EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An interpretable machine learning framework for opioid overdose surveillance from emergency medical services records

S Scott Graham iD, Savannah Shifflet, Maaz Amjad iD, Kasey Claborn

PLOS ONE · 2024

DOI: 10.1371/journal.pone.0292170 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, 2024. Verfasst von S Scott Graham und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Rhetoric & Writing, Center for Health Communication, University of Texas at Austin, Austin, TX, United States of Amedrica. Hauptthemen laut MEDLINE: Opiate Overdose, Drug Overdose, Emergency Medical Services. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIDA NIH HHS, SAMHSA HHS, Texas Health and Human Services Commission.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The goal of this study is to develop and validate a lightweight, interpretable machine learning (ML) classifier to identify opioid overdoses in emergency medical services (EMS) records. We conducted a comparative assessment of three feature engineering approaches designed for use with unstructured narrative data. Opioid overdose annotations were provided by two harm reduction paramedics and two supporting annotators trained to reliably match expert annotations. Candidate feature engineering techniques included term frequency-inverse document frequency (TF-IDF), a highly performant approach to concept vectorization, and a custom approach based on the count of empirically-identified keywords. Each feature set was trained using four model architectures: generalized linear model (GLM), Naïve Bayes, neural network, and Extreme Gradient Boost (XGBoost). Ensembles of trained models were also evaluated. The custom feature models were also assessed for variable importance to aid interpretation. Models trained using TF-IDF feature engineering ranged from AUROC = 0.59 (95% CI: 0.53–0.66) for the Naïve Bayes to AUROC = 0.76 (95% CI: 0.71–0.81) for the neural network. Models trained using concept vectorization features ranged from AUROC = 0.83 (95% 0.78–0.88)for the Naïve Bayes to AUROC = 0.89 (95% CI: 0.85–0.94) for the ensemble. Models trained using custom features were the most performant, with benchmarks ranging from AUROC = 0.92 (95% CI: 0.88–0.95) with the GLM to 0.93 (95% CI: 0.90–0.96) for the ensemble. The custom features model achieved positive predictive values (PPV) ranging for 80 to 100%, which represent substantial improvements over previously published EMS encounter opioid overdose classifiers. The application of this approach to county EMS data can productively inform local and targeted harm reduction initiatives.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Opiate OverdoseDrug OverdoseEmergency Medical ServicesHumansBayes TheoremMachine LearningAnalgesics, Opioid

Substanzen

Analgesics, Opioid

Autor:innen und Institutionen

  • Department of Rhetoric & Writing, Center for Health Communication, University of Texas at Austin, Austin, TX, United States of Amedrica.
  • Addiction Research Institute, University of Texas at Austin, Austin, TX, United States of Amedrica.
  • Steve Hicks School of Social Work, University of Texas at Austin, Austin, TX, United States of Amedrica.

ORCID-Profile: S Scott Graham, Maaz Amjad

Förderung

  • NIDA NIH HHS
  • SAMHSA HHS
  • Texas Health and Human Services Commission
  • National Institute on Drug Abuse

Zitieren

APA

Graham, S. S., Shifflet, S., Amjad, M., & Claborn, K. (2024). An interpretable machine learning framework for opioid overdose surveillance from emergency medical services records. PLOS ONE. https://doi.org/10.1371/journal.pone.0292170

Vancouver

Graham SS, Shifflet S, Amjad M, Claborn K. An interpretable machine learning framework for opioid overdose surveillance from emergency medical services records. PLOS ONE. 2024. doi:10.1371/journal.pone.0292170

BibTeX
@article{Graham2024,
  author = {Graham, S Scott and Shifflet, Savannah and Amjad, Maaz and Claborn, Kasey},
  title = {An interpretable machine learning framework for opioid overdose surveillance from emergency medical services records},
  journal = {PLOS ONE},
  year = {2024},
  doi = {10.1371/journal.pone.0292170}
}
Kostenlos starten →