Related Experiment Video
Updated: Jul 14, 2026
06:28
Biomechanical Changes Related to Low Back Pain: An Innovative Tool for Movement Pattern Assessment and Treatment Evaluation in Rehabilitation
Published on: December 13, 2024
ChatGPT improves readability in validated spine patient-reported outcome measures
George Abdelmalek1, Siraj Shaikh1,2, Daniel Coban1
1Department of Orthopedic Surgery, St. Joseph's University Medical Center, Paterson, NJ 07503, United States.
North American Spine Society Journal
|July 13, 2026
Summary
Large language models improved spine PROMs readability but altered content. Unsupervised AI revision risks measurement integrity, necessitating expert review for safe integration into outcomes research.
Area of Science:
- Medical Informatics
- Health Services Research
- Artificial Intelligence in Medicine
Background:
- Spine patient-reported outcome measures (PROMs) often exceed health literacy thresholds, hindering patient accessibility.
- Large language models (LLMs) show potential for simplifying medical text, but their impact on validated instruments is unknown.
Purpose of the Study:
- To assess the impact of ChatGPT 4.0 on the readability and content fidelity of validated spine PROMs.
- To determine if LLM-driven simplification meets health literacy standards without compromising measurement integrity.
Main Methods:
- Seventy-seven spine PROMs were revised using ChatGPT 4.0 for sixth-grade reading level.
- Readability metrics (grade level, linguistic indices) were assessed pre- and post-revision.
- Content fidelity was evaluated for changes in response scales, recall timeframes, and item meaning.
Main Results:
- Readability significantly improved across 18 linguistic parameters, with reduced word count and sentence complexity.
- Most readability indices met NIH/AMA sixth-grade compliance standards post-revision.
- However, 59.7% of PROMs had content errors, including altered response scales (23%) and simplified recall (18%).
Conclusions:
- ChatGPT 4.0 enhances spine PROM readability but can introduce content-altering errors.
- Unsupervised revision risks compromising the psychometric validity of PROMs.
- Expert review and psychometric validation are crucial before implementing AI-revised PROMs in research.
Related Concept Videos
01:21Methods of Documentation III: PIE
Problem-intervention-evaluation (PIE) is a systematic approach to documentation used in healthcare settings for clinical decision-making and patient care planning. It is a structured approach to organizing patient data based on problems, interventions, and evaluations. Here's a breakdown of its key features and considerations:
01:11Guidelines for Writing Outcome
When developing expected outcomes for a patient care plan, the nurse should adhere to the following recommendations:
Patient outcomes reflect the patient's response to the goal rather than what the nurse aims to achieve. Terminology should be observable and measurable to avoid the reader's interpretation. The desired outcome should be realistic and achievable in the designated care timeframe. Expected outcomes should align with adjunctive therapies. The outcome should enhance care evaluation by...
Patient outcomes reflect the patient's response to the goal rather than what the nurse aims to achieve. Terminology should be observable and measurable to avoid the reader's interpretation. The desired outcome should be realistic and achievable in the designated care timeframe. Expected outcomes should align with adjunctive therapies. The outcome should enhance care evaluation by...