Can ChatGPT Fool the Match? Artificial Intelligence Personal Statements for Plastic Surgery Residency Applications: A Comparative Study
Bibliographic record
Abstract
Introduction: Personal statements can be decisive in Canadian residency applications. With the rise in AI technology, ethical concerns regarding authenticity and originality become more pressing. This study explores the capability of ChatGPT in producing personal statements for plastic surgery residency that match the quality of statements written by successful applicants. Methods: ChatGPT was utilized to generate a cohort of personal statements for CaRMS (Canadian Residency Matching Service) to compare with previously successful Plastic Surgery applications. Each AI-generated and human-written statement was randomized and anonymized prior to assessment. Two retired members of the plastic surgery residency selection committee from the University of British Columbia, evaluated these on a 0 to 10 scale and provided a binary response judging whether each statement was AI or human written. Statistical analysis included Welch 2-sample t tests and Cohen's Kappa for agreement. Results: Twenty-two personal statements (11 AI-generated by ChatGPT and 11 human-written) were evaluated. The overall mean scores were 7.48 (SD 0.932) and 7.68 (SD 0.716), respectively, with no significant difference between AI and human groups ( P = .4129). The average accuracy in distinguishing between human and AI letters was 65.9%. The Cohen's Kappa value was 0.374. Conclusions: ChatGPT can generate personal statements for plastic surgery residency applications with quality indistinguishable from human-written counterparts, as evidenced by the lack of significant scoring difference and moderate accuracy in discrimination by experienced surgeons. These findings highlight the evolving role of AI and the need for updated evaluative criteria or guidelines in the residency application process.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 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".