The Influence of Patient Use of Artificial Intelligence on Doctor-Patient Interaction and Clinical Outcomes in Endometriosis Consultations

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.

Study Overview

• Status: Not yet recruiting
• Conditions: Endometriosis
• Intervention / Treatment: Other: using Chat gpt before outpatient clinic visit

Detailed Description

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.

• Study Type: Observational
• Enrollment (Estimated): 94

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

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

Description

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

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
using Chat gpt before outpatient clinic visit	Other: using Chat gpt before outpatient clinic visit; This study involves a behavioral, non-randomized observational intervention based on patients' self-directed use of generative artificial intelligence (AI) tools prior to their clinical visit. The intervention group consists of patients who report using AI-based large language models (e.g., ChatGPT or similar tools) to prepare for their endometriosis-related consultation. AI use may include seeking information about symptoms, diagnosis, treatment options, prognosis, or formulating questions for the physician. No specific AI platform, prompts, or duration of use is mandated, and AI engagement occurs independently and outside the clinical setting. The control group includes patients who report no use of AI tools in preparation for the visit. No AI tools are introduced, recommended, or used during the clinical encounter by study personnel. Physicians are blinded to patient AI use status and conduct consultations according to standard clinical practice. Aside from questionnaire administ
Chat -gpt non users

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Patient Satisfaction and Treatment Plan Adherence After Consultation	Overall patient satisfaction will be measured immediately after the endometriosis consultation using a structured post-visit questionnaire and reported as a score on a 0-5 scale, where 0 indicates not satisfied at all and 5 indicates very satisfied. Intention to adhere to the physician's treatment plan will be measured immediately after the consultation as a binary outcome (yes/no) based on the patient's response to the post-visit questionnaire item asking whether she intends to follow the doctor's treatment recommendations.	Immediately after the consultation (same day)

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Physician-Perceived Interaction Quality and Consultation Characteristics	Physician-perceived patient trust, compliance, and engagement will be measured immediately after the consultation using physician-completed ratings on a 0-4 ordinal scale. Physician-perceived patient prior knowledge regarding endometriosis will be recorded using a structured post-visit physician assessment. Patient-reported concordance between information obtained from artificial intelligence tools and the physician's treatment recommendations will be measured immediately after the consultation as a binary response (yes/no) using the post-visit questionnaire. Patient-reported receipt of new or additional information from the physician beyond AI-provided content will also be measured as a binary response (yes/no). Patient perception of the necessity of an in-person visit after AI use will be recorded as a binary response (yes/no). Pain experienced during the physical examination will be measured during the consultation using a 0-10 visual analog scale (VAS). Duration of the clinical	During and immediately after the consultation (same day)

Collaborators and Investigators

• Sponsor: Hadassah Medical Organization

Study record dates

Study Major Dates

• Study Start (Estimated): February 1, 2026
• Primary Completion (Estimated): January 1, 2027
• Study Completion (Estimated): January 1, 2027

Study Registration Dates

• First Submitted: December 17, 2025
• First Submitted That Met QC Criteria: January 31, 2026
• First Posted (Actual): February 6, 2026

Study Record Updates

• Last Update Posted (Actual): February 6, 2026
• Last Update Submitted That Met QC Criteria: January 31, 2026
• Last Verified: January 1, 2026

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Urogenital Diseases; Genital Diseases; Female Urogenital Diseases; Female Urogenital Diseases and Pregnancy Complications; Genital Diseases, Female; Endometriosis
• Other Study ID Numbers: 0423-25-HMO

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No