Cross-Lingual Knowledge Transfer for Clinical Phenotyping
This addresses the challenge of applying clinical phenotyping to clinics using languages other than English with limited data, offering incremental improvements over existing methods.
The paper tackled the problem of clinical phenotyping for non-English languages by investigating cross-lingual knowledge transfer strategies, finding that translation-based methods with domain-specific encoders and cross-lingual encoders with adapters outperform state-of-the-art models, especially for rare phenotypes, and improve performance to compensate for data sparseness.
Clinical phenotyping enables the automatic extraction of clinical conditions from patient records, which can be beneficial to doctors and clinics worldwide. However, current state-of-the-art models are mostly applicable to clinical notes written in English. We therefore investigate cross-lingual knowledge transfer strategies to execute this task for clinics that do not use the English language and have a small amount of in-domain data available. We evaluate these strategies for a Greek and a Spanish clinic leveraging clinical notes from different clinical domains such as cardiology, oncology and the ICU. Our results reveal two strategies that outperform the state-of-the-art: Translation-based methods in combination with domain-specific encoders and cross-lingual encoders plus adapters. We find that these strategies perform especially well for classifying rare phenotypes and we advise on which method to prefer in which situation. Our results show that using multilingual data overall improves clinical phenotyping models and can compensate for data sparseness.