SBDH-Reader: A Large Language Model-Powered Method for Extracting Social and Behavioral Determinants of Health from Clinical Notes
Read the abstract
Moderator
Presenter
Zifan "Ivan" Gu, MS
University of Texas Southwestern Medical Center
Statement of Purpose
Social and behavioral determinants of health (SBDH), including employment, housing stability, substance use, and other life context factors, are critical drivers of clinical outcomes and health disparities. However, clinicians prefer documenting this information in free text. The resulting variability in language, structure, and documentation style across note types makes chart review time-consuming and limits scalable extraction for clinical decision support and research. Consequently, essential contextual factors often remain underutilized in downstream analytics and care delivery.
Our team developed SBDH-Reader, a large language model–based framework to systematically extract high-fidelity SBDH data from free-text clinical notes. Developed in critical care cohorts and externally validated in heart failure populations, we demonstrate that a general purpose LLM (without task-specific fine-tuning) accurately and efficiently identify SBDH information across various note types and documentation patterns. This work establishes a scalable framework for capturing individual-level SBDH data to support care delivery, quality improvement, and translational research.
Learning Objectives
- Characterize the structural and stylistic heterogeneity of clinical note types and their implications for SBDH extraction.
- Design an LLM-based approach for extracting SBDH from free-text clinical documentation.
- Evaluate the generalizability of foundation models across distinct patient populations and documentation patterns.
Additional Information
The target audience for this activity includes physicians, nurses, other healthcare providers, and medical informaticians.
No commercial support (funding from a governmental agency, ineligible company or in-kind donation) was received for this activity.
Completion of this “Enduring Material” is demonstrated by participating in the live webinar or viewing the on-demand recording, engaging with presenters during the live session by submitting questions, and completing the evaluation survey at the conclusion of the course.
Learners may claim credit and download a certificate upon submission of the evaluation. Participation in additional resources and the course forum is encouraged but optional.
ACCME Accreditation Statement
The American Medical Informatics Association is accredited by the Accreditation Council for Continuing Medical Education (ACCME) to provide continuing medical education for physicians.
Designation Statement
The American Medical Informatics Association designates this Enduring activity for a maximum of 1 AMA PRA Category 1 Credit(s)™. Physicians should claim only the credit commensurate with the extent of their participation in the activity.
ANCC Accreditation Statement
The American Medical Informatics Association is accredited as a provider of nursing continuing professional development by the American Nurses Credentialing Center's Commission on Accreditation.
Nurse Planner (Content): Robin Austin, PhD, DNP, DC, RN, NI-BC, FAMIA, FAAN
Approved Contact Hours: 1 CME/CNE
*Learners may earn 1 contact hour for each monthly Journal Club session, for a maximum of 6 contact hours per year. To receive the full 6 contact hours, participants must either attend the live webinar or view the on-demand recording for each Regularly Scheduled Series (RSS) Journal Club presentation.
It is the policy of the American Medical Informatics Association (AMIA) to ensure that Continuing Medical Education (CME) activities are independent and free of commercial bias. To ensure educational content is objective, balanced, and guarantee content presented is in the best interest of its learners and the public, the AMIA requires that everyone in a position to control educational content disclose all financial relationships with ineligible companies within the prior 24 months. An ineligible company is one whose primary business is producing, marketing, selling, re-selling or distributing healthcare products used by or on patients. Examples can be found at accme.org.
In accordance with the ACCME Standards for Integrity and Independence in Accredited Continuing Education, AMIA has implemented mechanisms prior to the planning and implementation of this CME activity to identify and mitigate all relevant financial relationships for all individuals in a position to control the content of this CME activity.
In accordance with the ACCME Standards for Integrity and Independence in Accredited Continuing Education, AMIA has implemented mechanisms prior to planning and implementation of this CME activity to identify and mitigate all relevant financial relationships for all individuals in a position to control the content of this CME activity.
Faculty and planners who refuse to disclose any financial relationships with ineligible companies will be disqualified from participating in the educational activity.
For an individual with no relevant financial relationship(s), course participants must be informed that no conflicts of interest or financial relationship(s) exist.
Disclosures
Disclosures of relevant financial relationships of all planners and presenters of the Journal Club.
Planning Committee
The planning committee and reviewers reported that they have no relevant financial relationship(s) with ineligible companies to disclose.
- Joanna Abraham, PhD, FACMI, FAMIA
- Ratie Akabari, MS
- Zo Co
- Ivan Gu
- Andrew Lu, MSc, RN
- Elanore "Nora" Rae Scheer, ME
The following planning committee members have relevant financial relationship(s) with ineligible companies to disclose.
- Amy Krefman, MS - AbbVie; Individual Stocks/Stock Options
Presenter
The following presenters have no relevant financial relationship(s) with ineligible companies to disclose.
AMIA Staff
The AMIA staff have no relevant financial relationship(s) with ineligible companies to disclose.
*All of the relevant financial relationships listed for these individuals have been mitigated.