Designing a spoken dialogue interface to an intelligent cognitive assistant for people with dementia

Estimation of the Cognitive Functioning of the Elderly by AI Agents: A Comparative Analysis of the Effects of the Psychological Burden of Intervention

In recent years, an increasing number of studies have begun to use conversational data in spontaneous speech to estimate cognitive function in older people. The targets of spontaneous speech with older people used to be physicians and licensed psychologists, but it is now possible to have conversations with fully automatic AI agents. However, it has not yet been clarified what difference there is in conversational communication with older people when the examiner is a human or an AI agent. This study explored the psychological burden experienced by elderly participants during cognitive function assessments, comparing interactions with human and AI conversational partners. Thirty-four participants, averaging 78.71 years of age, were evaluated using the Mini-Mental State Examination (MMSE), the Visual Analogue Scale (VAS), and the State-Trait Anxiety Inventory (STAI). The objective was to assess the psychological impact of different conversational formats on the participants. The results indicated that the mental strain, as measured by VAS and STAI scores, was significantly higher during the MMSE sessions compared to other conversational interactions (p < 0.01). Notably, there was no significant difference in the mental burden between conversations with humans and AI agents, suggesting that AI-based systems could be as effective as human interaction in cognitive assessments.

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.

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.

You have interrupted me again!: making voice assistants more dementia-friendly with incremental clarification

In spontaneous conversation, speakers seldom have a full plan of what they are going to say in advance: they need to conceptualise and plan incrementally as they articulate each word in turn. This often leads to long pauses mid-utterance. Listeners either wait out the pause, offer a possible completion, or respond with an incremental clarification request (iCR), intended to recover the rest of the truncated turn. The ability to generate iCRs in response to pauses is therefore important in building natural and robust everyday voice assistants (EVA) such as Amazon Alexa. This becomes crucial with people with dementia (PwDs) as a target user group since they are known to pause longer and more frequently, with current state-of-the-art EVAs interrupting them prematurely, leading to frustration and breakdown of the interaction. In this article, we first use two existing corpora of truncated utterances to establish the generation of clarification requests as an effective strategy for recovering from interruptions. We then proceed to report on, analyse, and release SLUICE-CR: a new corpus of 3,000 crowdsourced, human-produced iCRs, the first of its kind. We use this corpus to probe the incremental processing capability of a number of state-of-the-art large language models (LLMs) by evaluating (1) the quality of the model's generated iCRs in response to incomplete questions and (2) the ability of the said LLMs to respond correctly after the users response to the generated iCR. For (1), our experiments show that the ability to generate contextually appropriate iCRs only emerges at larger LLM sizes and only when prompted with example iCRs from our corpus. For (2), our results are in line with (1), that is, that larger LLMs interpret incremental clarificational exchanges more effectively. Overall, our results indicate that autoregressive language models (LMs) are, in principle, able to both understand and generate language incrementally and that LLMs can be configured to handle speech phenomena more commonly produced by PwDs, mitigating frustration with today's EVAs by improving their accessibility.

Older adults' intention to use voice assistants: Usability and emotional needs

Population aging is a global problem, and improving the well-being of older adults is an urgent issue. Voice assistants (VAs) offer hands-free voice control and friendly human-computer interaction, making them a significant solution to address the aging problem. Most extant research on VAs is fragmented, and there are relatively few studies conducted from the perspective of emotional needs. This work proposes a comprehensive research model extending the technology acceptance model (TAM) by incorporating the influencing factors subordinate to two research directions: usability and emotional needs. Usability needs include three factors: perceived convenience, security/privacy, and Internet self-efficacy. Emotional needs include humanized interaction, perceived enjoyment, and perceived companionship. A structural equation model (SEM) was used to validate the model empirically with a sample of 425 older users of VAs. The analysis results are quite consistent with the research assumptions, and the findings illustrate that companionship is the most critical factor affecting older adults' intention to adopt VA use, which demonstrates the pivotal role of VAs in meeting the emotional needs of the elderly. The most unexpected observation was seen for the relationship between perceived ease of use and behavioral intention, which was non-significant. This result confirms that when a technology is perceived as very easy to use, perceived ease of use has little to no impact on individuals' intention to use that technology. The novelty of this study lies in the investigation of older adults' behavioral intentions toward using VAs, providing valuable insights for the design and development of VAs tailored for the elderly population. Beyond the academic realm, this research serves as direct inspiration for designers, developers, and policymakers in the fields of assistive technologies and geriatric care. It offers practical insights into creating VAs that effectively address the emotional needs of older adults and enhance their quality of life. Furthermore, elderly individuals are poised to experience significant benefits from the outcomes of this study，the insights garnered from this study empower the elderly to embrace technological advancements that align with their preferences and comfort levels. This study contributes to a more comprehensive understanding of VAs and their potential to enhance the well-being of older adults, while also paving the way for future investigations in this domain. As underscored by this study's emphasis on the significance of emotional needs in technology acceptance, it encourages the adoption of more user-centered design strategies in the development of future VAs.

Consumer direction in the field of digital technologies and people with dementia: a literature review

PURPOSE

Digital technologies have a great potential to improve the quality of life of people with dementia. However, this group is usually not involved in their development and dissemination. A consumer-directed role in the delivery of digital technologies could allow this group to regain autonomy and certain independence. This article aims to conceptualise the components of the Consumer Direction theory in the context of digital technologies and people with dementia.

METHOD

A literature review was conducted. We searched for studies within the aforementioned context in five relevant databases, covering the years 2012-2020. Identified studies were screened and assessed for inclusion. The data were categorised using two-stage qualitative content analysis.

RESULTS

Forty articles were included. The results provide definitions of the four components of the Consumer Direction theory in the context of this study. Namely, what it means for people with dementia to be (1) in control of technology use, (2) offered a variety of technological options, (3) informed and supported regarding the use and training of digital technologies, and (4) actively participating in systems design. These can lead to the empowerment of people with dementia.

CONCLUSION

The four theoretical components of the Consumer Direction theory are conceptualised differently in the context of this study. By providing new definitions, this paper contributes to research and practice. We expect the definitions to be deployed by researchers, practitioners, and policymakers for the creation of a more consumer-directed delivery of digital technologies to people with dementia.Implications for rehabilitationDigital technologies have a great potential to improve the quality of life of people with dementia.A consumer-directed role in the delivery of digital technologies could empower people with dementia and give them the opportunity to take control over the offered services as well as maintain a degree of independence.The Consumer Direction theory and its components should be conceptualised differently in the context of digital technologies and people with dementia than in previous contexts that used the theory.The new definitions can be utilised by researchers, practitioners and policymakers for the creation of a more consumer-directed delivery of digital technologies to people with dementia.

What's Up With These Conversational Health Agents? From Users' Critiques to Implications for Design

Recent advancements in speech recognition technology in combination with increased access to smart speaker devices are expanding conversational interactions to ever-new areas of our lives – including our health and wellbeing. Prior human-computer interaction research suggests that Conversational Agents (CAs) have the potential to support a variety of health-related outcomes, due in part to their intuitive and engaging nature. Realizing this potential requires however developing a rich understanding of users' needs and experiences in relation to these still-emerging technologies. To inform the design of CAs for health and wellbeing, we analyze 2741 critical reviews of 485 Alexa health and fitness Skills using an automated topic modeling approach; identifying 15 subjects of criticism across four key areas of design (functionality, reliability, usability, pleasurability). Based on these findings, we discuss implications for the design of engaging CAs to support health and wellbeing.

Dementia Care, Fall Detection, and Ambient-Assisted Living Technologies Help Older Adults Age in Place: A Scoping Review

OBJECTIVES

We aimed to describe recent technologic advances in the three domains of dementia care, falls, and home supports; summarize existing literature on usability; and identify knowledge gaps.

METHODS

A comprehensive search of five databases for recent peer-reviewed publications was conducted in May 2020. Independent reviewers performed title/abstract review, full-text screening, data extraction, and study characteristic summarization.

RESULTS

Out of 2,696 citations, 151 articles were retrieved for full-text evaluation, after which 54 studies were included in this scoping review. For each domain, different technologies are available to enhance the health and well-being of older adults; many users deemed them usable and useful. Technologies targeted improving function, psychosocial and cognitive status, home safety, and caregiver burden. Barriers to widespread uptake include privacy concerns, suboptimal user experience, and willingness to accept assistance.

CONCLUSION

Technologic innovations directed toward dementia care, fall detection, and ambient-assisted living can aid older adults "aging in place."

Voice Assistant Reminders and the Latency of Scheduled Medication Use in Older Adults With Pain: Descriptive Feasibility Study

Background

Pain is difficult to manage in older adults. It has been recommended that pain management in older adults should include both nonpharmacologic and pharmacologic strategies. Unfortunately, nonadherence to pain medication is more prevalent than nonadherence to any other chronic disease treatment. Technology-based reminders have some benefit for medication adherence, but adherence behavior outcomes have mostly been verified by self-reports.

Objective

We aimed to describe objective medication adherence and the latency of medication use after a voice assistant reminder prompted participants to take pain medications for chronic pain.

Methods

A total of 15 older adults created a voice assistant reminder for taking scheduled pain medications. A subsample of 5 participants were randomly selected to participate in a feasibility study, in which a medication event monitoring system for pain medications was used to validate medication adherence as a health outcome. Data on the subsample’s self-assessed pain intensity, pain interference, concerns and necessity beliefs about pain medications, self-confidence in managing pain, and medication implementation adherence were analyzed.

Results

In the 5 participants who used the medication event monitoring system, the overall latency between voice assistant reminder deployment and the medication event (ie, medication bottle cap opening) was 55 minutes. The absolute latency (before or after the reminder) varied among the participants. The shortest average time taken to open the cap after the reminder was 17 minutes, and the longest was 4.5 hours. Of the 168 voice assistant reminders for scheduled pain medications, 25 (14.6%) resulted in the opening of MEMS caps within 5 minutes of the reminder, and 107 (63.7%) resulted in the opening of MEMS caps within 30 minutes of the reminder.

Conclusions

Voice assistant reminders may help cue patients to take scheduled medications, but the timing of medication use may vary. The timing of medication use may influence treatment effectiveness. Tracking the absolute latency time of medication use may be a helpful method for assessing medication adherence. Medication event monitoring may provide additional insight into medication implementation adherence during the implementation of mobile health interventions.

Conversational System as Assistant Tool in Reminiscence Therapy for People with Early-Stage of Alzheimer's

Reminiscence therapy is a non-pharmacological intervention that helps mitigate unstable psychological and emotional states in patients with Alzheimer’s disease, where past experiences are evoked through conversations between the patients and their caregivers, stimulating autobiographical episodic memory. It is highly recommended that people with Alzheimer regularly receive this type of therapy. In this paper, we describe the development of a conversational system that can be used as a tool to provide reminiscence therapy to people with Alzheimer’s disease. The system has the ability to personalize the therapy according to the patients information related to their preferences, life history and lifestyle. An evaluation conducted with eleven people related to patient care (caregiver = 9, geriatric doctor = 1, care center assistant = 1) shows that the system is capable of carrying out a reminiscence therapy according to the patient information in a successful manner.

Voice-Controlled Intelligent Personal Assistants in Health Care: International Delphi Study

Background

Voice-controlled intelligent personal assistants (VIPAs), such as Amazon Echo and Google Home, involve artificial intelligence–powered algorithms designed to simulate humans. Their hands-free interface and growing capabilities have a wide range of applications in health care, covering off-clinic education, health monitoring, and communication. However, conflicting factors, such as patient safety and privacy concerns, make it difficult to foresee the further development of VIPAs in health care.

Objective

This study aimed to develop a plausible scenario for the further development of VIPAs in health care to support decision making regarding the procurement of VIPAs in health care organizations.

Methods

We conducted a two-stage Delphi study with an internationally recruited panel consisting of voice assistant experts, medical professionals, and representatives of academia, governmental health authorities, and nonprofit health associations having expertise with voice technology. Twenty projections were formulated and evaluated by the panelists. Descriptive statistics were used to derive the desired scenario.

Results

The panelists expect VIPAs to be able to provide solid medical advice based on patients’ personal health information and to have human-like conversations. However, in the short term, voice assistants might neither provide frustration-free user experience nor outperform or replace humans in health care. With a high level of consensus, the experts agreed with the potential of VIPAs to support elderly people and be widely used as anamnesis, informational, self-therapy, and communication tools by patients and health care professionals. Although users’ and governments’ privacy concerns are not expected to decrease in the near future, the panelists believe that strict regulations capable of preventing VIPAs from providing medical help services will not be imposed.

Conclusions

According to the surveyed experts, VIPAs will show notable technological development and gain more user trust in the near future, resulting in widespread application in health care. However, voice assistants are expected to solely support health care professionals in their daily operations and will not be able to outperform or replace medical staff.

Robotic Telemedicine for Mental Health: A Multimodal Approach to Improve Human-Robot Engagement

COVID-19 has severely impacted mental health in vulnerable demographics, in particular older adults, who face unprecedented isolation. Consequences, while globally severe, are acutely pronounced in low- and middle-income countries (LMICs) confronting pronounced gaps in resources and clinician accessibility. Social robots are well-recognized for their potential to support mental health, yet user compliance (i.e., trust) demands seamless affective human-robot interactions; natural 'human-like' conversations are required in simple, inexpensive, deployable platforms. We present the design, development, and pilot testing of a multimodal robotic framework fusing verbal (contextual speech) and nonverbal (facial expressions) social cues, aimed to improve engagement in human-robot interaction and ultimately facilitate mental health telemedicine during and beyond the COVID-19 pandemic. We report the design optimization of a hybrid face robot, which combines digital facial expressions based on mathematical affect space mapping with static 3D facial features. We further introduce a contextual virtual assistant with integrated cloud-based AI coupled to the robot's facial representation of emotions, such that the robot adapts its emotional response to users' speech in real-time. Experiments with healthy participants demonstrate emotion recognition exceeding 90% for happy, tired, sad, angry, surprised and stern/disgusted robotic emotions. When separated, stern and disgusted are occasionally transposed (70%+ accuracy overall) but are easily distinguishable from other emotions. A qualitative user experience analysis indicates overall enthusiastic and engaging reception to human-robot multimodal interaction with the new framework. The robot has been modified to enable clinical telemedicine for cognitive engagement with older adults and people with dementia (PwD) in LMICs. The mechanically simple and low-cost social robot has been deployed in pilot tests to support older individuals and PwD at the Schizophrenia Research Foundation (SCARF) in Chennai, India. A procedure for deployment addressing challenges in cultural acceptance, end-user acclimatization and resource allocation is further introduced. Results indicate strong promise to stimulate human-robot psychosocial interaction through the hybrid-face robotic system. Future work is targeting deployment for telemedicine to mitigate the mental health impact of COVID-19 on older adults and PwD in both LMICs and higher income regions.

Population subgroup differences in the use of a COVID-19 chatbot

COVID-19 chatbots are widely used to screen for symptoms and disseminate information about the virus, yet little is known about the population subgroups that interact with this technology and the specific features that are used. An analysis of 1,000,740 patients invited to use a COVID-19 chatbot, 69,451 (6.94%) of which agreed to participate, shows differences in chatbot feature use by gender, race, and age. These results can inform future public health COVID-19 symptom screening and information dissemination strategies.

Issues Associated With the Management and Governance of Sensor Data and Information to Assist Aging in Place: Focus Group Study With Health Care Professionals

Background

Smart home and telemonitoring technologies have often been suggested to assist health care workers in supporting older people to age in place. However, there is limited research examining diverse information needs of different groups of health care workers and their access to appropriate information technologies.

Objective

The aim of this study was to investigate the issues associated with using technologies that connect older people to their health care providers to support aging in place and enhance older people’s health and well-being.

Methods

Seven focus group discussions were conducted comprising 44 health care professionals who provided clinic-based or in-home services to community-dwelling older people. Participants were asked about their information needs and how technology could help them support older people to age in place. The recordings of the sessions were transcribed and thematically analyzed.

Results

The perspectives varied between the respondents who worked in primary care clinics and those who worked in community-based services. Three overarching themes were identified. The first theme was “access to technology and systems,” which examined the different levels of technology in use and the problems that various groups of health care professionals had in accessing information about their patients. Primary care professionals had access to good internal information systems but they experienced poor integration with other health care providers. The community-based teams had poor access to technology. The second theme was “collecting and sharing of information,” which focused on how technology might be used to provide them with more information about their patients. Primary care teams were interested in telemonitoring for specific clinical indicators but they wanted the information to be preprocessed. Community-based teams were more concerned about gaining information on the patients’ social environment. The third theme was that all respondents identified similar “barriers to uptake”: cost and funding issues, usability of systems by older people, and information security and privacy concerns.

Conclusions

The participants perceived the potential benefits of technologies, but they were concerned that the information they received should be preprocessed and integrated with current information systems and tailored to the older people’s unique and changing situations. Several management and governance issues were identified, which needed to be resolved to enable the widespread integration of these technologies into the health care system. The disconnected nature of the current information architecture means that there is no clear way for sensor data from telemonitoring and smart home devices to be integrated with other patient information. Furthermore, cost, privacy, security, and usability barriers also need to be resolved. This study highlights the importance and the complexity of management and governance of systems to collect and disseminate such information. Further research into the requirements of all stakeholder groups and how the information can be processed and disseminated is required.

Voice Assistant Reminders for Pain Self-Management Tasks in Aging Adults

Aging adults are impacted by pain. Technology can assist older adults with pain self-management while allowing for independence. The current usability study explored the use of voice assistant reminders for two pain self-management tasks in aging adults. Fifteen community-dwelling older adults with chronic pain and an average age of 65 years used the voice assistant for 4 weeks. Participants had moderate scores for pain severity (mean = 4.6 [SD = 2.3]) and pain interference (mean = 4 [SD = 2.6]). Voice assistant usability was above average (78 of 100). Median time to set up the Google Home Assistant profile was 5 minutes (SD = 7.5), with a median of asking for help two times. Pain self-management task reminders from the voice assistant were perceived as consistent, easy to set up, and helpful for accountability. Voice assistant reminders may be an option to help encourage a variety of pain self-management tasks in aging adults. [Journal of Gerontological Nursing, 46(10), 27-33.].

Active Involvement of People with Dementia: A Systematic Review of Studies Developing Supportive Technologies

Although there are promising benefits of supportive technology in dementia care, use of these technologies is still limited. It is challenging for researchers and developers in this field to actively involve people with dementia in development. This review updates and builds on existing knowledge by including a contemporary and relevant perspective. This perspective was gained by including search words and search databases from the field of Human Computer Interaction (HCI) and Design, as these fields were expected to supply novel insights in the complex task of actively involving people with dementia in developing supportive technologies. A total of 49 out of 3456 studies were included which describe the development of a great variety of technologies. Often people with dementia were involved in the generative or evaluative phase of the development. Interviews and observations were most commonly used methods. In seven articles the people with dementia were co-designers. This literature review reflects that people with dementia can influence the development of technology in regards to content, design, and even the initial idea, although the impact on how they experience their own involvement remains largely unknown. There is a lack of specific knowledge on appropriate methods and materials for active involvement of people with dementia in supportive technology development, even when including articles from the field of HCI and Design. Future research is needed to further appreciate and improve the desired role of people with dementia in meaningful technology development.

Evaluating the Facilitators, Barriers, and Medical Outcomes Commensurate with the Use of Assistive Technology to Support People with Dementia: A Systematic Review Literature

Background: Assistive technologies (AT) have been used to improve the daily living conditions of people living with dementia (PWD). Research supports the positive impact of the use of AT such as decreased burden on caregivers and behavioral support for people with dementia. Four reviews in the last six years have analyzed AT and PWD, but none have incorporated the dimension of medical outcomes. Objectives: The purpose of this review is to identify the facilitators, barriers, and medical outcomes commensurate with the use of AT with PWD. Method: This review queried The Cumulative Index of Nursing and Allied Health Literature (CINAHL), Web of Science, Science Direct, and PubMed databases for peer-reviewed publications in the last five years for facilitators, barriers, and medical outcomes commensurate with the use of AT with PWD. The study is reported and conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) and the Kruse Protocol for conducting a systematic review. Results: 48 studies were analyzed. Fourteen types of AT, 17 facilitators, 17 barriers, and 16 medical outcomes were identified in the literature. The two most frequently mentioned ATs were cognitive stimulators (9/48, 19%) and social robots (5/48, 10%). The two most frequently mentioned facilitators were caregivers want AT (8/68, 12%) and enables increased independence (7/68, 10%). The top two barriers were cost (8/75, 11%) and PWD reject AT (8/75, 11%). The top medical outcomes were improved cognitive abilities (6/69, 9%), increased activities of daily living (ADLs), and increased autonomy (each at 5/69, 7%): Zero negative outcomes were reported. Conclusion: The systematic review revealed the positive relations that occur when PWD and their caregivers use AT. Although many reservations surrounding the use of AT exist, a majority of the literature shows a positive effect of its use. Research supports a strong support for AT by caregivers due to many positive medical outcomes, but also a reticence to adopt by PWD. If ATs for PWD are a way to reduce stress on caregivers, barriers of cost and complexity need to be addressed through health policy or grants.

Development of an individualized asynchronous sensor-based telerehabilitation program for patients undergoing total knee replacement: Participatory design

Telerehabilitation programs can be employed to establish communication between patients and healthcare professionals and empower patients performing their training remotely. This study aimed to identify patients’ requirements after a total knee replacement following a self-training rehabilitation program, leading to the design and development of a telerehabilitation program that can meet the stakeholders’ actual needs. System design, development, and testing were conducted in five iterations based on a participatory design approach. Data collection was performed using interviews, observations, prototyping, and questionnaires. It was found that the main barriers facing the existing rehabilitation program were a lack of clear communication, lack of relevant information, and healthcare professional’s feedback. The participants emphasized the main themes of communication, information, training, and motivation in the process of design and development. In using the telerehabilitation program, the patients reported a high level of user-friendliness, flexibility, and a sense of security. This study has identified obstacles in the current rehabilitation program and revealed the potential effectiveness of using asynchronous communication and sensor-based technologies by employing participatory design and development. A higher level of portability and flexibility were observed. However, future studies and development are required to investigate the overall usability and reliability of the telerehabilitation program.

Effectiveness of Conversational Agents (Virtual Assistants) in Health Care: Protocol for a Systematic Review

Background

Conversational agents (also known as chatbots) have evolved in recent decades to become multimodal, multifunctional platforms with potential to automate a diverse range of health-related activities supporting the general public, patients, and physicians. Multiple studies have reported the development of these agents, and recent systematic reviews have described the scope of use of conversational agents in health care. However, there is scarce research on the effectiveness of these systems; thus, their viability and applicability are unclear.

Objective

The objective of this systematic review is to assess the effectiveness of conversational agents in health care and to identify limitations, adverse events, and areas for future investigation of these agents.

Methods

The Preferred Reporting Items for Systematic Reviews and Meta-Analyses Protocols will be used to structure this protocol. The focus of the systematic review is guided by a population, intervention, comparator, and outcome framework. A systematic search of the PubMed (Medline), EMBASE, CINAHL, and Web of Science databases will be conducted. Two authors will independently screen the titles and abstracts of the identified references and select studies according to the eligibility criteria. Any discrepancies will then be discussed and resolved. Two reviewers will independently extract and validate data from the included studies into a standardized form and conduct quality appraisal.

Results

As of January 2020, we have begun a preliminary literature search and piloting of the study selection process.

Conclusions

This systematic review aims to clarify the effectiveness, limitations, and future applications of conversational agents in health care. Our findings may be useful to inform the future development of conversational agents and promote the personalization of patient care.

International Registered Report Identifier (IRRID)

PRR1-10.2196/16934

Responses of Conversational Agents to Health and Lifestyle Prompts: Investigation of Appropriateness and Presentation Structures

BACKGROUND

Conversational agents (CAs) are systems that mimic human conversations using text or spoken language. Their widely used examples include voice-activated systems such as Apple Siri, Google Assistant, Amazon Alexa, and Microsoft Cortana. The use of CAs in health care has been on the rise, but concerns about their potential safety risks often remain understudied.

OBJECTIVE

This study aimed to analyze how commonly available, general-purpose CAs on smartphones and smart speakers respond to health and lifestyle prompts (questions and open-ended statements) by examining their responses in terms of content and structure alike.

METHODS

We followed a piloted script to present health- and lifestyle-related prompts to 8 CAs. The CAs' responses were assessed for their appropriateness on the basis of the prompt type: responses to safety-critical prompts were deemed appropriate if they included a referral to a health professional or service, whereas responses to lifestyle prompts were deemed appropriate if they provided relevant information to address the problem prompted. The response structure was also examined according to information sources (Web search-based or precoded), response content style (informative and/or directive), confirmation of prompt recognition, and empathy.

RESULTS

The 8 studied CAs provided in total 240 responses to 30 prompts. They collectively responded appropriately to 41% (46/112) of the safety-critical and 39% (37/96) of the lifestyle prompts. The ratio of appropriate responses deteriorated when safety-critical prompts were rephrased or when the agent used a voice-only interface. The appropriate responses included mostly directive content and empathy statements for the safety-critical prompts and a mix of informative and directive content for the lifestyle prompts.

CONCLUSIONS

Our results suggest that the commonly available, general-purpose CAs on smartphones and smart speakers with unconstrained natural language interfaces are limited in their ability to advise on both the safety-critical health prompts and lifestyle prompts. Our study also identified some response structures the CAs employed to present their appropriate responses. Further investigation is needed to establish guidelines for designing suitable response structures for different prompt types.

Conversational agents in healthcare: a systematic review

Objective

Our objective was to review the characteristics, current applications, and evaluation measures of conversational agents with unconstrained natural language input capabilities used for health-related purposes.

Methods

We searched PubMed, Embase, CINAHL, PsycInfo, and ACM Digital using a predefined search strategy. Studies were included if they focused on consumers or healthcare professionals; involved a conversational agent using any unconstrained natural language input; and reported evaluation measures resulting from user interaction with the system. Studies were screened by independent reviewers and Cohen’s kappa measured inter-coder agreement.

Results

The database search retrieved 1513 citations; 17 articles (14 different conversational agents) met the inclusion criteria. Dialogue management strategies were mostly finite-state and frame-based (6 and 7 conversational agents, respectively); agent-based strategies were present in one type of system. Two studies were randomized controlled trials (RCTs), 1 was cross-sectional, and the remaining were quasi-experimental. Half of the conversational agents supported consumers with health tasks such as self-care. The only RCT evaluating the efficacy of a conversational agent found a significant effect in reducing depression symptoms (effect size d = 0.44, p = .04). Patient safety was rarely evaluated in the included studies.

Conclusions

The use of conversational agents with unconstrained natural language input capabilities for health-related purposes is an emerging field of research, where the few published studies were mainly quasi-experimental, and rarely evaluated efficacy or safety. Future studies would benefit from more robust experimental designs and standardized reporting.

Protocol Registration

The protocol for this systematic review is registered at PROSPERO with the number CRD42017065917.

Needs of people with dementia and their informal caregivers concerning assistive technologies

Background and objective: Assistive technologies might be a suitable option for supporting people with dementia and their informal caregivers. To avoid "one-fits-all"-solutions and to design useful technologies, it is essential to consider the end-users' needs. The objective of this review was to examine the needs of people with dementia and their informal caregivers with regard to assistive technologies. Methods: We conducted a scoping review based on a comprehensive literature search in databases, handsearching, and free web searching. Additionally, we performed citation tracking of included studies. We included all types of study designs. Two researchers independently selected the studies. The results were thematically categorised by two researchers. Results: The search yielded 7160 references. 18 of 24 included studies were qualitative. The studies had been conducted in 13 different countries, mostly in Europe. The sample size ranged between two and 270 participants. Most of the studies involved people with dementia as well as informal caregivers. The analysis resulted in eleven themes. The themes could be assigned to three domains: "needed technologies", "characteristics of needed technologies", and "information about technologies". Conclusions: The results might guide future usage, development and research addressing end users' needs with regard to assistive technologies.

Factors Influencing the Adoption of Smart Health Technologies for People With Dementia and Their Informal Caregivers: Scoping Review and Design Framework

BACKGROUND

Smart Health technologies (s-Health technologies) are being developed to support people with dementia (PwD) and their informal caregivers at home, to improve care and reduce the levels of burden and stress they experience. However, although s-Health technologies have the potential to facilitate this, the factors influencing a successful implementation in this population are still unknown.

OBJECTIVE

The aim of this study was to review existing literature to explore the factors influencing PwD and their informal caregivers' adoption of s-Health technologies for home care.

METHODS

Following the Arksey and O'Malley methodology, this study is a scoping review providing a narrative description of the scientific literature on factors influencing s-Health technology adoption for PwD and their informal caregivers. A search was conducted using PubMed, the Cochrane library, the IEEE library, and Scopus. Publications screening was conducted by 2 researchers based on inclusion criteria, and full-text analysis was then conducted by 1 researcher. The included articles were thematically analyzed by 2 researchers to gain an insight into factors influencing adoption that PwD and their informal caregivers have to encounter when using s-Health technologies. Relevant information was identified and coded. Codes were later discussed between the researchers for developing and modifying them and for achieving a consensus, and the researchers organized the codes into broader themes.

RESULTS

Emerging themes were built in a way that said something specific and meaningful about the research question, creating a list of factors influencing the adoption of s-Health technologies for PwD and their informal caregivers, including attitudinal aspects, ethical issues, technology-related challenges, condition-related challenges, and identified gaps. A design framework was created as a guide for future research and innovation in the area of s-Health technologies for PwD and their informal caregivers: DemDesCon for s-Health Technologies. DemDesCon for s-Health Technologies addresses 4 domains to consider for the design and development of s-Health technologies for this population: cognitive decline domain, physical decline domain, social domain, and development domain.

CONCLUSIONS

Although s-Health technologies have been used in health care scenarios, more work is needed for them to fully achieve their potential for use in dementia care. Researchers, businesses, and public governments need to collaborate to design and implement effective technology solutions for PwD and their informal caregivers, but the lack of clear design guidelines seems to be slowing the process. We believe that the DemDesCon framework will provide them with the guidance and assistance needed for creating meaningful devices for PwD home care and informal caregivers, filling a much-needed space in the present knowledge gap.

Prompting Technology and Persons With Dementia: The Significance of Context and Communication

Background and Objectives

Smart home auto-prompting has the potential to increase the functional independence of persons with dementia (PWDs) and decrease caregiver burden as instrumental activities of daily living (IADLs) are completed at home. To improve prompting technologies, we sought to inductively understand how PWDs responded to auto-prompting while performing IADL tasks.

Research Design and Methods

Fifteen PWDs completed eight IADLs in a smart home testbed and received a hierarchy of verbal auto-prompts (indirect, direct, multimodal) as needed for task completion. Two researchers viewed archived videos and recorded the observed behaviors of the PWDs and their reflections watching the PWDs. Using qualitative descriptive methods, an interdisciplinary analytic team reviewed transcripts and organized data into themes using content analysis.

Results

Context and Communication emerged as the major themes, suggesting that positive user experiences will require auto-prompting systems to account for a multitude of contextual factors (individual and environmental) such as level of cognitive impairment, previous exposure to task, and familiarity of environment. Communicating with another human rather than an automated prompting system may be important if individuals begin to exhibit signs of stress while completing activities.

Discussion and Implications

Additional work is needed to create auto-prompting systems that provide specific, personalized, and flexible prompts. Holistic conceptualization of "successful task completion" is needed and a positive end-user experience will be key to utility. Such systems will benefit from including positive reinforcement, training, and exploration of how, and whether, direct human involvement can be minimized during the provision of in-home care.

Health and Fitness Apps for Hands-Free Voice-Activated Assistants: Content Analysis

Background

Hands-free voice-activated assistants and their associated devices have recently gained popularity with the release of commercial products, including Amazon Alexa and Google Assistant. Voice-activated assistants have many potential use cases in healthcare including education, health tracking and monitoring, and assistance with locating health providers. However, little is known about the types of health and fitness apps available for voice-activated assistants as it is an emerging market.

Objective

This review aimed to examine the characteristics of health and fitness apps for commercially available, hands-free voice-activated assistants, including Amazon Alexa and Google Assistant.

Methods

Amazon Alexa Skills Store and Google Assistant app were searched to find voice-activated assistant apps designated by vendors as health and fitness apps. Information was extracted for each app including name, description, vendor, vendor rating, user reviews and ratings, cost, developer and security policies, and the ability to pair with a smartphone app and website and device. Using a codebook, two reviewers independently coded each app using the vendor’s descriptions and the app name into one or more health and fitness, intended age group, and target audience categories. A third reviewer adjudicated coding disagreements until consensus was reached. Descriptive statistics were used to summarize app characteristics.

Results

Overall, 309 apps were reviewed; health education apps (87) were the most commonly occurring, followed by fitness and training (72), nutrition (33), brain training and games (31), and health monitoring (25). Diet and calorie tracking apps were infrequent. Apps were mostly targeted towards adults and general audiences with few specifically geared towards patients, caregivers, or medical professionals. Most apps were free to enable or use and 18.1% (56/309) could be paired with a smartphone app and website and device; 30.7% (95/309) of vendors provided privacy policies; and 22.3% (69/309) provided terms of use. The majority (36/42, 85.7%) of Amazon Alexa apps were rated by the vendor as mature or guidance suggested, which were geared towards adults only. When there was a user rating available, apps had a wide range of ratings from 1 to 5 stars with a mean of 2.97. Google Assistant apps did not have user reviews available, whereas most of Amazon Alexa apps had at least 1-9 reviews available.

Conclusions

The emerging market of health and fitness apps for voice-activated assistants is still nascent and mainly focused on health education and fitness. Voice-activated assistant apps had a wide range of content areas but many published in the health and fitness categories did not actually have a clear health or fitness focus. This may, in part, be due to Amazon and Google policies, which place restrictions on the delivery of care or direct recording of health data. As in the mobile app market, the content and functionalities may evolve to meet growing demands for self-monitoring and disease management.

Alexa, Siri, Cortana, and More: An Introduction to Voice Assistants

Voice assistants are software agents that can interpret human speech and respond via synthesized voices. Apple's Siri, Amazon's Alexa, Microsoft's Cortana, and Google's Assistant are the most popular voice assistants and are embedded in smartphones or dedicated home speakers. Users can ask their assistants questions, control home automation devices and media playback via voice, and manage other basic tasks such as email, to-do lists, and calendars with verbal commands. This column will explore the basic workings and common features of today's voice assistants. It will also discuss some of the privacy and security issues inherent to voice assistants and some potential future uses for these devices. As voice assistants become more widely used, librarians will want to be familiar with their operation and perhaps consider them as a means to deliver library services and materials.

User Requirements for Technology to Assist Aging in Place: Qualitative Study of Older People and Their Informal Support Networks

Background

Informal support is essential for enabling many older people to age in place. However, there is limited research examining the information needs of older adults’ informal support networks and how these could be met through home monitoring and information and communication technologies.

Objective

The purpose of this study was to investigate how technologies that connect older adults to their informal and formal support networks could assist aging in place and enhance older adults’ health and well-being.

Methods

Semistructured interviews were conducted with 10 older adults and a total of 31 members of their self-identified informal support networks. They were asked questions about their information needs and how technology could support the older adults to age in place. The interviews were transcribed and thematically analyzed.

Results

The analysis identified three overarching themes: (1) the social enablers theme, which outlined how timing, informal support networks, and safety concerns assist the older adults’ uptake of technology, (2) the technology concerns theme, which outlined concerns about cost, usability, information security and privacy, and technology superseding face-to-face contact, and (3) the information desired theme, which outlined what information should be collected and transferred and who should make decisions about this.

Conclusions

Older adults and their informal support networks may be receptive to technology that monitors older adults within the home if it enables aging in place for longer. However, cost, privacy, security, and usability barriers would need to be considered and the system should be individualizable to older adults’ changing needs. The user requirements identified from this study and described in this paper have informed the development of a technology that is currently being prototyped.

Impact evaluation of assistive technology support for the people with dementia

This study explores important factors of assistive technology (AT) and evaluates their relative impact on AT effectiveness and retention. Questionnaire based survey is used for data collection from 327 people with dementia (PWD). This empirical study uses statistical techniques including exploratory factor analysis for factor identification, linear regression for impact study, Kruskal Wallis H and Mann Whitney U tests for the statistical significant study in terms of demographic and characteristics. The exploratory factor analysis results into 11 factors: operational support, physical support, psychological support, social support, cultural match, reduced external help, affordability, travel help, compatibility, effectiveness and retention. The results reveal that social support, psychological support and travel help and reduced external help strongly impact on AT effectiveness and retention. The users are motivated by socialization support through using AT without any external help. The use of AT during travelling improves confidence of the PWD and helps them psychologically.

'I want to feel at home': establishing what aspects of environmental design are important to people with dementia nearing the end of life

BACKGROUND

The design of environments in which people with dementia live should be understandable, reinforce personal identity and maintain their abilities. The focus on supporting people with dementia to live well has omitted considering the needs or wishes for a supportive physical environment of those who are nearing the end of their lives. Using a combination of focus groups and a Delphi survey, this study explored the views of people with dementia, family carers and professionals on what aspects of the physical environment would be important to support a good quality of life to the very end.

METHODS

Three focus groups were carried out in three cities along the East Coast of Australia using a discussion guide informed by a literature review. Focus groups comprised recently bereaved family carers of people with dementia (FG1), people with dementia and family carers of people with dementia (FG2) and practitioners caring for people with dementia nearing or at the end of their lives (FG3). Focus group conversations were audio-recorded with participants' consent. Audio files were transcribed verbatim and analysed thematically to identify environmental features that could contribute to achieving the goal of providing a comfortable life to the end. A list of design features derived from analysis of focus group transcripts was distributed to a range of experts in the dementia field and a consensus sought on their appropriateness. From this, a set of features to inform the design of environments for people with dementia nearing the end of life was defined.

RESULTS

Eighteen people took part in three focus groups: two with dementia, eleven current or recently bereaved family carers and five practitioners. There were differences in opinion on what were important environmental considerations. People with dementia and family carers identified comfort through engagement, feeling at home, a calm environment, privacy and dignity and use of technology to remain connected as important. For practitioners, design to facilitate duty of care and institutional influences on their practice were salient themes. Twenty one experts in the dementia field took part in the survey to agree a consensus on the desirable features derived from analysis of focus group transcripts, with fifteen features agreed.

CONCLUSIONS

The fifteen features are compatible with the design principles for people with dementia who are mobile, but include a stronger focus on sensory engagement. We suggest that considering these features as part of a continuum of care will support good practice and offer those with dementia the opportunity to live well until the end and give their families a more positive experience in the last days of their lives together.