Chatbot uses AI to learn communicative practices in radiology

Radiologist from the University of California at Los Angeles (UCLA) have used artificial intelligence (AI) and machine learning to develop an application that acts as an assistant for clinicians when answering patient questions about upcoming radiologic care.

Presented at the Society of Interventional Radiology's 2017 Annual Scientific Meeting, the “chatbot” uses AI to teach itself new communicative tools.

"We theorized that artificial intelligence could be used in a low-cost, automated way in interventional radiology as a way to improve patient care," said Edward W. Lee, MD, PhD, assistant professor of radiology at UCLA and a study author. "Because artificial intelligence has already begun transforming many industries, it has great potential to also transform healthcare."

Using deep learning, researchers fed the platform 2,000 different data points in simulating conversations with patients. The platform relayed communications to a referring clinician and provided answers to questions, giving physicians real-time information about the patient. Responses included a variety of informational material including infographics, websites and programs. The platform learned from each encounter and grew continuously "smarter."

“This research will benefit many groups within the hospital setting. Patient care team members get faster, more convenient access to evidence-based information. Interventional radiologists spend less time on the phone and more time caring for their patients. And, most importantly, patients have better-informed providers able to deliver higher-quality care," said co-author Kevin Seals, MD, resident physician in radiology at UCLA and the programmer of the application.