Enhancing Suicide Attempt Risk Prediction Models with Temporal Clinical Note Features
Applied Clinical Informatics · 01.10.2024 · 15 (05) · 1107-1120
DOI: 10.1055/a-2411-5796 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Clinical Informatics, erschienen am 01.10.2024. Verfasst von Kevin J Krause und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, United States. Hauptthemen laut MEDLINE: Suicide, Attempted. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIMH NIH HHS, NLM NIH HHS, NICHD NIH HHS.
Abstract (Originalsprache)
Objectives
The objective of this study was to investigate the impact of enhancing a structured-data-based suicide attempt risk prediction model with temporal Concept Unique Identifiers (CUIs) derived from clinical notes. We aimed to examine how different temporal schemes, model types, and prediction ranges influenced the model's predictive performance. This research sought to improve our understanding of how the integration of temporal information and clinical variable transformation could enhance model predictions.
Methods
We identified modeling targets using diagnostic codes for suicide attempts within 30, 90, or 365 days following a temporally grouped visit cluster. Structured data included medications, diagnoses, procedures, and demographics, whereas unstructured data consisted of terms extracted with regular expressions from clinical notes. We compared models trained only on structured data (controls) to hybrid models trained on both structured and unstructured data. We used two temporalization schemes for clinical notes: fixed 90-day windows and flexible epochs. We trained and assessed random forests and hybrid long short-term memory (LSTM) neural networks using area under the precision recall curve (AUPRC) and area under the receiver operating characteristic, with additional evaluation of sensitivity and positive predictive value at 95% specificity.
Results
The training set included 2,364,183 visit clusters with 2,009 30-day suicide attempts, and the testing set contained 471,936 visit clusters with 480 suicide attempts. Models trained with temporal CUIs outperformed those trained with only structured data. The window-temporalized LSTM model achieved the highest AUPRC (0.056 ± 0.013) for the 30-day prediction range. Hybrid models generally showed better performance compared with controls across most metrics.
Conclusion
This study demonstrated that incorporating electronic health record-derived clinical note features enhanced suicide attempt risk prediction models, particularly with window-temporalized LSTM models. Our results underscored the critical value of unstructured data in suicidality prediction, aligning with previous findings. Future research should focus on integrating more sophisticated methods to continue improving prediction accuracy, which will enhance the effectiveness of future intervention.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, United States.
Förderung
- NIMH NIH HHS
- NLM NIH HHS
- NICHD NIH HHS
- NCRR NIH HHS
- AHRQ HHS
- Military Suicide Research Consortium
- National Center for Research Resources
- U.S. National Library of Medicine
Zitieren
APA
Krause, K. J., Davis, S. E., Yin, Z., Schafer, K. M., Rosenbloom, S. T., & Walsh, C. G. (2024). Enhancing Suicide Attempt Risk Prediction Models with Temporal Clinical Note Features. Applied Clinical Informatics, 15(05), 1107-1120. https://doi.org/10.1055/a-2411-5796
Vancouver
Krause KJ, Davis SE, Yin Z, Schafer KM, Rosenbloom ST, Walsh CG. Enhancing Suicide Attempt Risk Prediction Models with Temporal Clinical Note Features. Applied Clinical Informatics. 2024;15(05):1107-1120. doi:10.1055/a-2411-5796
BibTeX
@article{Krause2024,
author = {Krause, Kevin J and Davis, Sharon E and Yin, Zhijun and Schafer, Katherine M and Rosenbloom, Samuel Trent and Walsh, Colin G},
title = {Enhancing Suicide Attempt Risk Prediction Models with Temporal Clinical Note Features},
journal = {Applied Clinical Informatics},
year = {2024},
volume = {15},
number = {05},
pages = {1107--1120},
doi = {10.1055/a-2411-5796}
}
EUVIMED