AI Chatbot Helps Women Identify Heart Disease Risks and Symptoms

Heart disease is the leading cause of death among women and affects more than 60 million women in the U.S. Despite public health campaigns, awareness of its causes, risk factors, and symptoms has declined, potentially delaying care when women experience less obvious signs of a heart attack. To address this gap, researchers have developed a mobile conversational tool to help women better recognize heart disease risks and warning signs.

HeartBot II was developed by a University of California research team led by UC San Francisco, with collaborators from UCLA and UC Davis. The original HeartBot was launched in 2021 as a mobile tool designed to provide women with personalized conversations about heart health.

Enhanced in 2025, the current HeartBot II model includes learning modules covering heart disease basics, heart attack symptoms, risk factors, and prevention. As part of this update, the system transitioned from an SMS text-based format to a chatbot app that uses a large language model to support natural, personalized conversations.

HeartBot II can recall earlier exchanges with users, helping it respond in a more conversational manner. To reduce the risk of false or misleading medical information, its responses draw on a core knowledge bank developed by the research team. The team also refined the language to avoid unclear medical terms and make the information easier for average users to understand.

To build this knowledge bank, the researchers compiled almost 600 potential user questions, with research-based responses addressing variations of each question. They also examined how women discuss heart disease, including their language, rhythm, and cadence. Among the topics covered, the app explains that chest pain is common in both women and men, while women are more likely to experience shortness of breath, nausea, vomiting, and back or jaw pain.

The team is now completing a six-month randomized controlled trial involving 201 female UCSF Health patients. Half receive immediate access to HeartBot II educational sessions, while the remaining participants serve as a control group and will receive access later. Researchers are comparing changes in retention of heart disease information over time between the two groups.

“Getting accurate health information to women was not enough. The information also had to be understandable and engaging enough for women to use it,” said Yoshimi Fukuoka, Ph.D., RN, FAAN, nurse scientist and professor at UC San Francisco’s School of Nursing. 

“The goal was to increase women's awareness and knowledge of heart disease as a precursor to a heart attack and promote appropriate care-seeking behavior, particularly calling 911 when experiencing potential heart attack symptoms,” added Fukuoka.

Related Links
UC San Francisco