Domain Adaptation Strategies for Transformer-Based Disease Prediction using Electronic Health Records
Driever, J.; Lentzen, M.; Madan, S.; Fröhlich, H.
Show abstract
Electronic Health Records (EHRs) offer rich data for machine learning, but model generalizability across institutions is hindered by statistical and coding biases. This study investigates domain adaptation (DA) techniques to improve model transfer, focusing on the Ex-Med-BERT transformer architecture for structured EHR data. We compare supervised and un-supervised DA methods in transferring predictive capabilities from the large-scale IBM Explorys database (U.S.) to the UK Biobank. Results across six clinical endpoints show that DA methods outperform fine-tuning, especially with limited target data. These findings emphasize selecting DA strategies based on target data availability and the benefit of incorporating source domain data for robust adaptation.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Uncertainty in Deep Learning for EEG under Dataset Shifts 95%
- Deep ensemble multitask classification of emergency medical call incidents combining multimodal data improves emergency medical dispatch 94%
- Enriching Representation Learning Using 53 Million Patient Notes through Human Phenotype Ontology Embedding 94%
Similar papers in this journal
- A Transformer-Based Model Trained on Large Scale Claims Data for Prediction of Severe COVID-19 Disease Progression 95%
- Evaluating Explanations from AI Algorithms for Clinical Decision-Making: A Social Science-based Approach 95%
- Graph Regularized Probabilistic MatrixFactorization for Drug-Drug Interactions Prediction 94%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.