Generative artificial intelligence (AI), including large language models such as ChatGPT, Gemini, and Copilot, is increasingly used by patients to obtain medical information and prepare for clinical encounters. Although these tools often provide guideline-consistent information, their responses may be incomplete, inaccurate, or lack personalization, potentially influencing patient expectations and clinical interactions. The impact of patient AI use on satisfaction, adherence, and physician-patient communication remains poorly understood.

This prospective comparative study will evaluate the effects of patient AI use prior to gynecologic consultations for endometriosis. Women attending a specialized endometriosis clinic will be categorized as AI users or non-users based on their preparation for the visit. Patient-reported outcomes, including satisfaction, expectations, adherence to physician recommendations, and pain during physical examination, will be assessed using validated questionnaires and visual analogue scales. Physicians, blinded to AI use, will independently assess patient engagement, trust, and compliance. Visit duration will also be recorded.

The primary objective is to determine whether AI use affects patient satisfaction and adherence to treatment recommendations. Secondary objectives include evaluating physician-perceived interaction quality and concordance between AI-generated guidance and physician recommendations. Findings from this study will provide critical evidence on how AI influences patient behavior and clinical care in endometriosis, informing best practices for integrating AI-informed patients into routine clinical encounters.

Generative artificial intelligence (AI), including large language models, is increasingly used by patients to obtain medical information prior to clinical encounters. These tools provide rapid access to health-related content and may influence patient knowledge, expectations, communication style, and decision-making during physician consultations. The effect of patient use of AI tools on the doctor-patient interaction and short-term clinical outcomes in the context of endometriosis care has not been systematically evaluated.

This prospective comparative study is designed to examine differences in patient-reported and physician-reported outcomes between patients who used AI tools to prepare for an endometriosis-related consultation and those who did not. The study is conducted in a gynecology outpatient clinic specializing in endometriosis care. All eligible adult women attending the clinic during the study period are invited to participate. Following informed consent, participants are categorized into two groups based on self-reported use of AI tools for preparation prior to the clinic visit.

Data collection is performed using structured questionnaires administered before and after the clinical consultation. The pre-visit questionnaire captures baseline information regarding prior use of artificial intelligence tools, including use for medical information and preparation for the current visit. Baseline demographic and clinical characteristics are also collected. The post-visit questionnaire captures patient-reported satisfaction with the consultation, intention to adhere to the physician's treatment recommendations, perceived concordance between AI-provided information and physician guidance, perceived added value of the physician beyond AI, and perceived necessity of the in-person visit.

Physicians conducting the consultations are blinded to patient AI usage status and complete a structured assessment immediately after each visit. Physician-reported measures include perceived patient trust, compliance, engagement, and prior knowledge, as well as the duration of the consultation. Pain experienced during the physical examination is recorded using a visual analog scale.

No discussion of questionnaire responses occurs between physicians and participants during the visit. All physicians involved in data collection hold valid Good Clinical Practice certification and are listed as investigators or sub-investigators. Data are collected anonymously using coded identifiers and stored securely in accordance with institutional data protection policies.

Comparisons are performed between AI users and non-users to evaluate differences in patient satisfaction, intention to adhere to treatment recommendations, physician-perceived interaction quality, pain during examination, and visit duration. This study aims to provide structured evidence regarding the influence of patient use of artificial intelligence on the clinical encounter in endometriosis care and to inform future integration of AI-informed patients into routine clinical practice.

Inclusion Criteria:

• Women aged ≥18.
• Attending clinic for endometriosis-related complaints.
• Able to give informed consent.

Exclusion Criteria:

• Cognitive impairment or psychiatric conditions that affect communication or the ability to provide informed consent

endometriosis is only womens disease

The study population will consist of adult women (aged ≥18 years) attending a specialized gynecology outpatient clinic for evaluation or management of endometriosis-related complaints. Eligible participants must be able to provide informed consent and complete study questionnaires independently.

Participants will include both new and returning patients with suspected or confirmed endometriosis. Individuals with cognitive impairment or psychiatric conditions that significantly interfere with communication or the ability to provide informed consent will be excluded.

Following enrollment, participants will be categorized based on self-reported use of generative artificial intelligence (AI) tools to prepare for their clinical visit. Demographic and baseline clinical characteristics-including age, ethnicity, body mass index, smoking status, medical comorbidities, reproductive history, and prior surgical history-will be collected to characterize the study population and allow for compariso