Currently accepted at: JMIR Formative Research
Date Submitted: Dec 2, 2025
Open Peer Review Period: Jan 7, 2026 - Mar 4, 2026
Date Accepted: Mar 25, 2026
(closed for review but you can still tweet)
This paper has been accepted and is currently in production.
It will appear shortly on 10.2196/88818
The final accepted version (not copyedited yet) is in this tab.
Generative AI–Assisted Microlearning for Erectile Dysfunction Myth Reduction: A Single-Center Pre–Post Study
ABSTRACT
Background:
Erectile dysfunction (ED) is strongly influenced by persistent misconceptions that delay help-seeking and limit engagement with effective care. Patient-centered digital strategies, including generative–artificial intelligence (AI) microlearning, may improve sexual-health literacy; however, real-world evidence in urological practice remains sparse.
Objective:
To evaluate whether a clinician-supervised generative-AI microlearning video improves ED-related knowledge in adult men attending routine outpatient care.
Methods:
This single-center pre–post study included 200 adult men in a university urology clinic. Participants completed an 8-item ED-myth questionnaire immediately before and after watching a 3-minute educational video. The narration script was drafted using a large-language model (ChatGPT-5) and iteratively reviewed by urologists for accuracy and cultural appropriateness. The primary outcome was the within-participant change in total correct responses (0–8). Subgroup analyses assessed effects across age (<40 vs ≥40), education level, and self-reported ED. Paired analyses and multivariable logistic regression were used (α=.05).
Results:
All participants completed the intervention (mean age 44.0, SD 11.6 years). Total correct responses increased from 3.77 to 6.56 (mean Δ=2.79; P<.001), indicating a large effect (Cohen’s d >1.0). Knowledge gains were consistent across subgroups, with greater improvements among those with lower education. Self-reported ED was independently associated with lower odds of achieving ≥2-point improvement (odds ratio 0.46, 95% CI 0.26–0.81; P=.01). No adverse events or technical difficulties occurred.
Conclusions:
A brief generative-AI microlearning video, when supervised by clinicians, substantially reduced ED-related misconceptions in routine care. AI-assisted microlearning may serve as a scalable, low-burden adjunct to enhance sexual-health literacy during urological consultations. Long-term retention and behavioral outcomes should be evaluated in future trials. Clinical Trial: Not applicable.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.