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

• URL: http://arxiv.org/abs/2602.17962v1
• Date: Fri, 20 Feb 2026 03:37:05 GMT
• Title: Improving Generalizability of Hip Fracture Risk Prediction via Domain Adaptation Across Multiple Cohorts
• Abstract summary: We use a shared set of clinical and DXA-derived features across three large cohorts to evaluate the performance of three domain adaptation methods.<n>For a source cohort with males only, domain-adaptation methods consistently showed improved performance than the no-adaptation baseline.<n>Our outcome-free approaches enable the model selection under realistic deployment conditions and improve generalization of models in hip fracture risk prediction.
• Score: 15.756482189835566
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Dementia Etiology Diagnosis via Collaborative Meta Knowledge Enhancement [81.27196033392559]
  We propose a Collaborative Meta Knowledge Enhancement (COME) framework for dementia etiology diagnosis.<n>COME injects multi-center acquisition semantics, source identifiers, and modality indicators as heterogeneity-aware embeddings into a unified Transformer architecture for scale-up training.<n>Our method achieves state-of-the-art in-domain performance with a mean macro-averaged AUC of 85.62% and a 4.29-point gain over the strongest baseline.
  arXiv  Detail & Related papers  (2026-07-24T04:26:47Z)
• Federated Survival Analysis in Healthcare: A Multi-Model Evaluation on Cross-Institutional Heterogeneous Breast Cancer Data [0.6480963852869791]
  Federated learning (FL) offers a privacy-preserving alternative by training shared models without exchanging raw data.<n>Three survival models, the Cox Proportional Hazards model, DeepSurv, and Random Survival Forest (RSF), are compared across centralized, local, and federated training.<n>We derive practical, decision-oriented guidelines mapping data, privacy, interpretability, and resource constraints to recommended model and training-paradigm choices.
  arXiv  Detail & Related papers  (2026-06-22T19:14:51Z)
• Robust inference for risk heterogeneity under group imbalance [8.713612612607408]
  In intensive care unit studies, mortality risk associated with specific admission diagnoses can vary across ethnic groups.<n>Existing approaches for detecting risk heterogeneity are often sensitive to baseline model misspecification and regularization bias.<n>We propose a robust framework for inferring risk heterogeneity between two populations using Neymanity estimators that are locally insensitive to nuisance parameter estimation error.
  arXiv  Detail & Related papers  (2026-05-30T16:35:45Z)
• PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities [86.63247982275396]
  PRIME is a missing-aware multimodal self-supervised pretraining framework.<n>It learns robust and transferable representations from partially observed cohorts.<n>We evaluate PRIME on The Cancer Genome Atlas with label-free pretraining on 32 cancer types.
  arXiv  Detail & Related papers  (2026-04-05T21:14:27Z)
• Fairness-Aware Partial-label Domain Adaptation for Voice Classification of Parkinson's and ALS [1.7168966099863086]
  Voice-based digital biomarkers can enable scalable, non-invasive screening and monitoring of Parkinson's disease (PD) and Amyotrophic Lateral Sclerosis (ALS)<n>However, models trained on one cohort or device often fail on new acquisition settings due to cross-device and cross-cohort domain shift.<n>We propose a hybrid framework for unified three-class (healthy/PD/ALS) cross-domain voice classification from partially overlapping cohorts.
  arXiv  Detail & Related papers  (2026-02-20T11:18:44Z)
• Investigating the Impact of Histopathological Foundation Models on Regressive Prediction of Homologous Recombination Deficiency [52.50039435394964]
  We systematically evaluate foundation models for regression-based tasks.<n>We extract patch-level features from whole slide images (WSI) using five state-of-the-art foundation models.<n>Models are trained to predict continuous HRD scores based on these extracted features across breast, endometrial, and lung cancer cohorts.
  arXiv  Detail & Related papers  (2026-01-29T14:06:50Z)
• Causal and Federated Multimodal Learning for Cardiovascular Risk Prediction under Heterogeneous Populations [0.0]
  We create a single multimodal learning framework that integrates cross modal transformers with graph neural networks and causal representation learning to measure personalized CVD risk.<n>The model combines genomic variation, cardiac MRI, ECG waveforms, wearable streams, and structured EHR data to predict risk.<n>This study paves the way for a principled approach to clinically trustworthy, interpretable and privacy respecting CVD prediction at the population level.
  arXiv  Detail & Related papers  (2026-01-05T14:32:49Z)
• Cohort-Aware Agents for Individualized Lung Cancer Risk Prediction Using a Retrieval-Augmented Model Selection Framework [4.828586430285072]
  Lung cancer risk prediction remains challenging due to substantial variability across patient populations and clinical settings.<n>We propose a personalized lung cancer risk prediction agent that dynamically selects the most appropriate model for each patient.
  arXiv  Detail & Related papers  (2025-08-20T02:59:39Z)
• Targeted Data Fusion for Causal Survival Analysis Under Distribution Shift [46.84912148188679]
  Causal inference across multiple data sources offers a promising avenue to enhance the generalizability and replicability of scientific findings.<n>Existing approaches fail to address the unique challenges of survival analysis, such as censoring and the integration of discrete and continuous time.<n>We propose two novel methods for estimating target site-specific causal effects in multi-source settings.
  arXiv  Detail & Related papers  (2025-01-30T23:21:25Z)
• Ambiguous Medical Image Segmentation using Diffusion Models [60.378180265885945]
  We introduce a single diffusion model-based approach that produces multiple plausible outputs by learning a distribution over group insights. Our proposed model generates a distribution of segmentation masks by leveraging the inherent sampling process of diffusion. Comprehensive results show that our proposed approach outperforms existing state-of-the-art ambiguous segmentation networks.
  arXiv  Detail & Related papers  (2023-04-10T17:58:22Z)
• Domain-Specific Risk Minimization for Out-of-Distribution Generalization [104.17683265084757]
  We first establish a generalization bound that explicitly considers the adaptivity gap. We propose effective gap estimation methods for guiding the selection of a better hypothesis for the target. The other method is minimizing the gap directly by adapting model parameters using online target samples.
  arXiv  Detail & Related papers  (2022-08-18T06:42:49Z)
• Targeting Underrepresented Populations in Precision Medicine: A Federated Transfer Learning Approach [7.467496975496821]
  We propose a two-way data integration strategy that integrates heterogeneous data from diverse populations and from multiple healthcare institutions. We show that the proposed method improves the estimation and prediction accuracy in underrepresented populations, and reduces the gap of model performance across populations.
  arXiv  Detail & Related papers  (2021-08-27T04:04:34Z)
• Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data [62.29031007761901]
  This paper proposes a novel contrastive regularized clinical classification model. We introduce two unique positive sampling strategies specifically tailored for EHR data. Our framework yields highly competitive experimental results in predicting the mortality risk on real-world COVID-19 EHR data.
  arXiv  Detail & Related papers  (2021-04-07T06:02:04Z)
• Adversarial Sample Enhanced Domain Adaptation: A Case Study on Predictive Modeling with Electronic Health Records [57.75125067744978]
  We propose a data augmentation method to facilitate domain adaptation. adversarially generated samples are used during domain adaptation. Results confirm the effectiveness of our method and the generality on different tasks.
  arXiv  Detail & Related papers  (2021-01-13T03:20:20Z)
• On the Importance of Diversity in Re-Sampling for Imbalanced Data and Rare Events in Mortality Risk Models [0.0]
  The Surgical Outcome Risk Tool (SORT) is one of the tools developed to predict mortality risk throughout the entire period for major elective in-patient surgeries in the UK. In this study, we enhance the original SORT prediction model (SORT) by addressing the class imbalance within the dataset. Our proposed method investigates the application of diversity-based selection on top of common re-sampling techniques.
  arXiv  Detail & Related papers  (2020-12-15T09:45:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.