Ovarian Cancer Screening and AI

Condition(s) studied

Investigational drug(s) / intervention(s)

ChatGPT - Control: Three-turn conversation; discusses ovarian cancer risk and epidemiology; avoids screening topics; concise responses (5-8 sentences). Mode of Delivery: Online chat interface; participant interacts directly with ChatGPT.

ChatGPT - Evidence-Based Screening Discussion: Three-turn conversation; asks participants about screening rationale; provides evidence-based info on benefits/harms, trial data, guideline positions; concise responses (5-8 sentences). Mode of Delivery: Online chat interface; participant interacts directly with ChatGPT.

Study summary

Gynecologists frequently overestimate the benefits and safety of ovarian cancer screening. AI-supported discussions may help correct these misperceptions. This study tests whether an AI-guided conversation about the evidence on ovarian cancer screening can improve gynecologists' knowledge and reduce non-evidence-based screening recommendations, compared with a control AI discussion on ovarian cancer prevalence.

Eligibility

Primary outcome measure(s)

• Change in intention to recommend ovarian cancer screening — Immediately post intervention
  Difference in participants' self-reported frequency of recommending ovarian cancer screening to average-risk women in the future after the ChatGPT interaction and their self-reported frequency of recommending the screening in the past.

Trial sites (1)

More Charite University, Berlin, Germany trials in Germany