Litcius/Paper detail

LATTE: Label-efficient incident phenotyping from longitudinal electronic health records

Jun Wen, Jue Hou, Clara-Lea Bonzel, Yihan Zhao, Víctor M. Castro, Vivian S. Gainer, Dana Weisenfeld, Tianrun Cai, Tianrun Cai, Yuk‐Lam Ho, Vidul Ayakulangara Panickan, Lauren Costa, Chuan Hong, J. Michael Gaziano, Katherine P. Liao, Junwei Lu, Kelly Cho, Tianxi Cai, Tianxi Cai

2023Patterns10 citationsDOIOpen Access PDF

Abstract

Electronic health record (EHR) data are increasingly used to support real-world evidence studies but are limited by the lack of precise timings of clinical events. Here, we propose a label-efficient incident phenotyping (LATTE) algorithm to accurately annotate the timing of clinical events from longitudinal EHR data. By leveraging the pre-trained semantic embeddings, LATTE selects predictive features and compresses their information into longitudinal visit embeddings through visit attention learning. LATTE models the sequential dependency between the target event and visit embeddings to derive the timings. To improve label efficiency, LATTE constructs longitudinal silver-standard labels from unlabeled patients to perform semi-supervised training. LATTE is evaluated on the onset of type 2 diabetes, heart failure, and relapses of multiple sclerosis. LATTE consistently achieves substantial improvements over benchmark methods while providing high prediction interpretability. The event timings are shown to help discover risk factors of heart failure among patients with rheumatoid arthritis.

Topics & Concepts

InterpretabilityEvent (particle physics)Computer scienceBenchmark (surveying)Dependency (UML)Longitudinal dataArtificial intelligenceElectronic health recordMachine learningData miningEconomic growthQuantum mechanicsGeodesyEconomicsHealth careGeographyPhysicsMachine Learning in HealthcareArtificial Intelligence in HealthcareChronic Disease Management Strategies