Skip to main content
AAO-HNSF 2024 Annual Meeting & OTO EXPO Main banner
Icon Legend
This session is not in your schedule.
This session is in your schedule. Click again to remove it.
Back

Scientific Oral Presentations

Care Equity, Quality, and Safety

Session: Scientific Oral Presentations 2 - Care Equity, Quality, and Safety

Machine-Learning Modeling of Facial Trauma Volume With Regional Event and Weather Data

Monday, September 30, 2024
8:00 AM – 8:06 AM EDT
Location: MBCC, 235-237
Disclosure(s):
Feyisayo O. Adegboye, BA:

faculty for this accredited education activity has no relationship(s) with ineligible companies to disclose.

Introduction: Facial trauma volume is difficult to accurately predict. We aim to understand the capacity of climate and regional events to predict daily facial trauma volume. This can provide epidemiologic understanding and subsequently tailor workforce distribution and scheduling.

Methods: All facial trauma consults between 2017-2023 were extracted from a single Level I trauma center. Publicly accessible data on local concerts from 3 major venues, National Hockey League games (NHL), National Football League (NFL) games, and weather data from the National Oceanic and Atmospheric Administration data from local airports were merged with trauma data. Machine-learning random-forest plot feature identification was used to select variables to model high-volume facial trauma days (greater than 75th percentile).

Results: For analysis, 2,342 days were included for modeling. The median number of facial trauma consults was 3 (IQR 2-5). The month of May exhibited the highest rate of high-volume trauma days (13% of days, p < 0.001). On random-forest feature identification, the strongest predictive factors included weekend day status, average temperature, precipitation, hail, high/damaging winds, and holidays. Regional events were not included in the final models. On stepwise logistic regression modeling with pertinent variables, weekends (OR 2.20, 95%CI 1.80-2.69, p < 0.001), average temperature (OR 1.02, 95%CI 1.01-1.02, p < 0.001), and wind speed (0.97, 0.93-1.00, p = 0.049) were the only statistically significant variables.

Conclusions: Climate data were the primary factor that had predictive capacity for high-volume facial trauma days, more so than regional events. Testing models prospectively will help validate such models and help inform staffing for facial trauma coverage.

    Presenting Author(s)

  • Rahul Kamal Sharma, MD

    Resident Physician
    Vanderbilt University Medical Ctr
    Nashville, Tennessee, United States

    Disclosure information not submitted.

    • Co-Author(s)

  • Feyisayo O. Adegboye, BA

    Medical Student
    University of Virginia School of Medicine
    Marietta, GA, United States

    Disclosure(s):

    faculty for this accredited education activity has no relationship(s) with ineligible companies to disclose.

  • Rory J. Lubner, MD

    Physician Resident
    Vanderbilt University Medical Center
    Nashville, Tennessee, United States

    Disclosure information not submitted.

  • SY

    Shiayin F. Yang, MD

    Assistant Professor
    Vanderbilt University Medical Center, United States

    Disclosure information not submitted.

  • SS

    Scott J. Stephan, MD

    Associate Professor
    Vanderbilt University Medical Center
    Nashville, TN, United States

    Disclosure information not submitted.

    • Senior Author(s)

  • Priyesh N. Patel, MD

    Assistant Professor; Residency Program Director
    Vanderbilt University Medical Center
    Nashville, Tennessee, United States

    Disclosure information not submitted.