Augmenting Clinical Workflow With a Structured Chatbot for Patient History Collection and Diagnostic Support

Doctors spend much of each visit collecting the patient's medical history, and incomplete histories can delay diagnosis. This study tests an AI chatbot that interviews patients before their appointment and produces a structured summary of their history for the doctor. Adult patients at the first study site, a university gynecology outpatient clinic in Germany, answer the chatbot's questions on a tablet before they see their doctor. The doctor then takes the history and examines the patient as usual, without seeing the chatbot's output. Only after the doctor has finished planning care does the doctor review the chatbot's summary and rate how useful and accurate it is. The chatbot does not change patient care. Patients also rate how easy and acceptable the chatbot was to use. We will report how useful doctors find the summaries, how complete and correct they are, and how patients experience the tool.

Inclusion Criteria: Women 18 years or older First presentation or new complaint at the gynecology outpatient clinic (self-presentation, emergency, or referral) Sufficient German language skills to complete a structured patient interview independently Able to complete study participation without external support Written informed consent Exclusion Criteria: Acute emergency requiring immediate treatment (for example, impaired consciousness, hemodynamic instability, or acute bleeding requiring immediate care) Lack of legal or decisional capacity to consent Insufficient language skills Severe cognitive, visual, or motor impairment preventing tablet use Previous participation in this study Refusal or withdrawal of consent