Detecting Patient Deception and Adherence in Diabetes Support Using AI-Generated Conversation Summaries
Leveraging chat summaries to Enhance Doctor-Patient Communication
H.M.G. Koot (TU Delft - Electrical Engineering, Mathematics and Computer Science)
Catholijn Jonker – Mentor (TU Delft - Interactive Intelligence)
J.D. Top – Mentor (TU Delft - Interactive Intelligence)
Avishek Anand – Graduation committee member (TU Delft - Web Information Systems)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Unreliable patient self-reporting complicates diabetes management. This study investigates how AI-generated summaries of patient-chatbot conversations can be structured to help healthcare professionals detect deception and non-adherence. To address this, we developed a novel pipeline by first identifying four key behavioral indicators from literature and then using advanced prompt engineering to automatically flag these in structured summaries. The system's effectiveness was evaluated in an annotation experiment using synthetic chat data. The results showed that the summaries did not improve detection accuracy, increased annotation time, and revealed a critically low inter-annotator agreement. These findings highlight the inherent subjectivity and complexity of the detection task, demonstrating that the developed summarization method is not an effective intervention. Although the approach was unsuccessful, this research contributes a novel summarization pipeline, an open-source annotation tool, and a synthetic dataset, establishing a baseline for future work in enhancing doctor-patient communication.