Cognitive plausibility in voice-based AI health counselors

Abstract

Voice-based personal assistants using artificial intelligence (AI) have been widely adopted and used in home-based settings. Their success has created considerable interest for its use in healthcare applications; one area of prolific growth in AI is that of voicebased virtual counselors for mental health and well-being. However, in spite of its promise, building realistic virtual counselors to achieve higher-order maturity levels beyond task-based interactions presents considerable conceptual and pragmatic challenges. We describe one such conceptual challenge-cognitive plausibility, defined as the ability of virtual counselors to emulate the human cognitive system by simulating how a skill or function is accomplished. An important cognitive plausibility consideration for voice-based agents is its ability to engage in meaningful and seamless interactive communication. Drawing on a broad interdisciplinary research literature and based on our experiences with developing two voice-based (voice-only) prototypes that are in the early phases of testing, we articulate two conceptual considerations for their design and use-conceptualizing voice-based virtual counselors as communicative agents and establishing virtual co-presence. We discuss why these conceptual considerations are important and how it can lead to the development of voice-based counselors for real-world use.

Digital Translucence: Adapting Telemedicine Delivery Post-COVID-19

“…One of the fast growing areas, spurred by advances in artificial intelligence, is that of conversational agents. 11 Traditional conversational agents, relying on text-based interactions, play an important role helping patients with basic self-care and health maintenance tasks (e.g., medication reminders). 12 More recently, with voice-based personal devices gaining popularity (e.g., Alexa), there is considerable interest in virtual agents for delivering structured, evidence-based behavioral counseling, and wellness interventions.…”

Design and Formative Evaluation of a Voice-based Virtual Coach for Problem-Solving Treatment

“…Additionally, current technology is also not able to discern differences in emotion or other verbal cues that are easily interpreted in face-to-face human conversations [5]. With ongoing improvements in the technology, these challenges are likely to be mitigated over time, allowing for continued improvement of Lumen for optimized user experience.…”

“…First, we split longer conversations (especially in S1, where Lumen was providing overview) into multiple shorter conversations to reduce the mean length of conversations between Lumen and the participant. Such shorter lengths of (but more frequent) conversations allow more interactive turns and have been shown to improve the common ground and engagement between conversational partners [5, 25-28]. Second, we developed functionality that allowed participants to repeat, pause and resume conversations.…”

“…Lumen is a voice-only virtual coach that delivers an evidence-based, 8-session PST program for patients with mild-to-moderate depression and/or anxiety. Lumen’s design was based on two overarching principles: (a) providing cognitively plausible conversations, i.e., aligning Lumen’s conversations with the cognitive processes of human communicative interactions [5], and (b) alignment with the principles of evidence-based PST. This PST program was previously tested and delivered with a human coach [17]; Lumen incorporates essential components of that treatment protocol for coaching and monitors progress using surveys and ecological momentary assessments (EMAs).…”

“…Broad adoption of such platforms lends support for their potential utility in healthcare-related applications such as behavioral counseling to promote healthy lifestyle habits and emotional well-being [3, 4]. However, current healthcare-related applications of voice assistants are generally rudimentary and few have been developed for delivering evidence-based therapies or have been subjected to careful evaluation (e.g., to inform development, or for their effect on clinical or behavioral outcomes) [5]. Towards this end, we developed and evaluated, Lumen™, an end-to- voice-only virtual coach that delivers evidence-based, problem-solving treatment (PST) for patients with mild-to-moderate symptoms of depression and/or anxiety.…”