Using AI to Improve Communication Between the Doctor and Patient

Productive communication with the physician is essential for the patient to see improvements in their condition, however, most doctors have never had their communication skills formally assessed. When the doctor does not describe conditions and treatments to their patient in a comprehensible manner, it can lead to improper medication use, worsening of the condition, and low patient satisfaction. Exploring potential digital solutions to this gap in communication, researchers from The Dartmouth Institute for Health Policy and Clinical Practice, Trinity College Dublin, and the University of Edinburgh discussed the potential of artificial intelligence (AI) in enhancing patient-provider interactions in a BMJ article.

“Many clinicians’ communications skills aren’t formally assessed–either during school or in early practice,” said senior author Glyn Elwyn, MD, PhD, MSc, Dartmouth Institute Professor. “At the same time, there is a lot of evidence that clinicians often struggle when communicating with their patients. It’s hard to improve on something when you’re not being given any feedback and don’t know how you’re doing.”

Elwyn and colleagues claim that AI is an innovative solution that could completely change the communication process in healthcare. Providing practitioners with personalized, detailed assessments of their communication skills, AI may provide the first widely used tool for evaluating physician communication. In their article, Elwyn and his associates identify three main areas where AI and recordings of patient-physician interactions could be used to improve communication between the two parties.

Analysis of Conversations

Automatic analysis of words and phrasing in dialogues between a doctor and their patient could reveal whether the two understood each other. This could also provide feedback as to whether the provider is properly recording patient histories, recommending treatments based on evidence, and using words that the patient can understand. AI also has the potential to analyze conversations in real-time and suggest diagnoses that they may not have been considering and offer a broad range of treatment suggestions.

Letting the Patient Speak Their Mind

AI could also analyze the proportion of time that the physician lets the patient speak compared to how much time they spend talking. Many patients complain that their providers do not take pauses and allow them to voice their own questions and concerns, therefore it could be very beneficial to address this issue with AI. When the patient is given space to talk, higher adherence to medications and better memory of information is typically correlated. This analysis of dialogue could eventually provide insight that helps prevent premature decisions such as the ordering of invasive procedures. This AI could, for instance, guide further questioning that leads to a diagnosis of heartburn instead of cardiac pain.

Tone and Style in Voice

Algorithms have already been used to analyze the commercial pilot’s vocal pitch and energy, and this technology could have similar benefits in the healthcare industry. Analyzing these vocal features could help detect high-risk situations in which the doctor is under stress that inhibits their communication skills. In addition, this vocal analysis could also provide insight into the patient’s mental and physical health. Conditions like depression and heart failure can be characterized by distinct vocal changes that an AI-powered speech recognition device could detect.

Challenges Accompanied by AI Use in Healthcare

Despite these benefits, there are many challenges to the application of AI in healthcare. For example, issues such as patient privacy can be brought into question when there are devices in the room recording and analyzing conversations. In addition, even the most advanced AI systems are currently not capable of fulling decoding the complicated dialogue that occurs in the medical setting.

“Five years ago, the idea of using AI to analyze medical communication wouldn’t have been on anyone’s radar,” said Elwyn. “As the technology advances, it will be interesting to see whether healthcare systems can employ it effectively and whether providers will be open to using it as a tool for improving their communication skills.”