Predicting disease onset from electronic health records for population health management: a scalable and explainable Deep Learning approach

R Grout, R Gupta, R Bryant, MA Elmahgoub… - Frontiers in Artificial …, 2024 - frontiersin.org
Introduction The move from a reactive model of care which treats conditions when they arise
to a proactive model which intervenes early to prevent adverse healthcare events will benefit …

Generic medical concept embedding and time decay for diverse patient outcome prediction tasks

Y Li, W Dong, B Ru, A Black, X Zhang, Y Guan - Iscience, 2022 - cell.com
Summary Many fields, including Natural Language Processing (NLP), have recently
witnessed the benefit of pre-training with large generic datasets to improve the accuracy of …

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

J Wen, J Hou, CL Bonzel, Y Zhao, VM Castro… - Patterns, 2024 - cell.com
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 …

[HTML][HTML] Can Race-sensitive Biomedical Embeddings Improve Healthcare Predictive Models?

H Liu, N Moustafa-Fahmy, C Ta… - AMIA Summits on …, 2023 - ncbi.nlm.nih.gov
This reproducibility study presents an algorithm to weigh in race distribution data of clinical
research study samples when training biomedical embeddings. We extracted 12,864 …

Evaluation of Contextual and Non-contextual Word Embedding Models Using Radiology Reports

MS Khan - 2021 - search.proquest.com
Many clinical natural language processing (NLP) methods rely on non-contextual or
contextual word embedding models. Yet, few intrinsic evaluation benchmarks exist …