Two-stage Federated Phenotyping and Patient Representation Learning
This addresses the challenge of generalizing medical NLP models across heterogeneous healthcare systems, enabling knowledge progression in learning health systems.
The paper tackles the problem of extracting information from unstructured clinical notes across multiple healthcare providers by developing a two-stage federated NLP method, demonstrating its performance on obesity and comorbidities phenotyping without moving data.
A large percentage of medical information is in unstructured text format in electronic medical record systems. Manual extraction of information from clinical notes is extremely time consuming. Natural language processing has been widely used in recent years for automatic information extraction from medical texts. However, algorithms trained on data from a single healthcare provider are not generalizable and error-prone due to the heterogeneity and uniqueness of medical documents. We develop a two-stage federated natural language processing method that enables utilization of clinical notes from different hospitals or clinics without moving the data, and demonstrate its performance using obesity and comorbities phenotyping as medical task. This approach not only improves the quality of a specific clinical task but also facilitates knowledge progression in the whole healthcare system, which is an essential part of learning health system. To the best of our knowledge, this is the first application of federated machine learning in clinical NLP.