Personalized Support in Hereditary Breast and Ovarian Cancer After Genetic Counseling by the Chatbot-Based GENIE Mobile App: Proof-of-Concept Wizard of Oz Study.

Abstract

Background: The primary aim of genetic counseling at a human genetics center is to empower individuals at risk for hereditary diseases to make informed decisions regarding their health. In Germany, genetic counseling sessions typically last approximately 1 hour and provide highly personalized information by a specialist in human genetics. Despite this, many counselees report a need for additional support following the counseling session.

Objective: This study introduces GENIE, a chatbot-based mobile app designed to assist individuals in the postcounseling phase, with a focus on hereditary breast and ovarian cancer. GENIE delivers expert-curated, personalized information tailored to the user's health and family circumstances. The content is presented through predefined dialogs between the user and the mobile assistant, aiming to extend the benefits of genetic counseling beyond the initial session.

Methods: A Wizard of Oz study was conducted to evaluate a functional prototype of GENIE. A total of 6 patients with breast cancer, at least 2 years postdiagnosis, participated in the study. Participants were given access to the app for a minimum of 1 week. The evaluation was based on their interaction with GENIE, which was personalized using the details of a fictitious patient. Data collection included semistructured interviews and a 45-item questionnaire to assess usability and content quality.

Results: The analysis of the interview and questionnaire data indicated high usability for GENIE, with a mean System Usability Score of 75.33 (SD 4.13). In total, 5 of the 6 participants used the app daily; 3 participants were willing to pay between US $5 and US $45 as a single purchase, while the other 3 participants agreed that the app should be free for the user and the costs should be directly covered by health insurance. Still, opinions on the app's appeal were divided. The layout was seen as moderately professional, a bit crowded, and slightly uninspiring. Nevertheless, participants highlighted the credibility and relevance of the content, noting its alignment with the fictitious patient's scenario. However, areas for improvement were identified, particularly concerning the app's design. All participants would recommend the app to other affected persons.

Conclusions: The findings suggest that a mobile app like GENIE can provide valuable support to individuals in the postcounseling phase of genetic services. GENIE offers distinct advantages over large language models, as the information it provides is carefully curated by human experts, minimizing the risk of inaccuracies or hallucinations and significantly enhancing the system's credibility. This study highlights the need to involve the user group as early as possible in the development of a digital health app. Future work will focus on the implementation of a comprehensive personalization engine, redesign of the user interface, and the execution of a large-scale, 2-arm randomized intervention study to validate GENIE's effectiveness.