Exploring ChatGPT's potential in the context of colon cancer patient education: proof-of-concept study (Preprint)
Bibliographic record
Abstract
Background:ChatGPT is a large language model capable of generating human-like conversation.It has demonstrated promise as a tool for medical education for both professionals and patients.Previous research in medical oncology and colon cancer showed a glimpse of its application on topics like colonoscopy, colorectal surgery, and guideline-based treatment.Objective: To evaluate ChatGPT's performance as a source of patient medical education for colon cancer Methods: A set of twenty non-expert questions were prepared and fed to ChatGPT three times.Later, generated responses were evaluated by two doctors for accuracy, simplicity (0-10), and consistency (0,1).Mean, median and standard deviation were calculated for both accuracy and simplicity scores along with the Intraclass Correlation Coefficient and confidence interval for inter-rater agreement assessment.For consistency, rate, cohen's kappa, standard error, and confidence interval were calculated.Results: Accuracy: Mean = 8.4,Median = 8.5, SD = 1.7.ICC: Avg.measures for absolute agreement = 0.7 (95% CI 0.25 to 0.88), for consistency = 0.74 (95% CI 0.34 to 0.9).Simplicity: Mean = 8.55, Median = 9, SD = 1.69.ICC: Avg.measures for absolute agreement = 0.65 (95% CI 0.12 to 0.86), for consistency = 0.72 (95% CI 0.28 to 0.89).Consistency: rate = 67.5%,Cohen's Kappa: 0.66 (SE = 0.18, 95% CI 0.31 to 1.0). Conclusions:In this study, we assessed ChatGPT's capabilities of answering patients' questions about colon cancer.Findings showed significant and promising results of answers' accuracy, simplicity, and consistency in multiple trials.However, there is room for improvement.As ChatGPT continues to gain popularity among users, research studies on the impact of this technology on patient outcomes are needed urgently to guide clinical application.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| 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".