only training), and the use of combinations of multiple domain adaptation methods delivered the largest and most stable gains. The method that combines MMD, CORAL, and DANN achieved the highest discrimination with the area under curve (AUC) of 0.88 for a source cohort with males only and 0.95 for a source cohort with females only), demonstrating that integrating multiple domain adaptation methods could produce feature representations that are less sensitive to dataset differences. Unlike existing methods that rely heavily on supervised tuning or assume known outcomes of samples in target cohorts, our outcome-free approaches enable the model selection under realistic deployment conditions and improve generalization of models in hip fracture risk prediction.