Deep learning for identifying personal and family history of suicidal thoughts and behaviors from EHRs

Prakash Adekkanattu; Al’ona Furmanchuk; Yonghui Wu; Aman Pathak; Braja Gopal Patra; Sarah Bost; Destinee Morrow; Grace Hsin Min Wang; Yuyang Yang; Noah James Forrest; Yuan Luo; Theresa L. Walunas; Weihsuan Lo-Ciganic; Walid Gelad; Jiang Bian; Yuhua Bao; Mark Weiner; David Oslin; Jyotishman Pathak

doi:10.1038/s41746-024-01266-7

Deep learning for identifying personal and family history of suicidal thoughts and behaviors from EHRs

Prakash Adekkanattu^*, Al’ona Furmanchuk, Yonghui Wu, Aman Pathak, Braja Gopal Patra, Sarah Bost, Destinee Morrow, Grace Hsin Min Wang, Yuyang Yang, Noah James Forrest, Yuan Luo, Theresa L. Walunas, Weihsuan Lo-Ciganic, Walid Gelad, Jiang Bian, Yuhua Bao, Mark Weiner, David Oslin, Jyotishman Pathak

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

Personal and family history of suicidal thoughts and behaviors (PSH and FSH, respectively) are significant risk factors associated with suicides. Research is limited in automatic identification of such data from clinical notes in Electronic Health Records. This study developed deep learning (DL) tools utilizing transformer models (Bio_ClinicalBERT and GatorTron) to detect PSH and FSH in clinical notes derived from three academic medical centers, and compared their performance with a rule-based natural language processing tool. For detecting PSH, the rule-based approach obtained an F1-score of 0.75 ± 0.07, while the Bio_ClinicalBERT and GatorTron DL tools scored 0.83 ± 0.09 and 0.84 ± 0.07, respectively. For detecting FSH, the rule-based approach achieved an F1-score of 0.69 ± 0.11, compared to 0.89 ± 0.10 for Bio_ClinicalBERT and 0.92 ± 0.07 for GatorTron. Across sites, the DL tools identified more than 80% of patients at elevated risk for suicide who remain undiagnosed and untreated.

Original language	English (US)
Article number	260
Journal	npj Digital Medicine
Volume	7
Issue number	1
DOIs	https://doi.org/10.1038/s41746-024-01266-7
State	Published - Dec 2024

ASJC Scopus subject areas

Medicine (miscellaneous)
Health Informatics
Computer Science Applications
Health Information Management

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1038/s41746-024-01266-7

Cite this

Adekkanattu, P., Furmanchuk, A., Wu, Y., Pathak, A., Patra, B. G., Bost, S., Morrow, D., Wang, G. H. M., Yang, Y., Forrest, N. J., Luo, Y., Walunas, T. L., Lo-Ciganic, W., Gelad, W., Bian, J., Bao, Y., Weiner, M., Oslin, D., & Pathak, J. (2024). Deep learning for identifying personal and family history of suicidal thoughts and behaviors from EHRs. npj Digital Medicine, 7(1), Article 260. https://doi.org/10.1038/s41746-024-01266-7

@article{4a50f6cecfbc4234bab2aa1c0f7b48d9,

title = "Deep learning for identifying personal and family history of suicidal thoughts and behaviors from EHRs",

abstract = "Personal and family history of suicidal thoughts and behaviors (PSH and FSH, respectively) are significant risk factors associated with suicides. Research is limited in automatic identification of such data from clinical notes in Electronic Health Records. This study developed deep learning (DL) tools utilizing transformer models (Bio_ClinicalBERT and GatorTron) to detect PSH and FSH in clinical notes derived from three academic medical centers, and compared their performance with a rule-based natural language processing tool. For detecting PSH, the rule-based approach obtained an F1-score of 0.75 ± 0.07, while the Bio_ClinicalBERT and GatorTron DL tools scored 0.83 ± 0.09 and 0.84 ± 0.07, respectively. For detecting FSH, the rule-based approach achieved an F1-score of 0.69 ± 0.11, compared to 0.89 ± 0.10 for Bio_ClinicalBERT and 0.92 ± 0.07 for GatorTron. Across sites, the DL tools identified more than 80% of patients at elevated risk for suicide who remain undiagnosed and untreated.",

author = "Prakash Adekkanattu and Al{\textquoteright}ona Furmanchuk and Yonghui Wu and Aman Pathak and Patra, {Braja Gopal} and Sarah Bost and Destinee Morrow and Wang, {Grace Hsin Min} and Yuyang Yang and Forrest, {Noah James} and Yuan Luo and Walunas, {Theresa L.} and Weihsuan Lo-Ciganic and Walid Gelad and Jiang Bian and Yuhua Bao and Mark Weiner and David Oslin and Jyotishman Pathak",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2024.",

year = "2024",

month = dec,

doi = "10.1038/s41746-024-01266-7",

language = "English (US)",

volume = "7",

journal = "npj Digital Medicine",

issn = "2398-6352",

publisher = "Nature Publishing Group",

number = "1",

}

Adekkanattu, P, Furmanchuk, A, Wu, Y, Pathak, A, Patra, BG, Bost, S, Morrow, D, Wang, GHM, Yang, Y, Forrest, NJ, Luo, Y , Walunas, TL, Lo-Ciganic, W, Gelad, W, Bian, J, Bao, Y, Weiner, M, Oslin, D & Pathak, J 2024, 'Deep learning for identifying personal and family history of suicidal thoughts and behaviors from EHRs', npj Digital Medicine, vol. 7, no. 1, 260. https://doi.org/10.1038/s41746-024-01266-7

TY - JOUR

T1 - Deep learning for identifying personal and family history of suicidal thoughts and behaviors from EHRs

AU - Adekkanattu, Prakash

AU - Furmanchuk, Al’ona

AU - Wu, Yonghui

AU - Pathak, Aman

AU - Patra, Braja Gopal

AU - Bost, Sarah

AU - Morrow, Destinee

AU - Wang, Grace Hsin Min

AU - Yang, Yuyang

AU - Forrest, Noah James

AU - Luo, Yuan

AU - Walunas, Theresa L.

AU - Lo-Ciganic, Weihsuan

AU - Gelad, Walid

AU - Bian, Jiang

AU - Bao, Yuhua

AU - Weiner, Mark

AU - Oslin, David

AU - Pathak, Jyotishman

PY - 2024/12

Y1 - 2024/12

N2 - Personal and family history of suicidal thoughts and behaviors (PSH and FSH, respectively) are significant risk factors associated with suicides. Research is limited in automatic identification of such data from clinical notes in Electronic Health Records. This study developed deep learning (DL) tools utilizing transformer models (Bio_ClinicalBERT and GatorTron) to detect PSH and FSH in clinical notes derived from three academic medical centers, and compared their performance with a rule-based natural language processing tool. For detecting PSH, the rule-based approach obtained an F1-score of 0.75 ± 0.07, while the Bio_ClinicalBERT and GatorTron DL tools scored 0.83 ± 0.09 and 0.84 ± 0.07, respectively. For detecting FSH, the rule-based approach achieved an F1-score of 0.69 ± 0.11, compared to 0.89 ± 0.10 for Bio_ClinicalBERT and 0.92 ± 0.07 for GatorTron. Across sites, the DL tools identified more than 80% of patients at elevated risk for suicide who remain undiagnosed and untreated.

AB - Personal and family history of suicidal thoughts and behaviors (PSH and FSH, respectively) are significant risk factors associated with suicides. Research is limited in automatic identification of such data from clinical notes in Electronic Health Records. This study developed deep learning (DL) tools utilizing transformer models (Bio_ClinicalBERT and GatorTron) to detect PSH and FSH in clinical notes derived from three academic medical centers, and compared their performance with a rule-based natural language processing tool. For detecting PSH, the rule-based approach obtained an F1-score of 0.75 ± 0.07, while the Bio_ClinicalBERT and GatorTron DL tools scored 0.83 ± 0.09 and 0.84 ± 0.07, respectively. For detecting FSH, the rule-based approach achieved an F1-score of 0.69 ± 0.11, compared to 0.89 ± 0.10 for Bio_ClinicalBERT and 0.92 ± 0.07 for GatorTron. Across sites, the DL tools identified more than 80% of patients at elevated risk for suicide who remain undiagnosed and untreated.

UR - http://www.scopus.com/inward/record.url?scp=85205255257&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85205255257&partnerID=8YFLogxK

U2 - 10.1038/s41746-024-01266-7

DO - 10.1038/s41746-024-01266-7

M3 - Article

C2 - 39341983

AN - SCOPUS:85205255257

SN - 2398-6352

VL - 7

JO - npj Digital Medicine

JF - npj Digital Medicine

IS - 1

M1 - 260

ER -

Deep learning for identifying personal and family history of suicidal thoughts and behaviors from EHRs

Abstract

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this