Two-stage Federated Phenotyping and Patient Representation Learning

By Dianbo Liu, Dmitriy Dligach, Timothy Miller. 2019

92 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

LoAdaBoost: Loss-based AdaBoost federated machine learning with reduced computational complexity on IID and non-IID intensive care data (2018, methodology): “used a federated transfer learning strategy to balance global and local learning [13–16,20].”
A review of applications in federated learning (2020, methodology): “Proceedings of the 18th BioNLP Workshop and Shared Task, 283–291. https://doi.org/10.18653/v1/W19-5030 Liu, F., Wu, X., Ge, S., Fan, W. and Zou, Y. (2020).”
Federated Learning for Smart Healthcare: A Survey (2021, methodology): “• FL is also useful for facilitating in-home health monitoring, by training a global model from distributed homes under the control of a data server, while preventing data leakage by keeping user data locally [92], [93].”
Federated Learning for Healthcare Informatics (2019, background): “[67] conducted both patient representation learning and obesity comorbidity phenotyping in a federated manner and got good results.”
A Survey on federated learning* (2020, background): “Studies[58] also demonstrated that FL can be applied in the domain of Natural language processing (NLP) to analyze valid information from health records.”
Federated Learning for Healthcare: Systematic Review and Architecture Proposal (2022, methodology): “[26] employ a deep averaging network and SVM to predict diagnoses using plain text EHR records.”
FedHome: Cloud-Edge Based Personalized Federated Learning for In-Home Health Monitoring (2020, unknown): “demonstrate its superior performance [14].”