Designing Effective Chatbots for Better Clinical Outcomes
Event Type
Oral Presentations
TimeWednesday, April 1411:00am - 11:20am EDT
LocationDigital Health
DescriptionIn a distressed healthcare system facing skyrocketing costs, widespread provider-burnout, and disincentives to meaningful change, is it possible to deliver better clinical outcomes at a lower cost?

This session will examine the use of AI chatbots in healthcare to: provide better customer service at a reduced cost; accelerate patient access to specialized care; improve the accuracy of diagnoses; keep patients proactively engaged; reduce stress on clinicians; and humanize patient-reported outcomes for measuring perceived value and treatment progress over time.

What makes chatbots so uniquely capable to solve these problems? The answer lies in the conversational interface, which is a universally understood medium for human-to-human and human-to-machine communication. Conversational interfaces facilitate interaction via natural language, such as the written word and voice. Because they’re based on natural languages, conversational agents reduce the cognitive load for patients attempting to access and utilize healthcare services and hold enormous potential to improve clinical outcomes.

With support for text, voice, image and rich interaction patterns, conversational interfaces are multimodal and provide patients the choice of entry point for their care. For example, patients may initiate care through a web-deployed chatbot but then report symptoms via an app on their phone. Moreover, the multimodality of conversational interfaces opens up the possibility for altogether re-imagining the patient experience in healthcare.

Attendees of this session need not have any previous knowledge or experience with chatbots or conversational interfaces. The speaker will describe the general architecture of conversational agents and will provide a brief history of the evolution of the modern chat user interface metaphor from its invention in the 1990s to today.