Using artificial intelligence to analyse and teach communication in healthcare

Abstract

Communication is a core component of effective healthcare that impacts many patient and doctor outcomes, yet is complex and challenging to both analyse and teach. Human-based coding and audit systems are time-intensive and costly; thus, there is considerable interest in the application of artificial intelligence to this topic, through machine learning using both supervised and unsupervised learning algorithms. In this article we introduce health communication, its importance for patient and health professional outcomes, and the need for rigorous empirical data to support this field. We then discuss historical interaction coding systems and recent developments in applying artificial intelligence (AI) to automate such coding in the health setting. Finally, we discuss available evidence for the reliability and validity of AI coding, application of AI in training and audit of communication, as well as limitations and future directions in this field. In summary, recent advances in machine learning have allowed accurate textual transcription, and analysis of prosody, pauses, energy, intonation, emotion and communication style. Studies have established moderate to good reliability of machine learning algorithms, comparable with human coding (or better), and have identified some expected and unexpected associations between communication variables and patient satisfaction. Finally, application of artificial intelligence to communication skills training has been attempted, to provide audit and feedback, and through the use of avatars. This looks promising to provide confidential and easily accessible training, but may be best used as an adjunct to human-based training.

Personalized Health Care and Public Health in the Digital Age

“…Future devices need to demonstrate robust services in a live, potentially noisy environment (63,64). They also need to incorporate user feedback, such as emotions and verbal inputs, to improve personalized medical judgements (65)(66)(67)(68)(69)(70).…”

“It’s Always Been a Second Class Cancer”: An Exploration of the Experiences and Journeys of Bereaved Family Carers of People with Sarcoma

“…Communication was key in the family member’s transition to palliative care. The need for sensitive and effective communication emerges consistently and frequently across a number of areas in oncology, despite many years of work developing and trialling communication skills training for oncology health professionals [ 27 , 28 ]. A recent study by O’Connor et al [ 29 ] found that patients in hospitals were generally comfortable talking about end-of-life preferences in a goals of care discussion but only if the discussions are conducted sensitively and in a patient-centred way.…”

Machine learning to extract communication and history‐taking skills in OSCE transcripts

“…and Hoque, proposed using machine learning (ML) to improve evaluation of communication skills. 5,6 Two recent reviews summarise the situation. An integrated review in medical education identified 37 articles but most of these analysed procedural skills (eg, for surgery) and only two analysed language.…”

“…To address shortcomings, bias and costs, Ryan et al and Butow and Hoque, proposed using machine learning (ML) to improve evaluation of communication skills 5,6 . Two recent reviews summarise the situation.…”