Automated identification of fall-related injuries in unstructured clinical notes - Summary - MDSpire

Automated identification of fall-related injuries in unstructured clinical notes

  • By

  • Wendong Ge

  • Lilian M Godeiro Coelho

  • Maria A Donahue

  • Hunter J Rice

  • Deborah Blacker

  • John Hsu

  • Joseph P Newhouse

  • Sonia Hernández-Díaz

  • Sebastien Haneuse

  • Brandon Westover

  • Lidia M V R Moura

  • July 26, 2024

  • 0 min

Share

Objective:

To develop and evaluate NLP models for identifying fall-related injuries (FRIs) in unstructured clinical notes, thereby enhancing clinical research efficiency.

Key Findings:
  • RoBERTa showed the best performance with precision of 0.90 (95% CI, 0.88-0.91), recall of 0.91 (95% CI, 0.90-0.93), and F1 score of 0.91 (95% CI, 0.89-0.92).
  • AUROC and AUPR curves were both 0.96 (95% CI, 0.95-0.97), indicating high accuracy in identifying FRIs.
Interpretation:

NLP models can effectively identify FRIs from unstructured clinical notes, enhancing research efficiency.

Limitations:
  • The study relied on keyword-based identification, which may miss nuanced cases of FRIs and could introduce bias.
  • Generalizability may be limited to the specific health-care system studied, affecting broader applicability.
Conclusion:

Automated NLP models represent a promising approach to improve the identification of FRIs in clinical documentation, potentially aiding clinical research and enhancing patient care.

Original Source(s)

Automated identification of fall-related injuries in unstructured clinical notes

  • by Wendong Ge, Lilian M Godeiro Coelho, Maria A Donahue, Hunter J Rice, Deborah Blacker, John Hsu, Joseph P Newhouse, Sonia Hernández-Díaz, Sebastien Haneuse, Brandon Westover, Lidia M V R Moura

  • July 26, 2024

Related Content

Low Follow-Up After Behavioral ED Care

Follow-up occurred after fewer than 15% of mental health ED visits and about 11% of substance use–related visits in Washington Medicaid claims.

CN-105, an Apolipoprotein E Mimetic Peptide, and Its Impact on Postoperative Delirium in Elderly Patients: Insights from the Phase 2 MARBLE Study

Association between neurodegenerative plasma biomarkers and geriatric depression in older adults with and without clinical dementia in Kinshasa, Democratic Republic of the Congo