Study Comparing AI-Assisted and Traditional Weekly Symptom Reviews in Pelvic Radiotherapy Patients

What this Trial Is About

Researchers are evaluating the use of artificial intelligence AI and large language models to improve the efficiency and accuracy of weekly treatment consultations for patients undergoing radiotherapy in the pelvic area. The study aims to compare AI-generated symptom summaries with traditional doctor-led reviews to see if AI can match accuracy while saving time. This is a comparative clinical trial focusing on patients receiving pelvic radiotherapy, excluding those with prior pelvic reirradiation or surgery. Participants receive both standard weekly consultations with a physician and separate consultations where AI-assisted symptom summaries are generated using the OpenAI GPT-4 API. These AI summaries are compared with traditional doctor summaries by blinded specialist doctors using a validated questionnaire called the Physician Documentation Quality Instrument-9 PDQI-9. The study also gathers satisfaction ratings from both patients and physicians regarding clarity, accuracy, and overall experience. During the study, time needed to complete each type of consultation is tracked to assess efficiency. Patients undergo symptom questionnaires under medical supervision during their AI-assisted visits. Researchers evaluate documentation quality, time efficiency, physician satisfaction, and patient satisfaction over a two-month period. The trial began in July 2024 and is expected to complete by December 2024.

AI as an Aid for Weekly Symptom Intake in Radiotherapy