Related Experiment Video
Updated: Aug 6, 2026
05:19
Closed-Loop Neurostimulation for Biomarker-Driven, Personalized Treatment of Major Depressive Disorder
Published on: July 7, 2023
Symptom burden in multiple long-term conditions: An AI-supported, mixed-methods concept elicitation study
Sarah E Hughes1,2,3,4, Benjamin M A Hughes1,2, Shamil Haroon2
1Centre for Patient Reported Outcome Research, University of Birmingham, Birmingham, Birmingham, UK.
JRSM Open
|July 17, 2026
Summary
This study developed a conceptual framework for a new patient-reported outcome measure for symptom burden in MLTC. The approach combined existing data, AI, and expert review to identify key symptoms for better clinical management.
Area of Science:
- Health Services Research
- Patient-Reported Outcomes
- Artificial Intelligence in Healthcare
Background:
- Developing patient-reported outcome measures (PROMs) specific to Multiple Long-Term Conditions (MLTC) is crucial for effective symptom management.
- Existing PROMs may not adequately capture the complex symptom burden experienced by individuals with MLTC.
- A structured approach is needed to identify and organize relevant symptoms for a new MLTC-specific PROM.
Purpose of the Study:
- To establish the conceptual framework for the Symptom Burden Questionnaire™ for MLTC (SBQ™-MLTC), a novel patient-reported outcome measure.
- To identify, refine, and organize symptoms relevant to the MLTC population.
Main Methods:
- A mixed-methods approach was employed, including symptom list generation and assessment of face validity.
- Concept elicitation involved analyzing existing PROMs and utilizing AI-generated symptom lists.
- Seventeen healthcare practitioners reviewed and refined the symptom list to develop the conceptual framework.
Main Results:
- A total of 51 condition-specific PROMs were reviewed, and AI generated symptom lists for 24 prevalent MLTC conditions.
- An initial merged list of 2202 symptoms was reduced to 190 for expert review.
- The final conceptual framework incorporated 151 symptoms organized into 18 body system and functional domains.
Conclusions:
- This study successfully developed the conceptual framework for the SBQ™-MLTC, marking a significant step in creating an MLTC-specific PROM.
- The integration of generative AI, existing PROMs, and expert clinical review proved to be a feasible method for concept elicitation.
- The SBQ™-MLTC has the potential to enhance integrated, symptom-led clinical management strategies for individuals with MLTC.
