Evaluating a Chatbot as a Companion for Patients With Breast Cancer: Collaborative Pilot Study
Our findings demonstrate that an artificial intelligence-powered chatbot with GPT-4 and retrieval augmentation can effectively provide personalized, linguistically accessible, and largely accurate information to German-speaking patients with breast cancer. This approach holds considerable promise for improving patient-centered communication, empowering patients to make informed decisions. Nonetheless, observed limitations regarding response completeness and potential harm underscore the critical need for ongoing human oversight. Future research and development should prioritize regularly updated databases, advanced retrieval methods to handle complex document structures, multimodal capabilities, and clearly articulated disclaimers emphasizing the necessity of professional medical consultation. Our evaluation, along with the provided set of realistic patient questions, establishes a benchmark for future development and validation of German-language oncology chatbots.
Authors
- Sebastian Daniel Boie (ORCID: https://orcid.org/0000-0001-7993-7901)
- Michael P. Lux (ORCID: https://orcid.org/0000-0002-2781-2178)
- Esther Glastetter
- Christof von Kalle (ORCID: https://orcid.org/0000-0001-9221-3297)
- Felix Balzer (ORCID: https://orcid.org/0000-0003-1575-2056)
- Ulrich Müller (ORCID: https://orcid.org/0000-0002-8298-0465)
- Christian Lenz
Institutions
- Humboldt-Universität zu Berlin (DE)
- Pfizer (Germany) (DE)
- St. Vincenz-Krankenhaus Limburg (DE)
- Berlin Institute of Health at Charité - Universitätsmedizin Berlin (DE)
- Freie Universität Berlin (DE)
- Charité - Universitätsmedizin Berlin (DE)
Publication Details
- Journal
- JMIR Cancer
- Published
- 2025-06-17
- DOI
- https://doi.org/10.2196/68426
- Citations
- 2
- Primary Topic
- Economic and Financial Impacts of Cancer
- Type
- article
- Field-Weighted Citation Impact
- 6.26