Mitigating Patient and Consumer Safety Risks When Using Conversational Assistants for Medical Information: Exploratory Mixed Methods Experiment

Design and rationale of the mobile health intervention for rural atrial fibrillation

BACKGROUND

Atrial fibrillation (AF) is a highly morbid condition which requires long-term adherence to oral anticoagulation and may be associated with adverse quality of life and health care utilization. We developed a relational agent-an interactive smartphone-based intervention accessible regardless of digital or health literacy-to assist individuals residing in rural, Western Pennsylvania, with AF with chronic disease self-management.

METHODS

The "Mobile health intervention for rural atrial fibrillation" is a single center, parallel-arm randomized clinical trial for adults with AF funded by the National Institute of Health's National Heart, Lung, and Blood Institute to enroll 264 participants. All participants receive a smartphone with data plan: The intervention is a 4 month relational agent coupled with the AliveCor Kardia for heart rate and rhythm monitoring provided by smartphone, and the control a pre-installed, smartphone-based application for health-related information (WebMD). The study uses remote recruitment and engagement to enroll individuals who would otherwise be unlikely to participate in clinical research due to rurality. The primary outcome of the trial is adherence to oral anticoagulation, determined by proportion of days covered, as measured at 12 months. The secondary outcomes are quality of life, both AF-specific and general, and health care utilization. The study entails a baseline visit, a 4 month intervention phase, and 8 and 12 month follow-up visits.

CONCLUSIONS

This mobile health trial tests the effectiveness of a smartphone-based relational agent to improve clinical and patient-reported outcomes in rural-dwelling individuals.

"Hey Siri, Help Me Take Care of My Child": A Feasibility Study With Caregivers of Children With Special Healthcare Needs Using Voice Interaction and Automatic Speech Recognition in Remote Care Management

Background

About 23% of households in the United States have at least one child who has special healthcare needs. As most care activities occur at home, there is often a disconnect and lack of communication between families, home care nurses, and healthcare providers. Digital health technologies may help bridge this gap.

Objective

We conducted a pre-post study with a voice-enabled medical note taking (diary) app (SpeakHealth) in a real world setting with caregivers (parents, family members) of children with special healthcare needs (CSHCN) to understand feasibility of voice interaction and automatic speech recognition (ASR) for medical note taking at home.

Methods

In total, 41 parents of CSHCN were recruited. Participants completed a pre-study survey collecting demographic details, technology and care management preferences. Out of 41, 24 participants completed the study, using the app for 2 weeks and completing an exit survey. The app facilitated caregiver note-taking using voice interaction and ASR. An exit survey was conducted to collect feedback on technology adoption and changes in technology preferences in care management. We assessed the feasibility of the app by descriptively analyzing survey responses and user data following the key focus areas of acceptability, demand, implementation and integration, adaptation and expansion. In addition, perceived effectiveness of the app was assessed by comparing perceived changes in mobile app preferences among participants. In addition, the voice data, notes, and transcriptions were descriptively analyzed for understanding the feasibility of the app.

Results

The majority of the recruited parents were 35–44 years old (22, 53.7%), part of a two-parent household (30, 73.2%), white (37, 90.2%), had more than one child (31, 75.6%), lived in Ohio (37, 90.2%), used mobile health apps, mobile note taking apps or calendar apps (28, 68.3%) and patient portal apps (22, 53.7%) to track symptoms and health events at home. Caregivers had experience with voice technology as well (32, 78%). Among those completed the post-study survey (in Likert Scale 1–5), ~80% of the caregivers agreed or strongly agreed that using the app would enhance their performance in completing tasks (perceived usefulness; mean = 3.4, SD = 0.8), the app is free of effort (perceived ease of use; mean = 3.2, SD = 0.9), and they would use the app in the future (behavioral intention; mean = 3.1, SD = 0.9). In total, 88 voice interactive patient notes were generated with the majority of the voice recordings being less than 20 s in length (66%). Most noted symptoms and conditions, medications, treatment and therapies, and patient behaviors. More than half of the caregivers reported that voice interaction with the app and using transcribed notes positively changed their preference of technology to use and methods for tracking symptoms and health events at home.

Conclusions

Our findings suggested that voice interaction and ASR use in mobile apps are feasible and effective in keeping track of symptoms and health events at home. Future work is suggested toward using integrated and intelligent systems with voice interactions with broader populations.