Improving the Readability of Institutional Heart Failure–Related Patient Education Materials Using GPT-4: Observational Study
Bibliographic record
Abstract
Background: Heart failure management involves comprehensive lifestyle modifications such as daily weights, fluid and sodium restriction, and blood pressure monitoring, placing additional responsibility on patients and caregivers, with successful adherence often requiring extensive counseling and understandable patient education materials (PEMs). Prior research has shown PEMs related to cardiovascular disease often exceed the American Medical Association's fifth- to sixth-grade recommended reading level. The large language model (LLM) ChatGPT may be a useful tool for improving PEM readability. Objective: We aim to assess the readability of heart failure-related PEMs from prominent cardiology institutions and evaluate GPT-4's ability to improve these metrics while maintaining accuracy and comprehensiveness. Methods: A total of 143 heart failure-related PEMs were collected from the websites of the top 10 institutions listed on the 2022-2023 US News & World Report for "Best Hospitals for Cardiology, Heart & Vascular Surgery." PEMs were individually entered into GPT-4 (version updated July 20, 2023), preceded by the prompt, "Please explain the following in simpler terms." Readability was assessed using the Flesch Reading Ease score, Flesch-Kincaid Grade Level (FKGL), Gunning Fog Index, Coleman-Liau Index, Simple Measure of Gobbledygook Index, and Automated Readability Index. The accuracy and comprehensiveness of revised GPT-4 PEMs were assessed by a board-certified cardiologist. Results: For 143 institutional heart failure-related PEMs analyzed, the median FKGL was 10.3 (IQR 7.9-13.1; high school sophomore) compared to 7.3 (IQR 6.1-8.5; seventh grade) for GPT-4's revised PEMs (P<.001). Of the 143 institutional PEMs, there were 13 (9.1%) below the sixth-grade reading level, which improved to 33 (23.1%) after revision by GPT-4 (P<.001). No revised GPT-4 PEMs were graded as less accurate or less comprehensive compared to institutional PEMs. A total of 33 (23.1%) GPT-4 PEMs were graded as more comprehensive. Conclusions: GPT-4 significantly improved the readability of institutional heart failure-related PEMs. The model may be a promising adjunct resource in addition to care provided by a licensed health care professional for patients living with heart failure. Further rigorous testing and validation is needed to investigate its safety, efficacy, and impact on patient health literacy.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".