Feasibility of a Voice-Enabled Medical Diary App (SpeakHealth) for Caregivers of Children With Special Health Care Needs and Health Care Providers: Mixed Methods Study

Vanderbilt Electronic Health Record Voice Assistant Supports Clinicians

BACKGROUND

 Electronic health records (EHRs) present navigation challenges due to time-consuming searches across segmented data. Voice assistants can improve clinical workflows by allowing natural language queries and contextually aware navigation of the EHR.

OBJECTIVES

 To develop a voice-mediated EHR assistant and interview providers to inform its future refinement.

METHODS

 The Vanderbilt EHR Voice Assistant (VEVA) was developed as a responsive web application and designed to accept voice inputs and execute the appropriate EHR commands. Fourteen providers from Vanderbilt Medical Center were recruited to participate in interactions with VEVA and to share their experience with the technology. The purpose was to evaluate VEVA's overall usability, gather qualitative feedback, and detail suggestions for enhancing its performance.

RESULTS

 VEVA's mean system usability scale score was 81 based on the 14 providers' evaluations, which was above the standard 50th percentile score of 68. For all five summaries evaluated (overview summary, A1C results, blood pressure, weight, and health maintenance), most providers offered a positive review of VEVA. Several providers suggested modifications to make the technology more useful in their practice, ranging from summarizing current medications to changing VEVA's speech rate. Eight of the providers (64%) reported they would be willing to use VEVA in its current form.

CONCLUSION

 Our EHR voice assistant technology was deemed usable by most providers. With further improvements, voice assistant tools such as VEVA have the potential to improve workflows and serve as a useful adjunct tool in health care.

Improving medication adherence monitoring and clinical outcomes through mHealth: A randomized controlled trial protocol in pediatric stem cell transplant

Medication non-adherence rates in children range between 50% and 80% in the United States. Due to multifaceted outpatient routines, children receiving hematopoietic stem cell transplant (HCT) are at especially high risk of non-adherence, which can be life-threatening. Although digital health interventions have been effective in improving non-adherence in many pediatric conditions, limited research has examined their benefits among families of children receiving HCT. To address this gap, we created the BMT4me© mobile health app, an innovative intervention serving as a "virtual assistant" to send medication-taking reminders for caregivers and to track, in real-time, the child's medication taking, barriers to missed doses, symptoms or side effects, and other notes regarding their child's treatment. In this randomized controlled trial, caregivers will be randomized to either the control (standard of care) group or the intervention (BMT4me© app) group at initial discharge post-HCT. Both groups will receive an electronic adherence monitoring device (i.e., medication event monitoring system "MEMS" cap, Medy Remote Patient Management "MedyRPM" medication adherence box) to store their child's immunosuppressant medication. Caregivers who agree to participate will be asked to complete enrollment, weekly, and monthly parent-proxy measures of their child's medication adherence until the child reaches Day 100 or complete taper from immunosuppression. Caregivers will also participate in a 15 to 30-minute exit interview at the conclusion of the study. Descriptive statistics and correlations will be used to assess phone activity and use behavior over time. Independent samples t-tests will examine the efficacy of the intervention to improve adherence monitoring and reduce readmission rates. The primary expected outcome of this study is that the BMT4me© app will improve the real-time monitoring and medication adherence in children receiving hematopoietic stem cell transplant following discharge, thus improving clinical outcomes.

"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.

Caregiver Expectations for Interfacing with Voice Assistants to Support Complex Home Care: Mixed-Methods Study (Preprint)

Background

Providing care in home environments is complex, and often the pressure is on caregivers to document information and ensure care continuity. Digital information management and communication technologies may support care coordination among caregivers. However, they have yet to be adopted in this context, partly because of issues with supporting long-term disease progression and caregiver anxiety. Voice assistant (VA) technology is a promising method for interfacing with digital health information that may aid in multiple aspects of being a caregiver, thereby influencing adoption. Understanding the expectations for VAs to support caregivers is fundamental to inform the practical development of this technology.

Objective

This study explored caregivers’ perspectives on using VA technology to support caregiving and inform the design of future digital technologies in complex home care.

Methods

This study was part of a larger study of caregivers across North America on the design of digital health technologies to support health communication and information management in complex home care. Caregivers included parents, guardians, and hired caregivers such as personal support workers and home care nurses. Video interviews were conducted with caregivers to capture their mental models on the potential application of VAs in complex home care and were theoretically analyzed using the technology acceptance model. Interviews were followed up with Likert-scale questions exploring perspectives on other VA applications beyond participants’ initial perceptions.

Results

Data were collected from 22 caregivers, and 3 themes were identified: caregivers’ perceived usefulness of VAs in supporting documentation, care coordination, and person-centered care; caregivers’ perceived ease of use in navigating information efficiently (they also had usability concerns with this interaction method); and caregivers’ concerns, excitement, expected costs, and previous experience with VAs that influenced their attitudes toward use. From the Likert-scale questions, most participants (21/22, 95%) agreed that VAs should support prompted information recording and retrieval, and all participants (22/22, 100%) agreed that they should provide reminders. They also agreed that VAs should support them in an emergency (18/22, 82%)—but only for calling emergency services—and guide caregivers through tasks (21/22, 95%). However, participants were less agreeable on VAs expressing a personality (14/22, 64%)—concerned they would manipulate caregivers’ perceptions—and listening ambiently to remind caregivers about their documentation (16/22, 73%). They were much less agreeable about VAs providing unprompted assistance on caregiving tasks (9/22, 41%).

Conclusions

The interviews and Likert-scale results point toward the potential for VAs to support family caregivers and hired caregivers by easing their information management and health communication at home. However, beyond information interaction, the potential impact of VA personality traits on caregivers’ perceptions of the care situation and the passive collection of audio data to improve user experience through context-specific interactions are critical design considerations that should be further examined.

A natural language processing pipeline to synthesize patient-generated notes toward improving remote care and chronic disease management: a cystic fibrosis case study

Objectives

Patient-generated health data (PGHD) are important for tracking and monitoring out of clinic health events and supporting shared clinical decisions. Unstructured text as PGHD (eg, medical diary notes and transcriptions) may encapsulate rich information through narratives which can be critical to better understand a patient’s condition. We propose a natural language processing (NLP) supported data synthesis pipeline for unstructured PGHD, focusing on children with special healthcare needs (CSHCN), and demonstrate it with a case study on cystic fibrosis (CF).

Materials and Methods

The proposed unstructured data synthesis and information extraction pipeline extract a broad range of health information by combining rule-based approaches with pretrained deep-learning models. Particularly, we build upon the scispaCy biomedical model suite, leveraging its named entity recognition capabilities to identify and link clinically relevant entities to established ontologies such as Systematized Nomenclature of Medicine (SNOMED) and RXNORM. We then use scispaCy’s syntax (grammar) parsing tools to retrieve phrases associated with the entities in medication, dose, therapies, symptoms, bowel movements, and nutrition ontological categories. The pipeline is illustrated and tested with simulated CF patient notes.

Results

The proposed hybrid deep-learning rule-based approach can operate over a variety of natural language note types and allow customization for a given patient or cohort. Viable information was successfully extracted from simulated CF notes. This hybrid pipeline is robust to misspellings and varied word representations and can be tailored to accommodate the needs of a specific patient, cohort, or clinician.

Discussion

The NLP pipeline can extract predefined or ontology-based entities from free-text PGHD, aiming to facilitate remote care and improve chronic disease management. Our implementation makes use of open source models, allowing for this solution to be easily replicated and integrated in different health systems. Outside of the clinic, the use of the NLP pipeline may increase the amount of clinical data recorded by families of CSHCN and ease the process to identify health events from the notes. Similarly, care coordinators, nurses and clinicians would be able to track adherence with medications, identify symptoms, and effectively intervene to improve clinical care. Furthermore, visualization tools can be applied to digest the structured data produced by the pipeline in support of the decision-making process for a patient, caregiver, or provider.

Conclusion

Our study demonstrated that an NLP pipeline can be used to create an automated analysis and reporting mechanism for unstructured PGHD. Further studies are suggested with real-world data to assess pipeline performance and further implications.