Extracting social support and social isolation information from clinical psychiatry notes: comparing a rule-based natural language processing system and a large language model

Unexpectedly, the RBS outperformed the LLMs across all metrics. An intensive review demonstrates that this finding is due to the divergent approach taken by the RBS and LLM. The RBS was designed and refined to follow the same specific rules as the gold-standard annotations. Conversely, the LLM was more inclusive with categorization and conformed to common English-language understanding. Both approaches offer advantages, although additional replication studies are warranted.

Authors

Institutions

Publication Details

Journal
Journal of the American Medical Informatics Association
Published
2024-10-18
DOI
https://doi.org/10.1093/jamia/ocae260
Citations
20
Primary Topic
Health disparities and outcomes
Type
article
Field-Weighted Citation Impact
10.56

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Extracting social support and social isolation information from clinical psychiatry notes: comparing a rule-based natural language processing system and a large language model

Praneet Kasi Reddy Jagadeesh Kumar, Myrna M. Weissman, Mark Olfson, Mohit Sharma et al.
20 citations
Journal of the American Medical Informatics Association
Health disparities and outcomes
10.56
article

Extracting social support and social isolation information from clinical psychiatry notes: comparing a rule-based natural language processing system and a large language model

Praneet Kasi Reddy Jagadeesh Kumar, Myrna M. Weissman, Mark Olfson, Mohit Sharma, Lauren Lepow, Braja Gopal Patra, Ardesheer Talati, Jorge A. Sánchez-Ruiz, Girish N. Nadkarni, Joanna M. Biernacka, Jyotishman Pathak, Euijung Ryu, J. John Mann, Veer Vekaria, Isotta Landi, Brian Fennessy, Alexander W. Charney, Prakash Adekkanattu, Yiye Zhang, Gavin Hynes
article en
20 citations

Abstract

Unexpectedly, the RBS outperformed the LLMs across all metrics. An intensive review demonstrates that this finding is due to the divergent approach taken by the RBS and LLM. The RBS was designed and refined to follow the same specific rules as the gold-standard annotations. Conversely, the LLM was more inclusive with categorization and conformed to common English-language understanding. Both approaches offer advantages, although additional replication studies are warranted.

Journal of the American Medical Informatics AssociationVol. 32(1)
Mayo Clinic (US), Cornell University (US), Columbia University Irving Medical Center (US), WinnMed (US), Mayo Clinic in Florida (US), Weill Cornell Medicine (US), New York State Psychiatric Institute, Columbia University (US), Icahn School of Medicine at Mount Sinai (US)
National Institutes of Health
Openalex Percentile: Top 1%
Health disparities and outcomes
10.56
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.