Researchers examined whether the artificial intelligence (AI)-based chatbot ChatGPT can help provide answers to patients with cancer regarding radiation oncology treatment, according to a recent study published by Yalamanchili et al in JAMA Network Open.
Background
Over 60% (n = 500,000) of patients with cancer may require radiation oncology treatment per year, according to the National Cancer Institute. However, patients are often too overwhelmed to address all of their concerns during a clinical visit or may forget what their physicians communicated to them.
“The goal of this project is to empower patients,” explained lead study author Amulya Yalamanchili, MD, a radiation oncology resident at Northwestern Medicine. “This is a really technical field that can be hard to understand. All this information can be overwhelming to patients. If they have cancer in a sensitive area, they may not feel comfortable asking what their life will look like long term. The hope is patients can educate themselves with ChatGPT before and after they see a physician,” she added.
Study Methods and Results
In the recent study, the researchers assessed the capabilities of a specially designed ChatGPT to determine whether it could successfully answer 115 common questions about radiation oncology treatment.
The researchers found that a majority of ChatGPT’s responses were comparable or exceeded answers from professional societies in terms of accuracy, completeness, and conciseness.
The researchers suggested that ChatGPT may also reduce physicians’ workload and potentially reduce burnout, since the incidence of newly diagnosed cancer cases and demands on provider time continue to rise.
Although ChatGPT performed well overall, several responses were concerning—involving language ranked at a college reading level that may be more complex than the language used on professional society websites, omitting details about a specialized technology for brain tumors, and failing to mention the tiny tattoos sometimes used to position the patient for radiation oncology treatment.
Conclusions
The researchers emphasized that ChatGPT technology needs ongoing refinement and training in specialized medical domains.
“The study highlights the potential of AI-driven technologies, such as ChatGPT, to provide accurate and comprehensive responses to patient queries in the field of radiation oncology, but we need to make these AI chatbot responses easier for [patients] to understand,” noted senior study author P. Troy Teo, PhD, Instructor of Radiation Oncology at the Northwestern University Feinberg School of Medicine. “These AI chatbots could serve as valuable tools for assisting health-care providers in answering patient questions, particularly in contexts where access to expert advice may be limited,” he suggested.
The researchers plan to develop and analyze an in-house application using generative AI to answer patient questions regarding radiation oncology treatment.
“We're exploring how these advanced AI chat systems can do more than just deliver quick, accurate and personalized information about radiation oncology treatment,” underscored co–study author Bharat Mittal, MD, Chair of Radiation Oncology at the Northwestern University Feinberg School of Medicine. “We're also examining how they can be integrated into daily routines of patient care, ensuring care is more efficient and precise,” he concluded.
Disclosure: For full disclosures of the study authors, visit jamanetwork.com.
