Validation of a Virtual Assistant for Improving Medication Adherence in Patients with Comorbid Type 2 Diabetes Mellitus and Depressive Disorder

Evaluating the Potential and Pitfalls of AI-Powered Conversational Agents as Humanlike Virtual Health Carers in the Remote Management of Noncommunicable Diseases: Scoping Review

BACKGROUND

The rising prevalence of noncommunicable diseases (NCDs) worldwide and the high recent mortality rates (74.4%) associated with them, especially in low- and middle-income countries, is causing a substantial global burden of disease, necessitating innovative and sustainable long-term care solutions.

OBJECTIVE

This scoping review aims to investigate the impact of artificial intelligence (AI)-based conversational agents (CAs)-including chatbots, voicebots, and anthropomorphic digital avatars-as human-like health caregivers in the remote management of NCDs as well as identify critical areas for future research and provide insights into how these technologies might be used effectively in health care to personalize NCD management strategies.

METHODS

A broad literature search was conducted in July 2023 in 6 electronic databases-Ovid MEDLINE, Embase, PsycINFO, PubMed, CINAHL, and Web of Science-using the search terms "conversational agents," "artificial intelligence," and "noncommunicable diseases," including their associated synonyms. We also manually searched gray literature using sources such as ProQuest Central, ResearchGate, ACM Digital Library, and Google Scholar. We included empirical studies published in English from January 2010 to July 2023 focusing solely on health care-oriented applications of CAs used for remote management of NCDs. The narrative synthesis approach was used to collate and summarize the relevant information extracted from the included studies.

RESULTS

The literature search yielded a total of 43 studies that matched the inclusion criteria. Our review unveiled four significant findings: (1) higher user acceptance and compliance with anthropomorphic and avatar-based CAs for remote care; (2) an existing gap in the development of personalized, empathetic, and contextually aware CAs for effective emotional and social interaction with users, along with limited consideration of ethical concerns such as data privacy and patient safety; (3) inadequate evidence of the efficacy of CAs in NCD self-management despite a moderate to high level of optimism among health care professionals regarding CAs' potential in remote health care; and (4) CAs primarily being used for supporting nonpharmacological interventions such as behavioral or lifestyle modifications and patient education for the self-management of NCDs.

CONCLUSIONS

This review makes a unique contribution to the field by not only providing a quantifiable impact analysis but also identifying the areas requiring imminent scholarly attention for the ethical, empathetic, and efficacious implementation of AI in NCD care. This serves as an academic cornerstone for future research in AI-assisted health care for NCD management.

TRIAL REGISTRATION

Open Science Framework; https://doi.org/10.17605/OSF.IO/GU5PX.

Service innovations for people with multiple long-term conditions: reflections of a rapid evaluation team

Background

People living with multiple long-term conditions represent a significant concern for National Health Service policy and practice, and their care is a major theme in the 2019 National Health Service Long Term Plan. The Birmingham RAND and Cambridge Rapid Evaluation Centre team has undertaken a thematic synthesis of the 10 evaluations it has conducted from 2018 to 2023, exploring the needs, priorities and implications for people with multiple long-term conditions.

Objectives

The aims for this overarching study were to: (1) build a body of learning about service innovations in primary and community settings for people of all ages with multiple long-term conditions, focused on questions that matter most to people with multimorbidity; and (2) develop methodological insights about how rapid evaluation can be used to inform the scoping, testing and implementation of service innovations for people with multiple long-term conditions.

Design

The focus on multiple long-term conditions came from a Birmingham RAND and Cambridge Rapid Evaluation Centre prioritisation process undertaken in 2018 using James Lind Alliance methods. Cross-analysis of the findings from the 10 individual rapid evaluations was supplemented by (1) building aspects of multimorbidity into the design of later evaluations; (2) interviewing national and regional stakeholders (n=19) working in or alongside integrated care systems; (3) undertaking a rapid review of evidence on remote monitoring for people with multiple long-term conditions (19 papers included); and (4) testing overall insights with organisations representing patients and carers through a patient, public and professional engagement workshop with 10 participants plus members of the research team.

Results

While living with multiple long-term conditions is common and is the norm for people over the age of 50 using health and care services, it is not often a focus of health service provision or innovation, nor of research and evaluation activity. We discuss six themes emerging from the totality of the study: (1) our health system is mainly organised around single conditions and not multiple long-term conditions; (2) research calls and studies usually focus on single conditions and associated services; (3) building opportunities for engaged, informed individuals and carers and improved self-management; (4) the importance of measures that matter for patients and carers; (5) barriers to developing and implementing service innovations for people with multiple long-term conditions; and (6) what is needed to make patients with multiple long-term conditions a priority in healthcare planning and delivery.

Limitations

Care of people with multiple long-term conditions was not the principal focus of several of the rapid evaluations. While this was a finding in itself, it limited our learning about designing and implementing, as well as methodological approaches to evaluating, service innovations for people with multiple long-term conditions.

Conclusions

Through a thematic analysis of the portfolio of evaluations, we have deduced a set of suggested implications for how the needs of people with multiple long-term conditions can be better embedded in policy, research and practice.

Future work

Areas of uncertainty related to the care of people with multiple long-term conditions should be further explored, including developing and testing measures of patient experience of (un)co-ordinated care across settings, and interrogating the experience of health and care staff when working with people with multiple long-term conditions, to understand what works.

Funding

This award was funded by the National Institute for Health and Care Research (NIHR) Health and Social Care Delivery Research programme (NIHR award ref: NIHR134284) and is published in full in Health and Social Care Delivery Research; Vol. 12, No. 15. See the NIHR Funding and Awards website for further award information.

Depiction of conversational agents as health professionals: a scoping review

OBJECTIVE

The purpose of this scoping review was to examine the depiction of conversational agents as health professionals. We identified the professional characteristics that are used with these depictions and determined the prevalence of these characteristics among conversational agents that are used for health care.

INTRODUCTION

The depiction of conversational agents as health professionals has implications for both the users and the developers of these programs. For this reason, it is important to know more about these depictions and how they are implemented in practical settings.

INCLUSION CRITERIA

This review included scholarly literature on conversational agents that are used for health care. It focused on conversational agents designed for patients and health seekers, not health professionals or trainees. Conversational agents that address physical and/or mental health care were considered, as were programs that promote healthy behaviors.

METHODS

This review was conducted in accordance with JBI methodology for scoping reviews. The databases searched included MEDLINE (PubMed), Embase, CINAHL with Full Text (EBSCOhost), Scopus, Web of Science, ACM Guide to Computing Literature (Association for Computing Machinery Digital Library), and IEEE Xplore (IEEE). The main database search was conducted in June 2021, and an updated search was conducted in January 2022. Extracted data included characteristics of the report, basic characteristics of the conversational agent, and professional characteristics of the conversational agent. Extracted data were summarized using descriptive statistics. Results are presented in a narrative summary and accompanying tables.

RESULTS

A total of 38 health-related conversational agents were identified across 41 reports. Six of these conversational agents (15.8%) had professional characteristics. Four conversational agents (10.5%) had a professional appearance in which they displayed the clothing and accessories of health professionals and appeared in professional settings. One conversational agent (2.6%) had a professional title (Dr), and 4 conversational agents (10.5%) were described as having professional roles. Professional characteristics were more common among embodied vs disembodied conversational agents.

CONCLUSIONS

The results of this review show that the depiction of conversational agents as health professionals is not particularly common, although it does occur. More discussion is needed on the potential ethical and legal issues surrounding the depiction of conversational agents as health professionals. Future research should examine the impact of these depictions, as well as people's attitudes toward them, to better inform recommendations for practice.

Are e-Health Interventions Effective in Reducing Diabetes-Related Distress and Depression in Patients with Type 2 Diabetes? A Systematic Review with Meta-Analysis

Background: e-Health refers to any health care service delivered through the internet or related technologies, to improve quality of life. Despite the increasing use of e-health interventions to manage type 2 diabetes (T2D), there is a lack of evidence about the effectiveness on diabetes distress and depression, which are common issues in those living with T2D. Purpose: To synthesize and determine the effects of e-health interventions on diabetes distress and depression among patients with T2D. Methods: We systematically searched PubMed, Scopus, Cochrane CENTRAL, and Web of Science for randomized controlled trials (RCTs), non-RCTs and observational cohort studies for the effects of e-health interventions on diabetes distress and depression in patients with T2D up to September 14, 2022. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses 2020 recommendations were followed. The risk of bias was assessed according to the Risk-of-Bias 2 tool (RCTs), the Risk Of Bias In Non-randomised Studies-of Interventions (ROBINS-I) (non-RCTs) and the National Institute of Health tool (observational). The standardized mean difference (SMD) and its related 95% confidence intervals (CIs) were estimated with the DerSimonian-Laird method through random-effect models. A pooled raw mean difference (MD) meta-analysis was conducted for RCTs comparing the effects of e-health versus control on diabetes distress screening to display the clinical impact. Results: A total of 41 studies (24 RCTs, 14 non-RCTs, and 3 observational) involving 8,667 individuals were included. The pooled SMD for the effect of e-health versus the control group on diabetes distress was -0.14 (95% CI = -0.24 to -0.04; I2 = 23.9%; n = 10 studies), being -0.06 (95% CI = -0.15 to 0.02; I2 = 7.8%; n = 16 studies) for depression. The pooled raw MD on diabetes distress screening showed a reduction of -0.54 points (95% CI = -0.81 to -0.27; I2 = 85.1%; n = 7 studies). Conclusion: e-Health interventions are effective in diminishing diabetes distress among adults with T2D, inducing clinically meaningful reductions.

Impact of text reminders on pneumatic compression device (PCD) compliance in patients with breast cancer-related lymphedema

PURPOSE

Do cell phone text reminders impact the rate of compliance with pneumatic compression device (PCD) therapy among women with breast cancer-related lymphedema (BCRL)?

METHODS

A prospective, randomized, 2-group feasibility study conducted at 2 centers. Participants were adult females (≥18 years old) with unilateral BCRL who had the capability of receiving reminder text messages. All participants underwent PCD therapy. Participants were randomized 1:1 to control (no text messages) or test group (received text message reminders if the PCD had not been used for 2 consecutive days). The rate of compliance between treatment groups was the main outcome measure. Secondary outcome measures were changes in arm girth, quality of life (QOL), and symptom severity.

RESULTS

Twenty-nine participants were enrolled and randomized, 25 were available for follow-up at 60 days (14 test, 11 control). Overall, 52.2% (12/23) of all participants were completely compliant, an additional 43.5% (10/23) were partially compliant, and 1 patient (4.3%) was noncompliant. The test and control groups did not differ in device compliance. In the pooled population, weight, BMI, and arm girth were improved. Overall disease-specific QOL and symptom severity were improved. Regression analysis showed benefits were greater among participants with higher rates of compliance.

CONCLUSIONS

Automated text reminders did not improve compliance in patients with BCRL as compliance rates were already high in this patient population. Improvements in weight, BMI, arm girth, disease-specific quality of life, and symptom severity measures were observed regardless of the treatment assignment. Full compliance resulted in greater functional and QOL benefits.

TRIAL REGISTRATION

The study was registered at www.

CLINICALTRIALS

gov (NCT04432727) on June 16, 2020.

Decoding Applications of Artificial Intelligence in Rheumatology

Artificial intelligence (AI) is not a newcomer in medicine. It has been employed for image analysis, disease diagnosis, drug discovery, and improving overall patient care. ChatGPT (Chat Generative Pre-trained Transformer, Inc., Delaware) has renewed interest and enthusiasm in artificial intelligence. Algorithms, machine learning, deep learning, and data analysis are some of the complex terminologies often encountered when health professionals try to learn AI. In this article, we try to review the practical applications of artificial intelligence in vernacular language in the fields of medicine and rheumatology in particular. From the standpoint of the everyday physician, we have endeavored to encapsulate the influence of AI on the cutting edge of medical practice and the potential revolutionary shift in the realm of rheumatology.

When Virtual Assistants Meet Teledermatology: Validation of a Virtual Assistant to Improve the Quality of Life of Psoriatic Patients

Teledermatology has given dermatologists a tool to track patients' responses to therapy using images. Virtual assistants, the programs that interact with users through text or voice messages, could be used in teledermatology to enhance the interaction of the tool with the patients and healthcare professionals and the overall impact of the medication and quality of life of patients. As such, this work aimed to investigate the effectiveness of using a virtual assistant for teledermatology and its impact on the quality of life. We conducted surveys with the participants and measured the usability of the system with the System Usability Scale (SUS). A total of 34 participants (30 patients diagnosed with moderate-severe psoriasis and 4 healthcare professionals) were included in the study. The measurement of the improvement of quality of life was done by analyzing Psoriasis Quality of Life (PSOLIFE) and Dermatology Life Quality Index (DLQI) questionnaires. The results showed that, on average, the quality of life improved (from 63.8 to 64.8 for PSOLIFE (with a p-value of 0.66 and an effect size of 0.06) and 4.4 to 2.8 for DLQI (with a p-value of 0.04 and an effect size of 0.31)). Patients also used the virtual assistant to do 52 medical consultations. Moreover, the usability is above average, with a SUS score of 70.1. As supported by MMAS-8 results, adherence also improved slightly. Our work demonstrates the improvement of the quality of life with the use of a virtual assistant in teledermatology, which could be attributed to the sense of security or peace of mind the patients get as they can contact their dermatologists directly within the virtual assistant-integrated system.

Electronic health strategies to improve medication adherence in patients with cardiometabolic disease: current status and future directions

PURPOSE OF REVIEW

Enabled by widespread technological advancements, electronic health (eHealth) strategies have expanded rapidly over the last decade, presenting opportunities to support self-management including medication adherence for cardiometabolic disease control. eHealth can minimize access barriers to medications, enable timely assessment and shared decision-making, and provide medication reminders and health data feedback. This review summarizes current evidence for effectiveness of eHealth strategies for improving medication adherence in patients with hypertension, type 2 diabetes, and/or hyperlipidemia, and identifies priorities for future research.

RECENT FINDINGS

Current research supports the effectiveness of eHealth strategies to improve medication adherence and clinical outcomes for cardiometabolic disease. Although patient acceptability of eHealth strategies is generally high, engagement may decline over time. In addition, differences in effectiveness across intervention characteristics and sociodemographic groups are understudied, limiting generalizability and tailoring of interventions to local health system resources, culture, and patient needs or preferences.

SUMMARY

eHealth is a promising tool for addressing low medication adherence. Further work incorporating rigorous evaluation, assessment of patient engagement over time and effectiveness of intervention characteristics and components, and a health equity lens addressing eHealth use in vulnerable groups will increase understanding of the full potential of eHealth for improving medication adherence in diverse patients with cardiometabolic disease.