Automated Extraction of Social Determinants of Health from Clinical Notes

Event Time

Originally Aired - Wednesday, March 13 12:00 PM - 1:00 PM Eastern Time (US & Canada)

Info Alert

Create or Log in to My Show Planner to see Videos and Resources.

Info Alert

Create or Login to MyHIMSSPlanner to build your schedule and see more information.

Videos

Resources

Create or Log in to My Show Planner to see Videos and Resources.


{{chatHeaderContent}}

{{chatBodyContent}}

Resources

Create or Log in to My Show Planner to see Videos and Resources.


Info Alert

This Session Has Not Started Yet

Be sure to come back after the session starts to have access to session resources.

Event Location

Location: W110A


Event Information

Type: Other Educational Events

Session ID: EHL4

Title: Automated Extraction of Social Determinants of Health from Clinical Notes

Description: Social determinants of health (SDoH) data are important data points for both patient-level and population-level analyses, but unfortunately, this information is often unavailable due to limited presence in structured data. SDoH information most often resides in unstructured data (such as clinical notes), which require more advanced techniques to analyze. Here, we present a language model and FHIR-based prototype for automated extraction of  SDoH from EHRs, with support for writing this information back to the EHR as structured observations. The developed application automatically retrieves clinical notes via FHIR, extracts SDoH information using a fine-tuned language model, and writes this information back to the EHR in structured form.

Level: Intermediate

Learning Objective #1: Define social determinants of health and explain their significance in healthcare analytics as well as the challenges associated with accessing SDoH data

Learning Objective #2: Summarize the role that fine-tuned language models can play in extracting SDoH information from clinical notes

Learning Objective #3: Demonstrate the ability to use FHIR to interoperate with an electronic health system, such as the Epic Sandbox

Learning Objective #4: Analyze the benefits of converting unstructured SDoH data into structured observations to improve healthcare decision making


Session is a part of

Wednesday, March 13, 2024 - 12:00 PM
Emerging Healthcare Leaders Poster Sessions: Meet the Authors


Speakers


Continuing Education Credits

  • CAHIMS – 1 Credit(s)
  • CME – 1 Credit(s)
  • CNE – 1 Credit(s)
  • CPD UK – 1 Credit(s)
  • CPHIMS – 1 Credit(s)

  • Tracks


    Categories

    Health Equity

    • Social Determinants of Health

    Audience

    • Clinical Informaticist
    • Data Scientist
    • IT Professional