MétaCan
Menu
Back to cohort
Record W4405221756 · doi:10.1093/jsxmed/qdae167.094

(096) REAL WORLD UTILITY OF CHATGPT IN PRE-VASECTOMY COUNSELLING IN AN OFFICE-BASED SETTING: A PILOT STUDY

2024· article· en· W4405221756 on OpenAlexaff
David Chung, Haryana M. Dhillon, Karim Sidhom, Dhiraj S. Bal, Premal Patel, Gary Jawanda

Bibliographic record

VenueThe Journal of Sexual Medicine · 2024
Typearticle
Languageen
FieldMedicine
TopicSexual function and dysfunction studies
Canadian institutionsManitoba HealthUniversity of Manitoba
Fundersnot available
KeywordsVasectomyMedicineGynecologyFamily medicineFamily planningResearch methodologyEnvironmental healthPopulation

Abstract

fetched live from OpenAlex

Abstract Introduction There is increasing interest among the medical community on to developing new ways to utilize ChatGPT. New applications have included writing scientific manuscripts, drafting correspondents, as well as testing its ability on standardized medical licensing examinations. Despite ChatGPT demonstrating good medical knowledge, it is still unclear if this translates to real world clinical practice. A potential application of this technology is to provide patient counseling and to improve patient flow in one’s practice. Objective Our goal is to assess if pre-vasectomy counseling with ChatGPT safely streamlines the consultation process by reducing visit times and increasing patient satisfaction through the consultation process. Methods A single institutional prospective, randomized single-blinded pilot study was conducted to evaluate the safety and efficacy for the use of ChatGPT (v4.0) for pre-vasectomy counselling. All eligible patients who are interested in undergoing vasectomy were included in the study. Patients were excluded if unwilling to participate in the study or did not have a home computer/internet connection to interact with the ChatGPT software. Patient were randomized 1:1 to pre-appointment counselling with ChatGPT + standard in-person consultation to in-person consultation alone. Baseline demographic information was collected including age, level of education. Outcomes collected at that time were length of visit, number of questions, as well as a Likert scale (/10) questionnaire assessing participant satisfaction in the ChatGPT counselling. Chat logs were reviewed by 2 men’s health specialists to assess the accuracy and safety of ChatGPT responses. Descriptive statistics were performed as well as comparative analysis with the independent sample t-test method. Results Total of 18 patients were analyzed with a mean age of 35.8 (±) 5.4 (n = 9) in the intervention arm and 36.9 (±) 7.4 (n = 9) in the control arm. Overall pre-vasectomy counselling with ChatGPT was associated with provider perceived improved understanding of the procedures (8.8 ± 1.0 vs 6.7 ± 2.8; p = 0.047) and decreased length of in-person consultation (7.7 ± 2.3 min vs 10.6 ± 3.4 min; p = 0.05). Patients however reported no difference in how they rated the quality of their clinical encounter, with excellent scores seen in all domains. Patient experiences with ChatGPT in respect to pre-vasectomy counseling was also surveyed. Quality of information provided by ChatGPT, ease of access/use, and overall experience were rated highly at 8.3 (±) 1.9, 9.1 (±) 1.5, and 8.6 (±) 1.7 respectively. Some participants did express concern regarding the confidentiality of information at 4.9 (±) 2.9. Of the 19 total questions and responses provided by ChatGPT, 95% (n = 18/19) were considered to be accurate responses. Conclusions ChatGPT for pre-vasectomy counselling did show to improve the efficiency of encounters and provider perceived patient understanding of the procedure. ChatGPT was also able to provide accurate responses to questions regarding the vasectomy in 95% of cases. Disclosure Any of the authors act as a consultant, employee or shareholder of an industry for: Boston Scientific.

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 imitation

Not 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.

metaresearch head score (Codex)0.005
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.172
Threshold uncertainty score0.483

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0050.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.087
GPT teacher head0.371
Teacher spread0.283 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

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".

Quick stats

Citations0
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueThe Journal of Sexual MedicineSame topicSexual function and dysfunction studiesFrench-language works237,207