Background

Clinical application of voice technology (VT) provides novel opportunities in the field of telehealth. However, patients’ readiness for this solution have not been investigated in patients with cardiovascular diseases (CVD).

Objectives

To evaluate anticipated patients’ experiences regarding telemedicine including voice conversational agents combined with provider-driven support delivered by phone.

Methods

A cross-sectional study enrolled patients with chronic CVD who were surveyed using a validated investigator-designed questionnaire combining 19 questions (demographic data, medical history, preferences to use telehealth services). Prior to the survey, respondents were educated on the telemedicine services presented in the questionnaire being assisted by a medical doctor. At the same time, responses were collected and analyzed, followed by multivariate logistic regression to identify predictors of willingness to use VT.

Result

In total, 249 patients (mean age 65.3 ± 13.8 years, 158 males [63.5%]) completed the questionnaire, which showed good repeatability in the validation procedure. Among the study population, 209 people (83.9%) reported high readiness for receiving services allowing for remote contact with a cardiologist and telemonitoring of vital signs (70.7% and 67.5% of individuals, respectively). The voice conversational agents combined with provider-driven support delivered by phone showed to be highly anticipated by CVD patients, among whom the readiness to use was statistically higher in people with previous difficulties accessing healthcare (OR=2.92) and was most frequent in city dwellers as well as individuals reporting higher education level. Age and sex of respondents did not impact the intention to use VT (p=0.2 and p=0.5, respectively).
Conclusion: Patients with cardiovascular diseases, including younger and older population, declare high readiness for voice technology.

Description

The cutting-edge development in the field of AI and natural language understanding brought voice assistants into the market, which enable verbal communication between patients and voice-driven chatbots.

Clinical-grade medical software deployed on widely used smartphones and smart speakers (ie, Amazon Echo and Google Home) provides a scalable framework for acute care triage and chronic disease management. Recently, Mayo Clinic (Rochester, Minnesota, United States) has implemented an Amazon Alexa-based tool incorporating COVID-19 guidelines from the Centers for Disease Control and Prevention, United States (https://newsnetwork.mayoclinic.org/discussion/mayo-clinic-introduces-skill-for-amazons-alexa-about-covid-19/ ). The voice chatbot–driven symptom checker streamlines repetitive operational tasks associated with answering coronavirus-related questions and provides first-line screening.

 

Moreover, voice-enabled technology has been applied to support the complex medical workflow. The CardioCube voice AI medical chatbot deploying Amazon Echo was clinically validated at Cedars-Sinai Medical Center (Los Angeles, California, United States) and implemented in routine clinical practice, helping telenurses to manage patients with HF ( https://fcncare.com/). Using voice interface, users answer a set of prespecified clinical questions. Collected verbal information is automatically converted from audio to text using a speech-to-text cloud service, whereas actionable data are gathered in patients’ electronic health records in hospital or clinic databases. To optimize the workflow, a clinical decision support system integrating electronic health records automatically screens responses and red-flag values exceeding predefined thresholds and notifies healthcare providers accordingly.

Long-term home monitoring with CardioCube supports early detection of HF deterioration prompting an adequate medical decision (https://fcncare.com/). As exemplified, voice AI technology can multiply medical workforce and help to deliver remote care providing safety for healthcare professionals and patients.

Description

To prevent the spread of COVID-19 and to continue responding to healthcare needs, hospitals are rapidly adopting telehealth and other digital health tools to deliver care remotely. Intelligent conversational agents and virtual assistants, such as chatbots and voice assistants, have been utilized to augment health service capacity to screen symptoms, deliver healthcare information, and reduce exposure. In this commentary, we examined the state of voice assistants (e.g., Google Assistant, Apple Siri, Amazon Alexa) as an emerging tool for remote healthcare delivery service and discussed the readiness of the health system and technology providers to adapt voice assistants as an alternative healthcare delivery modality during a health crisis and pandemic.

Description

Engaging in positive healthy lifestyle behaviors continues to be a public health challenge, requiring innovative solutions. As the market for voice assistants (Amazon Alexa, Google Assistant, and Apple Siri) grows and people increasingly use them to assist their daily tasks, there is a pressing need to explore how voice assistant (VA) technology may be used in behavioral health interventions.

A scoping review of literature was conducted to address a PICO (Population, Intervention, Comparison, and Outcome) question: across populations, how does the use of voice assistants in behavioral health research/interventions influence healthy lifestyle behaviors versus control or comparison interventions? To inform the science, a secondary aim of this review was to explore characteristics of VAs used in behavioral health research. The review was conducted following Preferred Reporting Items for Systematic Review and Meta-Analysis guidelines with scoping review extension (PRISMA-ScR).

 

Ten studies satisfied the inclusion criteria, representing research published through February 2019. Studies spanned pediatric to elderly populations, covering a vast array of self-management and healthy lifestyle behaviors. The majority of interventions were multicomponent, involving more than one of the following behavior change techniques grouped by cluster: shaping knowledge, self-belief, repetition and substitution, feedback and monitoring, goals and planning, antecedents, natural consequences, comparison of behavior, and identification. However, most studies were in early stages of development, with limited efficacy trials. VA technology continues to evolve and support behavioral interventions using various platforms (e.g., Interactive Voice Response [IVR] systems, smartphones, and smart speakers) which are used alone or in conjunction with other platforms.

Feasibility, usability, preliminary efficacy, along with high user satisfaction of research adapted VAs, in contrast to standalone commercially available VAs, suggest a role for VAs in behavioral health intervention research.