Development and validation of a virtual agent to screen tobacco and alcohol use disorders

Roles, Users, Benefits, and Limitations of Chatbots in Health Care: Rapid Review

BACKGROUND

Chatbots, or conversational agents, have emerged as significant tools in health care, driven by advancements in artificial intelligence and digital technology. These programs are designed to simulate human conversations, addressing various health care needs. However, no comprehensive synthesis of health care chatbots' roles, users, benefits, and limitations is available to inform future research and application in the field.

OBJECTIVE

This review aims to describe health care chatbots' characteristics, focusing on their diverse roles in the health care pathway, user groups, benefits, and limitations.

METHODS

A rapid review of published literature from 2017 to 2023 was performed with a search strategy developed in collaboration with a health sciences librarian and implemented in the MEDLINE and Embase databases. Primary research studies reporting on chatbot roles or benefits in health care were included. Two reviewers dual-screened the search results. Extracted data on chatbot roles, users, benefits, and limitations were subjected to content analysis.

RESULTS

The review categorized chatbot roles into 2 themes: delivery of remote health services, including patient support, care management, education, skills building, and health behavior promotion, and provision of administrative assistance to health care providers. User groups spanned across patients with chronic conditions as well as patients with cancer; individuals focused on lifestyle improvements; and various demographic groups such as women, families, and older adults. Professionals and students in health care also emerged as significant users, alongside groups seeking mental health support, behavioral change, and educational enhancement. The benefits of health care chatbots were also classified into 2 themes: improvement of health care quality and efficiency and cost-effectiveness in health care delivery. The identified limitations encompassed ethical challenges, medicolegal and safety concerns, technical difficulties, user experience issues, and societal and economic impacts.

CONCLUSIONS

Health care chatbots offer a wide spectrum of applications, potentially impacting various aspects of health care. While they are promising tools for improving health care efficiency and quality, their integration into the health care system must be approached with consideration of their limitations to ensure optimal, safe, and equitable use.

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.

Dialogue agents for artificial intelligence-based conversational systems for cognitively disabled: a systematic review

PURPOSE

We present a systematic literature review of dialogue agents for Artificial Intelligence (AI) and agent-based conversational systems dealing with cognitive disability of aged and impaired people including dementia and Parkinson's disease. We analyze current applications, gaps, and challenges in the existing research body, and provide guidelines and recommendations for their future development and use.

MATERIALS AND METHODS

We perform this study by applying Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) criteria. We performed a systematic search using relevant databases (ACM Digital Library, Google Scholar, IEEE Xplore, PubMed, and Scopus).

RESULTS

This study identified 468 articles on the use of conversational agents in healthcare. We finally selected 124 articles based on their objectives and content as directly related to our main topic.

CONCLUSION

We identified the main challenges in the field and analyzed the typical examples of the application of conversational agents in the healthcare domain, the desired characteristics of conversational agents, and chatbot support for aged people and people with cognitive disabilities. Our results contribute to a discussion on conversational health agents and emphasize current knowledge gaps and challenges for future research.IMPLICATIONS FOR REHABILITATIONA systematic literature review of dialogue agents for artificial intelligence and agent-based conversational systems dealing with cognitive disability of aged and impaired people.Main challenges and desired characteristics of the conversational agents, and chatbot support for aged people and people with cognitive disability.Current knowledge gaps and challenges for remote healthcare and rehabilitation.Guidelines and recommendations for future development and use of conversational systems.

Evaluation framework for conversational agents with artificial intelligence in health interventions: a systematic scoping review

OBJECTIVES

Conversational agents (CAs) with emerging artificial intelligence present new opportunities to assist in health interventions but are difficult to evaluate, deterring their applications in the real world. We aimed to synthesize existing evidence and knowledge and outline an evaluation framework for CA interventions.

MATERIALS AND METHODS

We conducted a systematic scoping review to investigate designs and outcome measures used in the studies that evaluated CAs for health interventions. We then nested the results into an overarching digital health framework proposed by the World Health Organization (WHO).

RESULTS

The review included 81 studies evaluating CAs in experimental (n = 59), observational (n = 15) trials, and other research designs (n = 7). Most studies (n = 72, 89%) were published in the past 5 years. The proposed CA-evaluation framework includes 4 evaluation stages: (1) feasibility/usability, (2) efficacy, (3) effectiveness, and (4) implementation, aligning with WHO's stepwise evaluation strategy. Across these stages, this article presents the essential evidence of different study designs (n = 8), sample sizes, and main evaluation categories (n = 7) with subcategories (n = 40). The main evaluation categories included (1) functionality, (2) safety and information quality, (3) user experience, (4) clinical and health outcomes, (5) costs and cost benefits, (6) usage, adherence, and uptake, and (7) user characteristics for implementation research. Furthermore, the framework highlighted the essential evaluation areas (potential primary outcomes) and gaps across the evaluation stages.

DISCUSSION AND CONCLUSION

This review presents a new framework with practical design details to support the evaluation of CA interventions in healthcare research.

PROTOCOL REGISTRATION

The Open Science Framework (https://osf.io/9hq2v) on March 22, 2021.

Improving counseling effectiveness with virtual counselors through nonverbal compassion involving eye contact, facial mimicry, and head-nodding

An effective way to reduce emotional distress is by sharing negative emotions with others. This is why counseling with a virtual counselor is an emerging methodology, where the sharer can consult freely anytime and anywhere without having to fear being judged. To improve counseling effectiveness, most studies so far have focused on designing verbal compassion for virtual counselors. However, recent studies showed that virtual counselors' nonverbal compassion through eye contact, facial mimicry, and head-nodding also have significant impact on the overall counseling experience. To verify this, we designed the virtual counselor's nonverbal compassion and examined its effects on counseling effectiveness (i.e., reduce the intensity of anger and improve general affect). A total of 40 participants were recruited from the university community. Participants were then randomly assigned to one of two virtual counselor conditions: a neutral virtual counselor condition without nonverbal compassion and a compassionate virtual counselor condition with nonverbal compassion (i.e., eye contact, facial mimicry, and head-nodding). Participants shared their anger-inducing episodes with the virtual counselor for an average of 16.30 min. Note that the virtual counselor was operated by the Wizard-of-Oz method without actually being technically implemented. Results showed that counseling with a compassionate virtual counselor reduced the intensity of anger significantly more than counseling with a neutral virtual counselor (F(1, 37) = 30.822, p < 0.001, ηp2 = 0.454). In addition, participants who counseled with a compassionate virtual counselor responded that they experienced higher empathy than those who counseled with a neutral virtual counselor (p < 0.001). These findings suggest that nonverbal compassion through eye contact, facial mimicry, and head-nodding of the virtual counselor makes the participants feel more empathy, which contributes to improving the counseling effectiveness by reducing the intensity of anger.

Development of a Virtual Human for Supporting Tobacco Cessation During the COVID-19 Pandemic

People who consume tobacco are at greater risk of developing severe COVID-19. Unfortunately, the COVID-19 pandemic reduced the accessibility of tobacco cessation services as a result of necessary social restrictions. Innovations were urgently needed to support tobacco cessation during the pandemic. Virtual humans are artificially intelligent computer agents with a realistic, humanlike appearance. Virtual humans could be a scalable and engaging way to deliver tobacco cessation information and support. Florence, a virtual human health worker, was developed in collaboration with the World Health Organization to remotely support people toward tobacco cessation during the COVID-19 pandemic. Florence delivers evidence-based information, assists with making quit plans, and directs people to World Health Organization-recommended cessation services in their country. In this viewpoint, we describe the process of developing Florence. The development was influenced by a formative evaluation of data from 115 early users of Florence from 49 countries. In general, Florence was positively perceived; however, changes were requested to aspects of her design and content. In addition, areas for new content were identified (eg, for nonsmoker support persons). Virtual health workers could expand the reach of evidence-based tobacco cessation information and personalized support. However, as they are a new innovation in tobacco cessation, their efficacy, feasibility, and acceptability in this application needs to be evaluated, including in diverse populations.

Stigmatization of people with addiction by health professionals: Current knowledge. A scoping review

Background

Stigma of people with substance and non-substance use disorders (SNSUD) is a long-known phenomenon. The aim of this review was to assess the stigmatization, by health professionals, of people with SNSUD, its characteristics and change over time.

Methods

A scoping review of literature reviews was conducted with systematic search of PubMed, Scopus and PsycINFO databases.

Results

From the 19 selected reviews, all focused on people with SUD (PWSUD) only and 20 % to 51 % of health professionals had negative attitudes/beliefs about SUD. Addiction training and clinical experience with PWSUD were associated with a less negative attitude. Health professionals' negative beliefs, lack of time or support were associated with less involvement in addiction care. Tobacco use disorder, SUDs other than alcohol and tobacco, relapse, psychiatric comorbidity or criminal records were associated with a more negative attitude. The influence of several variables potentially related to stigmatization was inconsistent across selected reviews. The evolution of stigmatization over time was not systematically assessed and showed mixed results.

Conclusions

The stigmatization of PWSUD has an impact on their care, and a change in some variables could reduce its importance: moral model of addiction, health professionals' negative beliefs, lack of training, time, and role support. Teaching what addiction is according to the medical chronic disease model, and developing stigma-focused training could improve caregivers' attitudes and further reduce stigma. Further studies are needed to determine whether stigma of PWSUD by health professionals has changed over time and to characterize stigma for people with non-substance use disorders.

Reimagining Healthcare: Unleashing the Power of Artificial Intelligence in Medicine

Artificial intelligence (AI) has opened new medical avenues and revolutionized diagnostic and therapeutic practices, allowing healthcare providers to overcome significant challenges associated with cost, disease management, accessibility, and treatment optimization. Prominent AI technologies such as machine learning (ML) and deep learning (DL) have immensely influenced diagnostics, patient monitoring, novel pharmaceutical discoveries, drug development, and telemedicine. Significant innovations and improvements in disease identification and early intervention have been made using AI-generated algorithms for clinical decision support systems and disease prediction models. AI has remarkably impacted clinical drug trials by amplifying research into drug efficacy, adverse events, and candidate molecular design. AI's precision and analysis regarding patients' genetic, environmental, and lifestyle factors have led to individualized treatment strategies. During the COVID-19 pandemic, AI-assisted telemedicine set a precedent for remote healthcare delivery and patient follow-up. Moreover, AI-generated applications and wearable devices have allowed ambulatory monitoring of vital signs. However, apart from being immensely transformative, AI's contribution to healthcare is subject to ethical and regulatory concerns. AI-backed data protection and algorithm transparency should be strictly adherent to ethical principles. Vigorous governance frameworks should be in place before incorporating AI in mental health interventions through AI-operated chatbots, medical education enhancements, and virtual reality-based training. The role of AI in medical decision-making has certain limitations, necessitating the importance of hands-on experience. Therefore, reaching an optimal balance between AI's capabilities and ethical considerations to ensure impartial and neutral performance in healthcare applications is crucial. This narrative review focuses on AI's impact on healthcare and the importance of ethical and balanced incorporation to make use of its full potential.

The Craving-Manager smartphone app designed to diagnose substance use/addictive disorders, and manage craving and individual predictors of relapse: a study protocol for a multicenter randomized controlled trial

Background

The rate of individuals with addiction who are currently treated are low, and this can be explained by barriers such as stigma, desire to cope alone, and difficulty to access treatment. These barriers could be overcome by mobile technologies. EMI (Ecological Momentary Intervention) is a treatment procedure characterized by the delivery of interventions (messages on smartphones) to people in their daily lives. EMI presents opportunities for treatments to be available to people during times and in situations when they are most needed. Craving is a strong predictor of relapse and a key target for addiction treatment. Studies using Ecological Momentary Assessment (EMA) method have revealed that, in daily life, person-specific cues could precipitate craving, that in turn, is associated with a higher probability to report substance use and relapse in the following hours. Assessment and management of these specific situations in daily life could help to decrease addictive use and avoid relapse. The Craving-Manager smartphone app has been designed to diagnose addictive disorders, and assess and manage craving as well as individual predictors of use/relapse. It delivers specific and individualized interventions (counseling messages) composed of evidence-based addiction treatments approaches (cognitive behavioral therapy and mindfulness). The Craving-Manager app can be used for any addiction (substance or behavior). The objective of this protocol is to evaluate the efficacy of the Craving-Manager app in decreasing use (of primary substance(s)/addictive behavior(s)) over 4 weeks, among individuals on a waiting list for outpatient addiction treatment.

Methods/design

This multicenter double-blind randomized controlled trial (RCT) will compare two parallel groups: experimental group (full interventional version of the app, 4 weeks, EMA + EMI), versus control group (restricted version of the app, 4 weeks, only EMA). Two hundred and seventy-four participants will be recruited in 6 addiction treatment centers in France.

Discussion

This RCT will provide indication on how the Craving-Manager app will reduce addictive use (e.g., better craving management, better stimulus control) in both substance and behavioral addictions. If its efficacy is confirmed, the app could offer the possibility of an easy to use and personalized intervention accessible to the greatest number of individuals with addiction.

Clinical Trial Registration

ClinicalTrials.gov: NCT04732676.

Implementation Fidelity of Chatbot Screening for Social Needs: Acceptability, Feasibility, Appropriateness

OBJECTIVES

Patient and provider-facing screening tools for social determinants of health have been explored in a variety of contexts; however, effective screening and resource referral remain challenging, and less is known about how patients perceive chatbots as potential social needs screening tools. We investigated patient perceptions of a chatbot for social needs screening using three implementation outcome measures: acceptability, feasibility, and appropriateness.

METHODS

We implemented a chatbot for social needs screening at one large public hospital emergency department (ED) and used concurrent triangulation to assess perceptions of the chatbot use for screening. A total of 350 ED visitors completed the social needs screening and rated the chatbot on implementation outcome measures, and 22 participants engaged in follow-up phone interviews.

RESULTS

The screened participants ranged in age from 18 to 90 years old and were diverse in race/ethnicity, education, and insurance status. Participants (n = 350) rated the chatbot as an acceptable, feasible, and appropriate way of screening. Through interviews (n = 22), participants explained that the chatbot was a responsive, private, easy to use, efficient, and comfortable channel to report social needs in the ED, but wanted more information on data use and more support in accessing resources.

CONCLUSION

In this study, we deployed a chatbot for social needs screening in a real-world context and found patients perceived the chatbot to be an acceptable, feasible, and appropriate modality for social needs screening. Findings suggest that chatbots are a promising modality for social needs screening and can successfully engage a large, diverse patient population in the ED. This is significant, as it suggests that chatbots could facilitate a screening process that ultimately connects patients to care for social needs, improving health and well-being for members of vulnerable patient populations.

Cross-analyzing addiction specialist and patient opinions and experiences about addictive disorder screening in primary care to identify interaction-related obstacles: a qualitative study

BACKGROUND

Promptly identifying individuals with addictive disorders reduces mortality and morbidity and improves quality of life. Although screening in primary care with the Screening, Brief Intervention and Referral Treatment strategy has been recommended since 2008, it remains underutilized. This may be due to barriers including lack of time, patient reluctance or perhaps the timing and approach for discussing addiction with their patients.

OBJECTIVE

This study aims to explore and cross-analyze patient and addiction specialist experiences and opinions about early addictive disorder screening in primary care to identify interaction-related screening obstacles.

DESIGN AND PARTICIPANTS

Qualitative study with purposive maximum variation sampling among nine addiction specialists and eight individuals with addiction disorders conducted between April 2017 and November 2019 in Val-de-Loire, France.

MAIN MEASURES

Using a grounded theory approach, verbatim data was collected from face-to-face interviews with addiction specialists and individuals with addiction disorders. These interviews explored their opinions and experiences with addiction screening in primary care. Initially, two independent investigators analyzed the coded verbatim according to the data triangulation principle. Secondly, convergences and divergences between addiction specialist and addict verbatim categories were identified, analyzed, and conceptualized.

KEY RESULTS

Four main interaction-related obstacles to early addictive disorder screening in primary care were identified and conceptualized: the new concepts of shared self-censorship and the patient's personal red line, issues not addressed during consultations, and opposition between how physicians and patients would like to approach addictive disorder screening.

CONCLUSIONS

To continue analysis of addictive disorder screening dynamics, further studies to examine the perspectives of all those involved in primary care are required. The information revealed from these studies will provide ideas to help patients and caregivers start discussing addiction and to help implement a collaborative team-based care approach.

TRIAL REGISTRATION

This study is registered with the Commission Nationale de l'Informatique et des Libertés (CNIL) under No. 2017-093.

Development and Validation of Conversational Agent to Pregnancy Safe-education

Pregnant women constantly need some information to support nutritional decisions during pregnancy, and many do not receive such assistance at all. This study aims to present a conversational agent to provide reliable information to pregnant women, focusing on nutritional education and evaluating the perception of pregnant women and health professionals about the agent. As a scientific contribution, this article developed and implemented a conversational agent in a real environment capable of generating reliable responses on the basis of a set of health documents. We proposed an intervention study with 25 women and 10 healthcare providers through a survey to measure the perceptions of these groups towards conversational agents. The results show that the intended design could ensure positive support for pregnant women, clarify certain issues for the public, and remove some knowledge barriers. The results showed no significant difference between the groups (p-value = 0.713). Depending on the perception of the pregnant group, the conversational agent model can teach new knowledge during the prenatal period (Mean = 4.56). The model presented for health professionals could already be indicated as a support tool for pregnant women (Mean = 4.7).

Chatbots for Smoking Cessation: Scoping Review

BACKGROUND

Despite significant progress in reducing tobacco use over the past 2 decades, tobacco still kills over 8 million people every year. Digital interventions, such as text messaging, have been found to help people quit smoking. Chatbots, or conversational agents, are new digital tools that mimic instantaneous human conversation and therefore could extend the effectiveness of text messaging.

OBJECTIVE

This scoping review aims to assess the extent of research in the chatbot literature for smoking cessation and provide recommendations for future research in this area.

METHODS

Relevant studies were identified through searches conducted in Embase, MEDLINE, APA PsycINFO, Google Scholar, and Scopus, as well as additional searches on JMIR, Cochrane Library, Lancet Digital Health, and Digital Medicine. Studies were considered if they were conducted with tobacco smokers, were conducted between 2000 and 2021, were available in English, and included a chatbot intervention.

RESULTS

Of 323 studies identified, 10 studies were included in the review (3 framework articles, 1 study protocol, 2 pilot studies, 2 trials, and 2 randomized controlled trials). Most studies noted some benefits related to smoking cessation and participant engagement; however, outcome measures varied considerably. The quality of the studies overall was low, with methodological issues and low follow-up rates.

CONCLUSIONS

More research is needed to make a firm conclusion about the efficacy of chatbots for smoking cessation. Researchers need to provide more in-depth descriptions of chatbot functionality, mode of delivery, and theoretical underpinnings. Consistency in language and terminology would also assist in reviews of what approaches work across the field.

Prenatal maternal alcohol exposure: Diagnosis and prevention of fetal alcohol syndrome

Fetal alcohol syndrome (FAS) is a developmental and congenital disorder characterized by neurocognitive impairment, structural defects, and growth restriction due to prenatal alcohol exposure. The estimated global prevalence of alcohol use during pregnancy is 9.8%, and the estimated prevalence of FAS in the general population is 14.6 per 10,000 people. In Korea, the estimated prevalence of alcohol use during pregnancy is 16%, and the prevalence of FAS is 18–51 per 10,000 women, which is higher than the global prevalence. Women’s alcohol consumption rates have increased, especially in women of childbearing age. This could increase the incidence of FAS, leading to higher medical expenses and burden on society. Alcohol is the single most important teratogen that causes FAS, and there is no safe trimester to drink alcohol and no known safe amount of alcohol consumption during pregnancy. Thus, physicians should assess women’s drinking patterns in detail and provide education on FAS to women by understanding its pathophysiology. Moreover, the prevention of FAS requires long-term care with a multidisciplinary approach.

Computerized Relational Agent to Deliver Alcohol Brief Intervention and Referral to Treatment in Primary Care: a Randomized Clinical Trial

BACKGROUND

Alcohol screening and brief intervention have demonstrated efficacy but limited effectiveness and implementation in real-world primary care settings.

OBJECTIVE

To evaluate the effectiveness of a computerized Relational Agent programmed to provide alcohol screening, brief intervention, and referral to treatment. We hypothesized that participants in the experimental condition would report greater reductions in their drinking and higher rates of brief intervention and referrals to specialty care compared to those in treatment as usual (TAU).

DESIGN

This was a Hybrid I implementation design and stratified RCT. Participants were randomized to TAU or Relational Agent + TAU and assessed at baseline and 3-month follow-up.

PARTICIPANTS

A total of 178 veteran participants were recruited by referral from primary care staff after a positive alcohol screen, or via letter sent do patients screening positive during recent visit.

INTERVENTION(S)

TAU involved yearly reminders to screen alcohol use and provide brief intervention and treatment referrals, as needed. The Relational Agent added an automated brief intervention, a 1-month follow-up Relational Agent visit, and referral to treatment if needed.

MAIN MEASURES

We measured average drinks per day, drinking days per week, number of brief interventions, and number of referrals over 3 months.

KEY RESULTS

Participants decreased their drinking in both study conditions, with no significant between-group differences on primary alcohol measures. However, Relational Agent + TAU participants evidenced greater improvements regarding negative alcohol-related consequences over 3 months, and were significantly more likely to receive a brief intervention and referral to specialty care.

CONCLUSIONS

The Relational Agent successfully provided brief intervention and referred many more patients to specialty care and was able to intervene with patients with less severe drinking without increasing primary care burden.

TRIAL REGISTRATION

clinicaltrials.gov , NCT02030288, https://clinicaltrials.gov/ct2/home.

Artificially intelligent chatbots in digital mental health interventions: a review

INTRODUCTION

Increasing demand for mental health services and the expanding capabilities of artificial intelligence (AI) in recent years has driven the development of digital mental health interventions (DMHIs). To date, AI-based chatbots have been integrated into DMHIs to support diagnostics and screening, symptom management and behavior change, and content delivery.

AREAS COVERED

We summarize the current landscape of DMHIs, with a focus on AI-based chatbots. Happify Health's AI chatbot, Anna, serves as a case study for discussion of potential challenges and how these might be addressed, and demonstrates the promise of chatbots as effective, usable, and adoptable within DMHIs. Finally, we discuss ways in which future research can advance the field, addressing topics including perceptions of AI, the impact of individual differences, and implications for privacy and ethics.

EXPERT OPINION

Our discussion concludes with a speculative viewpoint on the future of AI in DMHIs, including the use of chatbots, the evolution of AI, dynamic mental health systems, hyper-personalization, and human-like intervention delivery.

Security, privacy, and healthcare-related conversational agents: a scoping review

Health chatbots interview patients and collect health data. This process makes demands on data security and data privacy. To identify how and to what extent security and privacy are considered in current health chatbots. We conducted a scoping review by searching three bibliographic databases (PubMed, ACM Digital Library, IEEExplore) for papers reporting on chatbots in healthcare. We extracted which, how, and where data is stored by health chatbots and identified which external services have access to the data. Out of 1026 retrieved papers, we included 70 studies in the qualitative synthesis. Most papers report on chatbots that collect and process personal health data, usually in the context of mental health coaching applications. The majority did not provide any information regarding security or privacy aspects. We were able to determine limitations in literature and identified concrete challenges, including data access and usage of (third-party) services, data storage, data security methods, use case peculiarities and data privacy, as well as legal requirements. Data privacy and security in health chatbots are still underresearched and related information is underrepresented in scientific literature. By addressing the five key challenges in future, the transfer of theoretical solutions into practice can be facilitated.

Smartphone-based virtual agents and insomnia management: A proof-of-concept study for new methods of autonomous screening and management of insomnia symptoms in the general population

Insomnia is the most frequent sleep disorder, and the COVID-19 crisis has massively increased its prevalence in the population, due to psychosocial stress or direct viral contamination. KANOPEE_2 is a smartphone-based application that provides interactions with a virtual agent to autonomously screen and alleviate insomnia symptoms through an intervention programme giving personalized advices regarding sleep hygiene, relaxation techniques and stimulus-control. In this proof-of-concept study, we tested the effects of KANOPEE_2 among users from all over the country (France) who downloaded the app between 1 June and 26 October 2020 (to focus on effects after the end of COVID-19 confinement). Outcome measures include insomnia severity (Insomnia Severity Index) and sleep/wake schedules measured by a sleep diary. One-thousand and thirty-four users answered the screening interview (M_age  = 43.76 years; SD = 13.14), and 108 completed the two-step programme (M_age  = 46.64 years; SD = 13.63). Of those who answered the screening, 42.8% did not report sleep complaints, while 57.2% presented mild-to-severe insomnia symptoms. At the end of the intervention, users reported significantly fewer sleep complaints compared with the beginning of the intervention (Insomnia Severity Index_beginning  = 13.58; Insomnia Severity Index_end  = 11.30; p < 0.001), and significantly increased their sleep efficiency (sleep efficiency_beginning  = 76.46%; sleep efficiency_end  = 80.17%; p = 0.013). KANOPEE_2 is a promising solution both to provide autonomous evaluation of individuals' sleep hygiene and reduce insomnia symptoms over a brief and simple intervention. These results are very encouraging for addressing the issue of insomnia management in people exposed to major psychosocial stress and the consequences of COVID-19 infection.

Characterization of benzodiazepine misuse and comorbidities in patients with alcohol use disorder

BACKGROUND

Due to the frequent presence of anxious symptoms and sleep disorders, benzodiazepines (BZD) are often prescribed to patients with alcohol use disorder (AUD).

OBJECTIVES

To assess BZD misuse and psychiatric comorbidities in patients with AUD.

METHODS

This prospective, monocentric study included all adult patients with AUD hospitalized in a French addiction unit for alcohol withdrawal from November 2017 to May 2018.

RESULTS

Among the 153 patients included, 75 (49%) were using BZD at the time of their hospitalization. Duration of alcohol addiction was longer in BZD users: (33 ± 27 years vs. 29 ± 11 years; P = 0.001). BZD misuse was noted in 27 patients consuming benzodiazepines (36% of BZD users and 18% of all included patients), mainly increase in the dose (on average, 3 ± 4 times the prescribed dose). The most frequently misused benzodiazepines were diazepam (43.2%), alprazolam (18.9%), and lormetazepam (13.5%). The frequency of patients with lifetime use of cocaine or heroin was higher among BZD misusers than among non-misusers (84.6% vs. 42.2%; <0.01 and 53.9% vs. 27.1%; P = 0.04). The frequency of patients consuming cocaine in the last month was higher in BZD misusers than in others: 16% versus 6%, P = 0.002. In multivariate analysis, age (OR=1.65 for 5 years, 95% CI = 1.19-2.27; P = 0.023), psychiatric comorbidities (at least one comorbidity: OR=6.03, 95% CI = 1.40-25.83; P = 0.015) and lifetime cocaine consumption (OR=4.37, 95% CI = 1.21-15.86; P = 0.025) were independently associated with BZD misuse.

CONCLUSION

BZD prescription for long periods might result in tolerance and dose increase. Educational therapy, prescribers' awareness, and development of therapeutic alternatives are essential to limit BZD misuse.

Perceptions and Opinions of Patients About Mental Health Chatbots: Scoping Review

BACKGROUND

Chatbots have been used in the last decade to improve access to mental health care services. Perceptions and opinions of patients influence the adoption of chatbots for health care. Many studies have been conducted to assess the perceptions and opinions of patients about mental health chatbots. To the best of our knowledge, there has been no review of the evidence surrounding perceptions and opinions of patients about mental health chatbots.

OBJECTIVE

This study aims to conduct a scoping review of the perceptions and opinions of patients about chatbots for mental health.

METHODS

The scoping review was carried out in line with the PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) extension for scoping reviews guidelines. Studies were identified by searching 8 electronic databases (eg, MEDLINE and Embase) in addition to conducting backward and forward reference list checking of the included studies and relevant reviews. In total, 2 reviewers independently selected studies and extracted data from the included studies. Data were synthesized using thematic analysis.

RESULTS

Of 1072 citations retrieved, 37 unique studies were included in the review. The thematic analysis generated 10 themes from the findings of the studies: usefulness, ease of use, responsiveness, understandability, acceptability, attractiveness, trustworthiness, enjoyability, content, and comparisons.

CONCLUSIONS

The results demonstrated overall positive perceptions and opinions of patients about chatbots for mental health. Important issues to be addressed in the future are the linguistic capabilities of the chatbots: they have to be able to deal adequately with unexpected user input, provide high-quality responses, and have to show high variability in responses. To be useful for clinical practice, we have to find ways to harmonize chatbot content with individual treatment recommendations, that is, a personalization of chatbot conversations is required.

Effectiveness and Acceptance of a Smartphone-Based Virtual Agent Screening for Alcohol and Tobacco Problems and Associated Risk Factors During COVID-19 Pandemic in the General Population

Background: During the current COVID-19 pandemic, alcohol, and tobacco are the most available substances for managing stress and can induce a risk of addiction. KANOPEE is a smartphone application available to the general population using an embodied conversational agent (ECA) to screen for experiences of problems with alcohol/tobacco use and to provide follow-up tools for brief intervention. Objectives: This study aimed to determine if the smartphone KANOPEE application could identify people at risk for alcohol and/or tobacco use disorders in the context of the current COVID-19 pandemic, to assess adherence to a 7-day follow-up use diary, and to evaluate trust and acceptance of the application. Methods: The conversational agent, named Jeanne, interviewed participants about perceived problems with the use of alcohol and tobacco since the pandemic and explored risk for tobacco and alcohol use disorder with the five-item Cigarette Dependence Scale (CDS-5) and "Cut Down, Annoyed, Guilty, Eye-opener" (CAGE) questionnaire and experience of craving for each substance. Descriptive, univariate, and multivariate analyses were performed to specify personalized associations with reporting a problem with alcohol/tobacco use; descriptive analysis reported the experience with the intervention and acceptance and trust in the application. Results: From April 22 to October 26, 2020, 1,588 French participants completed the KANOPEE interview, and 318 answered the acceptance and trust scales. Forty-two percent of tobacco users and 27% of alcohol users reported problem use since the pandemic. Positive screening with CDS-5 and CAGE and craving were associated with reported problem use (p < 0.0001). Lockdown period influenced alcohol (p < 0.0005) but not tobacco use (p > 0.05). Eighty-eight percent of users reported that KANOPEE was easy to use, and 82% found Jeanne to be trustworthy and credible. Conclusion: KANOPEE was able to screen for risk factors for substance use disorder (SUD) and was acceptable to users. Reporting craving and being at risk for SUD seem to be early markers to be identified. Alcohol problem use seems to be more reliant on contextual conditions such as confinement. This method is able to offer acceptable, brief, and early intervention with minimal delay for vulnerable people.

Smartphone-Based Virtual Agents to Help Individuals With Sleep Concerns During COVID-19 Confinement: Feasibility Study

BACKGROUND

The COVID-19 crisis and consequent confinement restrictions have caused significant psychosocial stress and reports of sleep complaints, which require early management, have increased during recent months. To help individuals concerned about their sleep, we developed a smartphone-based app called KANOPEE that allows users to interact with a virtual agent dedicated to autonomous screening and delivering digital behavioral interventions.

OBJECTIVE

Our objective was to assess the feasibility of this app, in terms of inclusion rate, follow-up rate, perceived trust and acceptance of the virtual agent, and effects of the intervention program, in the context of COVID-19 confinement in France.

METHODS

The virtual agent is an artificial intelligence program using decision tree architecture and interacting through natural body motion and natural voice. A total of 2069 users aged 18 years and above downloaded the free app during the study period (April 22 to May 5, 2020). These users first completed a screening interview based on the Insomnia Severity Index (ISI) conducted by the virtual agent. If the users were positive for insomnia complaints (ISI score >14), they were eligible to join the 2-stage intervention program: (1) complete an electronic sleep diary for 1 week and (2) follow personalized sleep recommendations for 10 days. We collected and analyzed the following measures: sociodemographic information, ISI scores and sleep/wake schedules, and acceptance and trust of the agent.

RESULTS

Approximately 76% (1574/2069) of the app users completed the screening interview with the virtual agent. The virtual agent was well accepted by 27.4% (431/1574) of the users who answered the acceptance and trust questionnaires on its usability, satisfaction, benevolence, and credibility. Of the 773 screened users who reported sleep complaints (ISI score >14), 166 (21.5%) followed Step 1 of the intervention, and only 47 of those (28.3%) followed Step 2. Users who completed Step 1 found that their insomnia complaints (baseline mean ISI score 18.56, mean ISI score after Step 1 15.99; P<.001) and nocturnal sleep quality improved significantly after 1 week. Users who completed Step 2 also showed an improvement compared to the initial measures (baseline mean ISI score 18.87, mean ISI score after Step 2 14.68; P<.001). Users that were most severely affected (ISI score >21) did not respond to either intervention.

CONCLUSIONS

These preliminary results suggest that the KANOPEE app is a promising solution to screen populations for sleep complaints and that it provides acceptable and practical behavioral advice for individuals reporting moderately severe insomnia.

Adherence among HIV-positive injection drug users undergoing methadone treatment in Taiwan

AIMS

The study aims were to investigate adherence to methadone maintenance treatment (MMT) and to identify associated clinical factors in patients who inject drugs diagnosed with human immunodeficiency virus (HIV) infection in Taiwan.

METHODS

Data were from the National Health Surveillance System on HIV and the National Drug Treatment System on MMT. HIV-positive people who inject drugs (HIVPWID) were defined as the study population. Information obtained included age, sex, education, marital status, employment, methadone dose, and date of diagnosis of HIV infection. Adherence was defined as taking methadone for the past 90, 180 and 365 days, then categorized as high (> 90%), moderate (51 to 90%), or low (<=50%) adherent respectively.

RESULTS

Of 1641 HIVPWID registered in the datasets from 2007 to 2012, 961 (58.56%) had received MMT. For HIVPWID evaluated at 90 days (n = 951), 271 (28.5%), 382 (40.2%), and 298 (31.3%) were classified as high, moderate, and low adherent respectively. For HIVPWID evaluated at 180 days (n = 936), 190 (20.3%), 349 (37.3%), and 397 (42.4%) were classified as high, moderate, and low adherent respectively. For HIVPWID evaluated at 365 days (n = 919), 133 (14.5%), 271 (29.5%), and 515 (56.0%) were classified as high, moderate, and low adherent respectively. After controlling for sociodemographics, results showed that methadone dose, location of MMT clinic, and date of HIV diagnosis were significantly associated with MMT adherence.

CONCLUSIONS

Study findings underscore the importance to MMT adherence of methadone dosage, early diagnosis of patient's HIV infection, and area of patient residence.

Acceptance of virtual agents in a homecare context: Evaluation of excessive daytime sleepiness in apneic patients during interventions by continuous positive airway pressure (CPAP) providers

Sleep apnea syndrome treatment relies primarily on continuous positive airway pressure, which requires a homecare follow-up. Excessive daytime sleepiness is a key symptom to be measured during follow-up, and there is a need for more easy-to-administer, ecological and engaging tools to assess it. Virtual agents have shown their effectiveness in performing clinical evaluation in a medical environment. A virtual agent assessing excessive daytime sleepiness via the Epworth Sleepiness Scale has been tested at home by 102 patients treated by continuous positive airway pressure (CPAP) and their homecare providers. Acceptance and trustworthiness of the agent, as well as the influence of demographics and clinical characteristics of patients, were investigated. Results showed that both patients and homecare providers reported a positive attitude towards the virtual agent, which was found to be usable, satisfactory, credible and benevolent. Homecare providers reported that it was not a burden to their working routine. Positive regression coefficients were found between patients' and homecare providers' attitudes towards the virtual agent. We found no influence of patients' demographics and clinical characteristics on their acceptance of the virtual agent. This shows that virtual agents are well accepted by patients and homecare providers, independently of their demographics and clinical characteristics. Positive regression coefficients observed between patients' and homecare providers' perceptions of the agent indicate that the opinions of both influence acceptance of the virtual agent in a homecare context. Virtual agents are new innovative digital solutions to be considered in homecare follow-up of apneic patients treated by CPAP.

Technical Metrics Used to Evaluate Health Care Chatbots: Scoping Review

BACKGROUND

Dialog agents (chatbots) have a long history of application in health care, where they have been used for tasks such as supporting patient self-management and providing counseling. Their use is expected to grow with increasing demands on health systems and improving artificial intelligence (AI) capability. Approaches to the evaluation of health care chatbots, however, appear to be diverse and haphazard, resulting in a potential barrier to the advancement of the field.

OBJECTIVE

This study aims to identify the technical (nonclinical) metrics used by previous studies to evaluate health care chatbots.

METHODS

Studies were identified by searching 7 bibliographic databases (eg, MEDLINE and PsycINFO) in addition to conducting backward and forward reference list checking of the included studies and relevant reviews. The studies were independently selected by two reviewers who then extracted data from the included studies. Extracted data were synthesized narratively by grouping the identified metrics into categories based on the aspect of chatbots that the metrics evaluated.

RESULTS

Of the 1498 citations retrieved, 65 studies were included in this review. Chatbots were evaluated using 27 technical metrics, which were related to chatbots as a whole (eg, usability, classifier performance, speed), response generation (eg, comprehensibility, realism, repetitiveness), response understanding (eg, chatbot understanding as assessed by users, word error rate, concept error rate), and esthetics (eg, appearance of the virtual agent, background color, and content).

CONCLUSIONS

The technical metrics of health chatbot studies were diverse, with survey designs and global usability metrics dominating. The lack of standardization and paucity of objective measures make it difficult to compare the performance of health chatbots and could inhibit advancement of the field. We suggest that researchers more frequently include metrics computed from conversation logs. In addition, we recommend the development of a framework of technical metrics with recommendations for specific circumstances for their inclusion in chatbot studies.

Perceptions and Opinions of Patients About Mental Health Chatbots: Scoping Review (Preprint).. [DOI: 10.2196/preprints.17828]

BACKGROUND

Chatbots have been used in the last decade to improve access to mental health care services. Perceptions and opinions of patients influence the adoption of chatbots for health care. Many studies have been conducted to assess the perceptions and opinions of patients about mental health chatbots. To the best of our knowledge, there has been no review of the evidence surrounding perceptions and opinions of patients about mental health chatbots.

OBJECTIVE

This study aims to conduct a scoping review of the perceptions and opinions of patients about chatbots for mental health.

METHODS

The scoping review was carried out in line with the PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) extension for scoping reviews guidelines. Studies were identified by searching 8 electronic databases (eg, MEDLINE and Embase) in addition to conducting backward and forward reference list checking of the included studies and relevant reviews. In total, 2 reviewers independently selected studies and extracted data from the included studies. Data were synthesized using thematic analysis.

RESULTS

Of 1072 citations retrieved, 37 unique studies were included in the review. The thematic analysis generated 10 themes from the findings of the studies: usefulness, ease of use, responsiveness, understandability, acceptability, attractiveness, trustworthiness, enjoyability, content, and comparisons.

CONCLUSIONS

The results demonstrated overall positive perceptions and opinions of patients about chatbots for mental health. Important issues to be addressed in the future are the linguistic capabilities of the chatbots: they have to be able to deal adequately with unexpected user input, provide high-quality responses, and have to show high variability in responses. To be useful for clinical practice, we have to find ways to harmonize chatbot content with individual treatment recommendations, that is, a personalization of chatbot conversations is required.

Trust and acceptance of a virtual psychiatric interview between embodied conversational agents and outpatients

Virtual agents have demonstrated their ability to conduct clinical interviews. However, the factors influencing patients' engagement with these agents have not yet been assessed. The objective of this study is to assess in outpatients the trust and acceptance of virtual agents performing medical interviews and to explore their influence on outpatients' engagement. In all, 318 outpatients were enroled. The agent was perceived as trustworthy and well accepted by the patients, confirming the good engagement of patients in the interaction. Older and less-educated patients accepted the virtual medical agent (VMA) more than younger and well-educated ones. Credibility of the agent appeared to main dimension, enabling engaged and non-engaged outpatients to be classified. Our results show a high rate of engagement with the virtual agent that was mainly related to high trust and acceptance of the agent. These results open new paths for the future use of VMAs in medicine.

Conversational Interfaces for Health: Bibliometric Analysis of Grants, Publications, and Patents

BACKGROUND

Conversational interfaces (CIs) in different modalities have been developed for health purposes, such as health behavioral intervention, patient self-management, and clinical decision support. Despite growing research evidence supporting CIs' potential, CI-related research is still in its infancy. There is a lack of systematic investigation that goes beyond publication review and presents the state of the art from perspectives of funding agencies, academia, and industry by incorporating CI-related public funding and patent activities.

OBJECTIVE

This study aimed to use data systematically extracted from multiple sources (ie, grant, publication, and patent databases) to investigate the development, research, and fund application of health-related CIs and associated stakeholders (ie, countries, organizations, and collaborators).

METHODS

A multifaceted search query was executed to retrieve records from 9 databases. Bibliometric analysis, social network analysis, and term co-occurrence analysis were conducted on the screened records.

RESULTS

This review included 42 funded projects, 428 research publications, and 162 patents. The total dollar amount of grants awarded was US $30,297,932, of which US $13,513,473 was awarded by US funding agencies and US $16,784,459 was funded by the Europe Commission. The top 3 funding agencies in the United States were the National Science Foundation, National Institutes of Health, and Agency for Healthcare Research and Quality. Boston Medical Center was awarded the largest combined grant size (US $2,246,437) for 4 projects. The authors of the publications were from 58 countries and 566 organizations; the top 3 most productive organizations were Northeastern University (United States), Universiti Teknologi MARA (Malaysia), and the French National Center for Scientific Research (CNRS; France). US researchers produced 114 publications. Although 82.0% (464/566) of the organizations engaged in interorganizational collaboration, 2 organizational research-collaboration clusters were observed with Northeastern University and CNRS as the central nodes. About 112 organizations from the United States and China filed 87.7% patents. IBM filed most patents (N=17). Only 5 patents were co-owned by different organizations, and there was no across-country collaboration on patenting activity. The terms patient, child, elderly, and robot were frequently discussed in the 3 record types. The terms related to mental and chronic issues were discussed mainly in grants and publications. The terms regarding multimodal interactions were widely mentioned as users' communication modes with CIs in the identified records.

CONCLUSIONS

Our findings provided an overview of the countries, organizations, and topic terms in funded projects, as well as the authorship, collaboration, content, and related information of research publications and patents. There is a lack of broad cross-sector partnerships among grant agencies, academia, and industry, particularly in the United States. Our results suggest a need to improve collaboration among public and private sectors and health care organizations in research and patent activities.