Identifying Mentions of Pain in Mental Health Records Text: A Natural Language Processing Approach

TY - CHAP

T1 - Identifying Mentions of Pain in Mental Health Records Text

T2 - A Natural Language Processing Approach

AU - Chaturvedi, Jaya

AU - Velupillai, Sumithra

AU - Stewart, Robert

AU - Roberts, Angus

N1 - Publisher Copyright: © 2024 International Medical Informatics Association (IMIA) and IOS Press.

PY - 2024/1/25

Y1 - 2024/1/25

N2 - Pain is a common reason for accessing healthcare resources and is a growing area of research, especially in its overlap with mental health. Mental health electronic health records are a good data source to study this overlap. However, much information on pain is held in the free text of these records, where mentions of pain present a unique natural language processing problem due to its ambiguous nature. This project uses data from an anonymised mental health electronic health records database. A machine learning based classification algorithm is trained to classify sentences as discussing patient pain or not. This will facilitate the extraction of relevant pain information from large databases. 1,985 documents were manually triple-annotated for creation of gold standard training data, which was used to train four classification algorithms. The best performing model achieved an F1-score of 0.98 (95% CI 0.98-0.99).

AB - Pain is a common reason for accessing healthcare resources and is a growing area of research, especially in its overlap with mental health. Mental health electronic health records are a good data source to study this overlap. However, much information on pain is held in the free text of these records, where mentions of pain present a unique natural language processing problem due to its ambiguous nature. This project uses data from an anonymised mental health electronic health records database. A machine learning based classification algorithm is trained to classify sentences as discussing patient pain or not. This will facilitate the extraction of relevant pain information from large databases. 1,985 documents were manually triple-annotated for creation of gold standard training data, which was used to train four classification algorithms. The best performing model achieved an F1-score of 0.98 (95% CI 0.98-0.99).

KW - natural language processing

KW - pain

KW - electronic health records

KW - mental health

KW - Transformers

UR - http://www.scopus.com/inward/record.url?scp=85183574727&partnerID=8YFLogxK

U2 - 10.48550/arXiv.2304.01240

DO - 10.48550/arXiv.2304.01240

M3 - Conference paper

SN - 9781643684567

VL - 310

T3 - Studies in Health Technology and Informatics

SP - 695

EP - 699

BT - MEDINFO 2023 — The Future Is Accessible

A2 - Bichel-Findlay, Jen

A2 - Otero, Paula

A2 - Scott, Philip

A2 - Huesing, Elaine

PB - IOS Press

ER -