The power to seek out clear, related, and personalised well being info is a cornerstone of empowerment for medical sufferers. But, navigating the world of on-line well being info is usually a complicated, overwhelming, and impersonal expertise. We’re met with a flood of generic info that doesn’t account for our distinctive context, and it may be tough to know what particulars are related.
Giant language fashions (LLMs) have the potential to make this info extra accessible and tailor-made. Nevertheless, many AI instruments right this moment act as passive “question-answerers” — they supply a single, complete reply to an preliminary question. However this is not how an professional, like a health care provider, helps somebody navigate a posh matter. A well being skilled would not simply present a lecture; they ask clarifying questions to grasp the total image, uncover an individual’s targets, and information them via the knowledge maze. Although this context-seeking is crucial, it is a vital design problem for AI.
In “In direction of Higher Well being Conversations: The Advantages of Context-Looking for”, we describe how we designed and examined our “Wayfinding AI”, an early-stage analysis prototype, based mostly on Gemini, that explores a brand new method. Our elementary thesis is that by proactively asking clarifying questions, an AI agent can higher uncover a consumer’s wants, information them in articulating their issues, and supply extra useful, tailor-made info. In a sequence of 4 mixed-method consumer expertise research with a complete of 163 contributors, we examined how folks work together with AI for his or her well being questions, and we iteratively designed an agent that customers discovered to be considerably extra useful, related, and tailor-made to their wants than a baseline AI agent.
