An Audio Personal Health Library of Clinic Visit Recordings for Patients and Their Caregivers (HealthPAL): User-Centered Design Approach.

BACKGROUND: Providing digital recordings of clinic visits to patients has emerged as a strategy to promote patient and family engagement in care. With advances in natural language processing, an opportunity exists to maximize the value of visit recordings for patients by automatically tagging key visit information (eg, medications, tests, and imaging) and linkages to trustworthy web-based resources curated in an audio-based personal health library. OBJECTIVE: This study aims to report on the user-centered development of HealthPAL, an audio personal health library. METHODS: Our user-centered design and usability evaluation approach incorporated iterative rounds of video-recorded sessions from 2016 to 2019. We recruited participants from a range of community settings to represent older patient and caregiver perspectives. In the first round, we used paper prototypes and focused on feature envisionment. We moved to low-fidelity and high-fidelity versions of the HealthPAL in later rounds, which focused on functionality and use; all sessions included a debriefing interview. Participants listened to a deidentified, standardized primary care visit recording before completing a series of tasks (eg, finding where a medication was discussed in the recording). In the final round, we recorded the patients' primary care clinic visits for use in the session. Findings from each round informed the agile software development process. Task completion and critical incidents were recorded in each round, and the System Usability Scale was completed by participants using the digital prototype in later rounds. RESULTS: We completed 5 rounds of usability sessions with 40 participants, of whom 25 (63%) were women with a median age of 68 years (range 23-89). Feedback from sessions resulted in color-coding and highlighting of information tags, a more prominent play button, clearer structure to move between one's own recordings and others' recordings, the ability to filter recording content by the topic discussed and descriptions, 10-second forward and rewind controls, and a help link and search bar. Perceived usability increased over the rounds, with a median System Usability Scale of 78.2 (range 20-100) in the final round. Participants were overwhelmingly positive about the concept of accessing a curated audio recording of a clinic visit. Some participants reported concerns about privacy and the computer-based skills necessary to access recordings. CONCLUSIONS: To our knowledge, HealthPAL is the first patient-centered app designed to allow patients and their caregivers to access easy-to-navigate recordings of clinic visits, with key concepts tagged and hyperlinks to further information provided. The HealthPAL user interface has been rigorously co-designed with older adult patients and their caregivers and is now ready for further field testing. The successful development and use of HealthPAL may help improve the ability of patients to manage their own care, especially older adult patients who have to navigate complex treatment plans.

Natural language processing for automated annotation of medication mentions in primary care visit conversations.

OBJECTIVES: The objective of this study is to build and evaluate a natural language processing approach to identify medication mentions in primary care visit conversations between patients and physicians. MATERIALS AND METHODS: Eight clinicians contributed to a data set of 85 clinic visit transcripts, and 10 transcripts were randomly selected from this data set as a development set. Our approach utilizes Apache cTAKES and Unified Medical Language System controlled vocabulary to generate a list of medication candidates in the transcribed text and then performs multiple customized filters to exclude common false positives from this list while including some additional common mentions of the supplements and immunizations. RESULTS: Sixty-five transcripts with 1121 medication mentions were randomly selected as an evaluation set. Our proposed method achieved an F-score of 85.0% for identifying the medication mentions in the test set, significantly outperforming existing medication information extraction systems for medical records with F-scores ranging from 42.9% to 68.9% on the same test set. DISCUSSION: Our medication information extraction approach for primary care visit conversations showed promising results, extracting about 27% more medication mentions from our evaluation set while eliminating many false positives in comparison to existing baseline systems. We made our approach publicly available on the web as an open-source software. CONCLUSION: Integration of our annotation system with clinical recording applications has the potential to improve patients' understanding and recall of key information from their clinic visits, and, in turn, to positively impact health outcomes.

Algorithm-Driven Substance Use Disorder Treatment for Inner-City Clients With Serious Mental Illness and Multiple Impairments.

ABSTRACT: Mental health clients with serious mental illness in urban settings experience multiple chronic stresses related to poverty, unemployment, discrimination, homelessness, incarceration, hospitalization, posttraumatic stress disorder, pain syndromes, traumatic brain injury, and other problems. Substance use disorder exacerbates these difficulties. This study examined the efficacy of algorithm-driven substance use disorder treatments for 305 inner-city mental health clients with multiple challenges. Researchers assessed substance use quarterly using a combination of standardized self-reports and case manager ratings. Of the 305 multiply impaired clients who began treatment, 200 (66%) completed 2 years of treatment. One fourth (n = 53) of the completers were responders who developed abstinence and improved community function; one half (n = 97) were partial responders, who reduced substance use but did not become abstinent; and one fourth (n = 50) were nonresponders. Evidence-based interventions for substance use disorder can be effective for multiply impaired, inner-city clients, but numerous complications may hinder recovery.

A multi-sensory code for emotional arousal.

People express emotion using their voice, face and movement, as well as through abstract forms as in art, architecture and music. The structure of these expressions often seems intuitively linked to its meaning: romantic poetry is written in flowery curlicues, while the logos of death metal bands use spiky script. Here, we show that these associations are universally understood because they are signalled using a multi-sensory code for emotional arousal. Specifically, variation in the central tendency of the frequency spectrum of a stimulus-its spectral centroid-is used by signal senders to express emotional arousal, and by signal receivers to make emotional arousal judgements. We show that this code is used across sounds, shapes, speech and human body movements, providing a strong multi-sensory signal that can be used to efficiently estimate an agent's level of emotional arousal.

Sharing Annotated Audio Recordings of Clinic Visits With Patients-Development of the Open Recording Automated Logging System (ORALS): Study Protocol.

BACKGROUND: Providing patients with recordings of their clinic visits enhances patient and family engagement, yet few organizations routinely offer recordings. Challenges exist for organizations and patients, including data safety and navigating lengthy recordings. A secure system that allows patients to easily navigate recordings may be a solution. OBJECTIVE: The aim of this project is to develop and test an interoperable system to facilitate routine recording, the Open Recording Automated Logging System (ORALS), with the aim of increasing patient and family engagement. ORALS will consist of (1) technically proficient software using automated machine learning technology to enable accurate and automatic tagging of in-clinic audio recordings (tagging involves identifying elements of the clinic visit most important to patients [eg, treatment plan] on the recording) and (2) a secure, easy-to-use Web interface enabling the upload and accurate linkage of recordings to patients, which can be accessed at home. METHODS: We will use a mixed methods approach to develop and formatively test ORALS in 4 iterative stages: case study of pioneer clinics where recordings are currently offered to patients, ORALS design and user experience testing, ORALS software and user interface development, and rapid cycle testing of ORALS in a primary care clinic, assessing impact on patient and family engagement. Dartmouth's Informatics Collaboratory for Design, Development and Dissemination team, patients, patient partners, caregivers, and clinicians will assist in developing ORALS. RESULTS: We will implement a publication plan that includes a final project report and articles for peer-reviewed journals. In addition to this work, we will regularly report on our progress using popular relevant Tweet chats and online using our website, www.openrecordings.org. We will disseminate our work at relevant conferences (eg, Academy Health, Health Datapalooza, and the Institute for Healthcare Improvement Quality Forums). Finally, Iora Health, a US-wide network of primary care practices (www.iorahealth.com), has indicated a willingness to implement ORALS on a larger scale upon completion of this development project. CONCLUSIONS: Upon the completion of this project we will have developed a novel recording system that will be ready for large-scale testing. Our long-term goal is for ORALS to seamlessly fit into a clinic's and patient's daily routine, increasing levels of patient engagement and transparency of care.

Use of Software for Tablet Computers to Promote Engagement With Supported Employment: Results From an RCT.

OBJECTIVE: Information technology is opening up new ways to engage people who may benefit from psychiatric services. This study examined an intervention to promote engagement in supported employment for use with a tablet computer. METHODS: In a randomized controlled trial, 45 clients at an urban community mental health agency received a software application for use with a computer tablet and a brochure to promote engagement with supported employment services (N=22) or only the brochure (N=23). Engagement was defined as requesting and attending an in-person meeting with an employment specialist within 30 days postintervention. RESULTS: Engagement was reported for 11 (50%) participants who received the tablet-based application and one participant (4%) who received only the brochure (odds ratio=22.95, 95% confidence interval=2.51-193.38). CONCLUSIONS: Mobile computer-based engagement interventions can promote initial contact between clients and employment specialists.

Best practices: A national mental health learning collaborative on supported employment.

This column describes a best practice for dissemination and implementation used by the Johnson & Johnson-Dartmouth Program: a national learning collaborative among community mental health programs on supported employment. In this two-tiered learning collaborative, researchers meet regularly with mental health and vocational rehabilitation leaders in 12 states and the District of Columbia, and state leaders oversee more than 130 individual programs in their respective states. Participants share educational programs, implementation and intervention strategies, practice experiences, outcome data, and research projects. The national learning collaborative facilitates implementation, dissemination, standardization, and sustainability of supported employment.

Comprehensive electronic decision support systems.

This Open Forum describes a vision of comprehensive electronic decision support systems that could provide information and supports to both clients and clinicians in order to facilitate shared decision making and encourage collaborative management of illness and wellness. The authors argue that these systems have the potential to improve mental health care by enhancing and connecting the three elements of evidence-based medicine: client preferences, research evidence, and clinician skills.

Developing web-based online support tools: the Dartmouth decision support software.

TOPIC: This article discusses the development of Web-based online decision support tools intended for researchers examining the issue of shared decision making for the population of individuals with serious mental illnesses. PURPOSE: The authors describe the background and use of decision support tools to facilitate shared decision-making between individuals diagnosed with a psychiatric condition and clinicians and describes a novel software platform that allows researchers and other system designers to build decision support systems. CONCLUSIONS: In supporting ongoing research efforts, an online decision support tool appears to be useful for individuals facing preference-sensitive decisions and an online designer tool allows for rapid deployment of these research sites to support ongoing research efforts in shared decision making.

The long-term impact of employment on mental health service use and costs for persons with severe mental illness.

OBJECTIVE: Stable employment promotes recovery for persons with severe mental illness by enhancing income and quality of life, but its impact on mental health costs has been unclear. This study examined service cost over ten years among participants in a co-occurring disorders study. METHODS: Latent-class growth analysis of competitive employment identified trajectory groups. The authors calculated annual costs of outpatient services and institutional stays for 187 participants and examined group differences in ten-year utilization and cost. RESULTS: A steady-work group (N=51) included individuals whose work hours increased rapidly and then stabilized to average 5,060 hours per person over ten years. A late-work group (N=57) and a no-work group (N=79) did not differ significantly in utilization or cost outcomes, so they were combined into a minimum-work group (N=136). More education, a bipolar disorder diagnosis (versus schizophrenia or schizoaffective disorder), work in the past year, and lower scores on the expanded Brief Psychiatric Rating Scale predicted membership in the steady-work group. These variables were controlled for in the outcomes analysis. Use of outpatient services for the steady-work group declined at a significantly greater rate than it did for the minimum-work group, while institutional (hospital, jail, or prison) stays declined for both groups without a significant difference. The average cost per participant for outpatient services and institutional stays for the minimum-work group exceeded that of the steady-work group by $166,350 over ten years. CONCLUSIONS: Highly significant reductions in service use were associated with steady employment. Given supported employment's well-established contributions to recovery, evidence of long-term reductions in the cost of mental health services should lead policy makers and insurers to promote wider implementation.