Mayo Clinic\u00a0researchers have developed and evaluated\u00a0MedEduChat, an electronic health record (EHR)\u00a0that\u00a0works with\u00a0a\u00a0large language model to\u00a0provide\u00a0accurate, patient-specific\u00a0prostate cancer\u00a0education.\u00a0<\/p>\n
The findings are published in\u00a0Nature Portfolio Digital Medicine\u00a0and highlight\u00a0a new approach\u00a0to delivering\u00a0timely, individualized guidance for people navigating a prostate cancer diagnosis.\u00a0<\/p>\n
Cancer patients often face uncertainty as they process complex information about their diagnosis and treatment options. Limited time with clinicians can make it difficult for patients to receive the detailed\u00a0answers they need to understand decisions that shape their care.\u00a0<\/p>\n
This\u00a0MedEduChat\u00a0study\u00a0demonstrates\u00a0how advanced AI, grounded in Mayo-validated clinical data, can help bridge these gaps by delivering clear, conversational explanations based on each patient’s own health record.\u00a0<\/p>\n
Understanding the patient experience using\u00a0AI\u00a0<\/p>\n
Fifteen prostate cancer patients interacted with\u00a0MedEduChat\u00a0for 20 to 30 minutes as part of a mixed-method usability study conducted at Mayo Clinic campuses in Arizona and Minnesota.\u00a0<\/p>\n
Patients reported higher confidence after using the tool, with Health Confidence Scores increasing from 9.9 to 13.9 on a 16-point scale. Usability scores were also high;\u00a0average survey responses ranked\u00a0MedEduChat\u00a083.7 out of 100.\u00a0<\/p>\n
Patients noted that\u00a0MedEduChat\u00a0helped them understand their diagnosis in a more accessible way. The\u00a0tool\u00a0provided relief by explaining unfamiliar or complex terms\u00a0in a clear and concise manner.\u00a0<\/p>\n
The conversational format\u00a0helped\u00a0participants replace incorrect assumptions with medically\u00a0accurate\u00a0information derived from their own EHR.\u00a0<\/p>\n
Clinician-evaluated accuracy and safety\u00a0<\/p>\n
Wei Liu, Ph.D.,\u00a0a radiation oncology medical physicist,\u00a0and three Mayo Clinic clinicians\u00a0independently reviewed 85 anonymized question-and-response pairs. They rated MedEduChat’s answers as highly correct (2.9 out of 3), complete (2.7 out of 3) and safe (2.7 out of 3).\u00a0<\/p>\n
Clinicians also noted strong patient-readiness and moderate personalization, reflecting\u00a0MedEduChat’s ability to tailor explanations to each person’s age, treatment\u00a0history\u00a0and cancer stage.\u00a0<\/p>\n
Although\u00a0MedEduChat\u00a0delivered\u00a0accurate\u00a0and clinically aligned information, clinicians emphasized the importance of ongoing monitoring to prevent errors that could arise from incomplete or inconsistently documented EHR data.\u00a0<\/p>\n
The research team incorporated a\u00a0multilayer\u00a0approach\u00a0to address these concerns and guide future system enhancements.\u00a0<\/p>\n
Combining patient-centered education with AI\u00a0<\/p>\n
MedEduChat\u00a0was designed with a structured educational model that combines closed-domain clinical data, semi-structured\u00a0guidance\u00a0and personalized interaction.\u00a0<\/p>\n
Patients can explore diagnosis details, learn about treatment\u00a0options\u00a0and side effects, and review lifestyle considerations and follow-up expectations. The tool draws only from validated sources,\u00a0such as Mayo Clinic materials and\u00a0National Comprehensive Cancer Network\u00a0guidelines.\u00a0<\/p>\n
This research demonstrates how large language models can be safely and effectively integrated into real clinical systems to improve cancer education. By combining advanced AI with Mayo Clinic’s electronic health records, MedEduChat delivers personalized, accurate and easy-to-understand explanations tailored to each patient’s medical history.”\u00a0<\/p>\n
Wei Liu, Ph.D., radiation oncology medical physicist<\/p>\n
Expanding AI\u00a0cancer research\u00a0<\/p>\n
The study team plans to translate this work into clinical use across all three Mayo Clinic campuses\u00a0in Arizona,\u00a0Florida\u00a0and Minnesota. Next steps include expanding\u00a0MedEduChat\u00a0beyond radiation oncology to\u00a0additional\u00a0cancer specialties. These efforts aim to make personalized AI-assisted education a routine part of cancer care.\u00a0<\/p>\n
This research was funded by the National Cancer Institute, the Eric and Wendy Schmidt Fund for AI Research and Innovation, the Fred C. and Katherine B.\u00a0Andersen\u00a0Foundation,\u00a0and the Kemper Marley Foundation.\u00a0<\/p>\n
Source:<\/p>\n
Journal reference:<\/p>\n