A Machine-Learning Based Approach for Predicting Older Adults' Adherence to Technology-Based Cognitive Training.

Adequate adherence is a necessary condition for success with any intervention, including for computerized cognitive training designed to mitigate age-related cognitive decline. Tailored prompting systems offer promise for promoting adherence and facilitating intervention success. However, developing adherence support systems capable of just-in-time adaptive reminders requires understanding the factors that predict adherence, particularly an imminent adherence lapse. In this study we built machine learning models to predict participants' adherence at different levels (overall and weekly) using data collected from a previous cognitive training intervention. We then built machine learning models to predict adherence using a variety of baseline measures (demographic, attitudinal, and cognitive ability variables), as well as deep learning models to predict the next week's adherence using variables derived from training interactions in the previous week. Logistic regression models with selected baseline variables were able to predict overall adherence with moderate accuracy (AUROC: 0.71), while some recurrent neural network models were able to predict weekly adherence with high accuracy (AUROC: 0.84-0.86) based on daily interactions. Analysis of the post hoc explanation of machine learning models revealed that general self-efficacy, objective memory measures, and technology self-efficacy were most predictive of participants' overall adherence, while time of training, sessions played, and game outcomes were predictive of the next week's adherence. Machine-learning based approaches revealed that both individual difference characteristics and previous intervention interactions provide useful information for predicting adherence, and these insights can provide initial clues as to who to target with adherence support strategies and when to provide support. This information will inform the development of a technology-based, just-in-time adherence support systems.

Cognitive Training: Transfer Beyond the Laboratory?

OBJECTIVE: To assess the evidence of general transfer from training on abstract computer-based exercises and video games to driving and flight control. BACKGROUND: Many believe that training on abstract computer-based exercises and video games enhances cognitive capacities to the benefit of performance in operational contexts. The basic research in this area is controversial. METHOD: We summarize reviews of the basic research data on transfer from training on abstract computer-based exercises and video games and undertake a detailed methodological review of flight and driving transfer studies. RESULTS: Reviews of basic transfer research fail to reveal evidence of general transfer, although a few applied studies are said to show general transfer to driving or flight control. Our review of these applied studies identifies issues with research methods and data interpretation that compromise the credibility of their results to an extent that they do not provide robust evidence of general transfer from abstract computer-based exercises or video games. CONCLUSION: The state of cognitive training and video game training in relation to transfer has failed to meet early expectations. Much of the research in this area suffers from inadequate experimental control and flawed interpretation of results. We call for adherence to robust experimental design, critical evaluation of data patterns, and replication of keystone results. We also call for a theoretically grounded research effort, and we outline relevant theoretical conceptions of transfer. APPLICATION: A robust theory of transfer and better understanding of transfer effects can guide development of principles for design and use of training simulators.

Remote Health Monitoring for Older Adults and Those with Heart Failure: Adherence and System Usability.

BACKGROUND: Remote health monitoring technology has been suggested as part of an early intervention and prevention care model. Older adults with a chronic health condition have been shown to benefit from remote monitoring but often have challenges with complex technology. The current study reports on the usability of and adherence with an integrated, real-time monitoring system over an extended period of time by older adults with and without a chronic health condition. MATERIALS AND METHODS: Older adults 55 years of age and over with and without heart failure participated in a study in which a telehealth system was used for 6 months each. The system consisted of a wireless wristwatch-based monitoring device that continuously collected temperature and motion data. Other health information was collected daily using a weight scale, blood pressure cuff, and tablet that participants used for health surveys. Data were automatically analyzed and summarized by the system and presented to study nurses. RESULTS: Forty-one older adults participated. Seventy-one percent of surveys, 75% of blood pressure readings, and 81% of daily weight measurements were taken. Participants wore the watch monitor 77% of the overall 24/7 time requested. The weight scale had the highest usability rating in both groups. The groups did not otherwise differ on device usage. CONCLUSIONS: The findings indicate that a health monitoring system designed for older adults can and will be used for an extended period of time and may help older adults with chronic conditions reside longer in their own homes in partnership with the healthcare system.

Predicting Older Adults' Perceptions about a Computer System Designed for Seniors.

PURPOSE: Although computer technology may be particularly useful for older adults (e.g., for communication, information access), they have been slower adopters than their younger counterparts. Perceptions about computers such as perceived usefulness and perceived ease of use can pose barriers to acceptance and universal access [1]. Therefore, understanding the precursors to these perceptions for older adult non-computer users may provide insight into the reasons for their non-adoption. METHODS: We examined the relationship between perceived usefulness and perceived ease of use of a computer interface designed for older users and demographic, technology experience, cognitive abilities, personality, and attitudinal variables in a sample of 300 non-computer using adults between the ages of 64 and 98, selected for being at high risk for social isolation. RESULTS: The strongest correlates of perceived usefulness and perceived ease of use were: technology experience, personality dimensions of agreeableness and openness to experience, and attitudes. The emotional stability personality dimension was significantly correlated with perceived ease of use but not perceived usefulness. Hierarchical regression analysis revealed that attitudes (i.e., self-efficacy, comfort, interest) remained predictive of perceptions of usefulness and ease of use when technology experience and personality variables were accounted for. CONCLUSION: Given that attitudes are more malleable than other variables, such as demographic and cognitive abilities, these findings highlight the potential to increase technology acceptance through positive experiences, appropriate training, and educational campaigns about the benefits of computers and other technologies.

Dutch nurses' willingness to use home telehealth: implications for practice and education.

Home telehealth (HT) refers to the use of videoconferencing to provide care to patients remotely and can help older adults age in place. However, these technologies are unlikely to impact care unless health care providers are motivated to use them. Education may play a key role in increasing motivation to use and competence regarding HT. To help guide the development of nursing education to facilitate adoption and use, the current study examined predictors of Dutch nurses' willingness to use HT, based on a survey of 67 Dutch nurses with and 126 without HT experience. Nurses' willingness to use this technology was predicted by HT's (a) perceived usefulness to the client, (b) effort expectancy, (c) social influence, and (d) cost expectations. These observed relationships are anticipated to help with the development of effective educational programs to increase HT use and, therefore, improve older adults' quality of life. [Journal of Gerontological Nursing, 41(4), 47-56.].

Improving the safety of aging road users: a mini-review.

Older drivers are at greatest risk for injury or death as a result of a car crash. In this mini-review, we outline the normative age-related changes to perceptual, cognitive, and motor abilities that contribute to increased crash risk and decreased comfort with driving, and highlight specific driving scenarios and conditions that are particularly challenging for aging road users. Adopting a person-environment fit framework, we discuss how the roadway environment can be modified to better match the abilities of the aging driver. We also review evidence for the efficacy of training interventions that aim to change the abilities and strategies of the aging driver to better match the demands of the driving environment. Evidence suggests that specific changes to the roadway and driver training strategies can bring the abilities of the older driver back into alignment with the demands of the driving task. A focus on both approaches will help ensure the safety of all road users as the number of aging drivers greatly increases over the next few decades.

Prioritizing Technology Initiatives to Reduce Social Isolation and Loneliness Among Older Adults.

In their insightful commentary, Kokorelias et al. (2024) explore the potential of technology in supporting aging in the right place, addressing both opportunities and challenges from individual to societal levels. Our commentary specifically focuses on recent empirical evidence for technology's benefits in enhancing social connectivity and reducing loneliness for older adults, both with and without cognitive impairments. It emphasizes the need for a proper balance between the use of technology and face-to-face interactions and highlights the importance of addressing concerns related to privacy, cybersecurity and safety in this domain. In addition to the barriers outlined by Kokorelias et al. (2024), we discuss challenges related to the transfer of technology, the necessary steps required to ensure that technological interventions are effective beyond well-controlled studies and the responsibility of industries to design technology in such a way that innovations can benefit as many people as possible.

Development of the Japanese version of the Mobile Device Proficiency Questionnaire: A cross-sectional validation study.

AIM: In response to the growing popularity of mobile devices among older adults in Japan, this study aimed to establish a reliable and valid measure of mobile device proficiency by developing a Japanese version of the Mobile Device Proficiency Questionnaire (MDPQ-J) for the Japanese population. METHODS: To evaluate the reliability and validity of the MDPQ-J, we administered the questionnaire to 100 young or middle-aged participants (37.78 ± 13.90 years, 57.00% women), and 62 older participants (75.90 ± 6.01 years; 59.68% women). RESULTS: The MDPQ-J showed a high degree of internal consistency (Cronbach's α = 0.98). Moreover, MDPQ-J scores in older participants tended to be lower than those in young or middle-aged participants. In terms of validity, the MDPQ-J score of older participants was significantly associated with age (ρ = -0.31), the amount of time using a mobile device per day (ρ = 0.64), and the system usability scale (ρ = 0.39). Additionally, the MDPQ-J scores were significantly positively associated with the importance (ρ = 0.37), performance (ρ = 0.57), and satisfaction (ρ = 0.29) associated with daily mobile device use in older participants. CONCLUSIONS: The high reliability and validity of the MDPQ-J in the Japanese population highlight its utility in adapting mobile devices for older adults, which is crucial in an increasingly digital society. Further research should explore the mediating role of mobile device proficiency in various health-related outcomes. Geriatr Gerontol Int 2024; ••: ••-••.

The Benefits of Technology for Engaging Aging Adults: Findings From the PRISM 2.0 Trial.

Background and Objectives: Technology has potential for providing support for aging adults. This study evaluated the Personal Reminder Information and Social Management 2.0 (PRISM 2.0) software, in terms of enhancing social engagement and quality of life, and decreasing loneliness among older adults. Research Design and Methods: The randomized field trial conducted in diverse living contexts (rural locations, senior housing, and assisted living communities [ALC]). Two hundred and forty-five adults, aged 64 to 99 years, were randomly assigned to the PRISM 2.0 (integrated software system designed for aging through an iterative design process) or a Standard Tablet (without PRISM) Control condition, where participants received the same amount of contact and training as those in the PRISM 2.0 condition. Primary outcomes included measures of loneliness, social support, social connectedness, and quality of life. Secondary outcomes included measures of social isolation, mobile device proficiency, and technology readiness. Data were collected at baseline and 6 and 9 months postrandomization. This article focuses on the 6-month outcomes due to coronavirus disease 2019-related data challenges at 9 months. Results: Contrary to our hypothesis, participants in rural locations and senior housing in both conditions reported less loneliness and social isolation, and greater social support and quality of life at 6 months, and an increase in mobile device proficiency. Participants in the ALCs in both conditions also evidenced an increase in mobile device proficiency. Improvements in quality of life and health-related quality of life were associated with decreases in loneliness. Discussion and Implications: This study provides compelling evidence about the benefits of technology for older adults in terms of enhancing social outcomes and quality of life. However, the findings also underscore that for technology applications to be successful, they need to be adapted to the abilities and needs of the user group and instructional support needs to be provided. Clinical Trials Registration #: NCT03116399.

Predicting adherence to gamified cognitive training using early phase game performance data: Towards a just-in-time adherence promotion strategy.

BACKGROUND AND OBJECTIVES: This study aims to develop a machine learning-based approach to predict adherence to gamified cognitive training using a variety of baseline measures (demographic, attitudinal, and cognitive abilities) as well as game performance data. We aimed to: (1) identify the cognitive games with the strongest adherence prediction and their key performance indicators; (2) compare baseline characteristics and game performance indicators for adherence prediction, and (3) test ensemble models that use baseline characteristics and game performance data to predict adherence over ten weeks. RESEARCH DESIGN AND METHOD: Using machine learning algorithms including logistic regression, ridge regression, support vector machines, classification trees, and random forests, we predicted adherence from weeks 3 to 12. Predictors included game performance metrics in the first two weeks and baseline measures. These models' robustness and generalizability were tested through five-fold cross-validation. RESULTS: The findings indicated that game performance measures were superior to baseline characteristics in predicting adherence. Notably, the games "Supply Run," "Ante Up," and "Sentry Duty" emerged as significant adherence predictors. Key performance indicators included the highest level achieved, total game sessions played, and overall gameplay proportion. A notable finding was the negative correlation between initial high achievement levels and sustained adherence, suggesting that maintaining a balanced difficulty level is crucial for long-term engagement. Conversely, a positive correlation between the number of sessions played and adherence highlighted the importance of early active involvement. DISCUSSION AND IMPLICATIONS: The insights from this research inform just-in-time strategies to promote adherence to cognitive training programs, catering to the needs and abilities of the aging population. It also underscores the potential of tailored, gamified interventions to foster long-term adherence to cognitive training.

Terms of Engagement: Understanding the Motivations, Preferences, and Attitudes of Older Adults Toward Mobile Cognitive Assessment and Training.

BACKGROUND AND OBJECTIVES: The future of cognitive assessment is likely to involve mobile applications for smartphones and tablets; cognitive training is also often delivered in these formats. Unfortunately, low adherence to these programs can hinder efforts at the early detection of cognitive decline and interfere with examining cognitive training efficacy in clinical trials. We explored factors that increase adherence to these programs among older adults. RESEARCH DESIGN AND METHODS: Focus groups were conducted with older adults (N = 21) and a younger adult comparison group (N = 21). Data were processed using reflexive thematic analysis with an inductive, bottom-up approach. RESULTS: Three primary themes related to adherence were developed from the focus group data. Switches of engagement reflects factors that must be present; without them, engagement is unlikely. Dials of engagement reflects a cost-benefit analysis that users undergo, the outcome of which determines whether a person will be more or less likely to engage. Bracers of engagement reflects factors that nudge users toward engagement by minimizing barriers associated with the other themes. Older adults in general were more sensitive to opportunity costs, preferred more cooperative interactions, and were more likely to mention technology barriers. DISCUSSION AND IMPLICATIONS: Our results are important for informing the design of mobile cognitive assessment and training apps for older adults. These themes provide guidance about ways apps could be modified to increase engagement and adherence, which in turn can more effectively facilitate the early detection of cognitive impairment and the evaluation of cognitive training efficacy.

Adherence Promotion With Tailored Motivational Messages: Proof of Concept and Message Preferences in Older Adults.

This study examined the feasibility of using tailored text messages to promote adherence to longitudinal protocols and determined what facets of text message tone influence motivation. Forty-three older adults (Mage = 73.21, SD = 5.37) were recruited to engage in video-game-based cognitive training for 10 consecutive days. Participants received encouraging text messages each morning that matched their highest or lowest ranking reasons for participating in the study, after which they rated how effective each message was in motivating them to play the games that day. After 10 days, participants rated all possible messages and participated in semi-structured interviews to elicit their preferences for these messages. Results showed that messages matching participants' reasons for participating were more motivating than mismatched messages. Further, participants preferred messages that were personalized (i.e., use second person voice) and in formal tones. Messages consistent with these preferences were also rated as more motivating. These findings establish the feasibility of using message tailoring to promote adherence to longitudinal protocols and the relevance of tailoring messages to be personal and formal.

Predicting Older Adults' Continued Computer Use After Initial Adoption.

Background and Objectives: Sustained computer and internet use have the potential to help older adults in various aspects of their lives, making predicting sustained use a critical goal. However, some factors related to adoption and use (e.g., computer attitudes) change over time and with experience. To understand these dynamics, the current study modeled changes in constructs related to computer use after initial computer adoption and examined whether these changes predict continued use. Research Design and Methods: We used data from the computer arm (N = 150, MAge = 76.15) of a 12-month field trial examining the potential benefits of computer use in older adults. Individual differences identified in the technology acceptance literature (perceived usefulness, ease of use, computer interest, computer self-efficacy, computer anxiety, quality of life, social isolation, and social support) were measured before (baseline), during (Month 6), and after the intervention (post-test). Univariate and bivariate latent change score models examined changes in each predictor and their potential causal relationship with use. Results: Results demonstrated large interindividual differences in the change patterns of individual difference factors examined. Changes in perceived usefulness, perceived ease of use, computer interest, computer self-efficacy, and computer anxiety were correlated with but not predictive of change in use. Discussion and Implications: Our findings demonstrate the limitation of popular constructs in technology acceptance literature in predicting continued use and point out important gaps in knowledge to be targeted in future investigations.

Comparing the effectiveness of two theory-based strategies to promote cognitive training adherence.

This study compared the effectiveness of two theory-based strategies to promote cognitive training adherence among older adults (Mage = 70 years, SD = 4.42, range = 64-84). Strategies incorporated either (a) elements of implementation intention formation or (b) positive message framing, both of which have been found to promote adherence to health behaviors in other domains. Participants (N = 120) were asked to engage in technology-based cognitive training at home comprised of seven gamified neuropsychological tasks. In Phase 1 (structured), participants were provided a schedule that required engagement in 1 hr of cognitive training 5 days each week over 2 months. In Phase 2 (unstructured), participants were instructed to engage with the intervention as much as they desired for 1 month. Contrary to expectations, neither the implementation intention nor positive message framing produced greater adherence relative to control as measured by the total number of training sessions completed in each phase. However, exploratory analysis indicated a greater likelihood of intervention engagement for participants assigned to the implementation intention condition on many days of the intervention, though the trajectory of engagement decline was similar for all three groups. Measures of cognition, attitudes/personality, and technology proficiency also did not predict adherence over either phase. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Understanding Barriers to the Collection of Mobile and Wearable Device Data to Monitor Health and Cognition in Older Adults: A Scoping Review.

Advances in technology have made continuous/remote monitoring of digital health data possible, which can enable the early detection and treatment of age-related cognitive and health declines. Using Arksey and O'Malley's methodology, this scoping review evaluated potential barriers to the collection of mobile and wearable device data to monitor health and cognitive status in older adults with and without mild cognitive impairment (MCI). Selected articles were US based and focused on experienced or perceived barriers to the collection of mobile and wearable device data by adults 55 years of age or older. Fourteen articles met the study's inclusion criteria. Identified themes included barriers related to usability, users' prior experiences with health technologies, first and second level digital divide, aesthetics, comfort, adherence, and attitudinal barriers. Addressing these barriers will be crucial for effective digital data-collection among older adults to achieve goals of improving quality of life and reducing care costs.

Using Immersive Virtual Reality to Enhance Social Interaction Among Older Adults: A Cross-Site Investigation.

Background and Objectives: Virtual reality (VR) applications are increasingly being targeted toward older adults as a means to maintain physical and cognitive skills and to connect with others, especially during the coronavirus disease 2019 era. Our knowledge about how older adults interact with VR is limited, however, since this is an emerging area and the related research literature is still rather slim. The current study focused specifically on older adults' reactions to a social-VR environment, examining participant's views about the possibility of meaningful interactions in this format, the impacts of social-VR immersion on mood and attitude, and features of the VR environment that affected these outcomes. Research Design and Methods: The researchers designed a novel social-VR environment with features intended to prompt conversation and collaborative problem-solving among older adults. Participants were recruited from 3 diverse geographic locations (Tallahassee, FL; Ithaca, NY; and New York City, NY), and were randomly assigned to a partner from one of the other sites for social-VR interaction. The sample consisted of 36 individuals aged 60 and older. Results: Reactions to the social VR were quite positive. Older adults reported high levels of engagement in the environment and perceived the social VR to be enjoyable and usable. Perceived spatial presence was found to be a central driver of positive outcomes. A majority of the participants indicated a willingness to reconnect with their VR partner in the future. The data also identified important areas for improvement that were of concern to older adults, such as the use of more realistic avatars, larger controllers more suited to aging hands, and more time for training/familiarization. Discussion and Implications: Overall, these findings suggest that VR can be an effective format for social engagement among older adults.

Effects of training strategies implemented in a complex videogame on functional connectivity of attentional networks.

We used the Space Fortress videogame, originally developed by cognitive psychologists to study skill acquisition, as a platform to examine learning-induced plasticity of interacting brain networks. Novice videogame players learned Space Fortress using one of two training strategies: (a) focus on all aspects of the game during learning (fixed priority), or (b) focus on improving separate game components in the context of the whole game (variable priority). Participants were scanned during game play using functional magnetic resonance imaging (fMRI), both before and after 20 h of training. As expected, variable priority training enhanced learning, particularly for individuals who initially performed poorly. Functional connectivity analysis revealed changes in brain network interaction reflective of more flexible skill learning and retrieval with variable priority training, compared to procedural learning and skill implementation with fixed priority training. These results provide the first evidence for differences in the interaction of large-scale brain networks when learning with different training strategies. Our approach and findings also provide a foundation for exploring the brain plasticity involved in transfer of trained abilities to novel real-world tasks such as driving, sport, or neurorehabilitation.

A Grand Challenge for Psychology: Reducing the Age-related Digital Divide.

World-wide population aging and rapid diffusion of digital technology have converged to produce an age-related digital divide in technology adoption, as seen in use of the internet and ownership of smartphones. Given the centrality of these technologies for full participation in modern society, reducing that gap is an important challenge for psychologists. We outline more and less malleable factors associated with technology adoption. We argue that interventions that can change both the aging user and the design of products will be necessary. Adaptive technology systems that incorporate artificial intelligence and extended reality represent promising new approaches to reducing the age-related digital divide.

Does Computer Use Improve Older Adults' Cognitive Functioning? Evidence From the Personal Reminder Information and Social Management Trial.

BACKGROUND AND OBJECTIVES: Numerous longitudinal studies suggest that technology use in late adulthood is associated with cognitive benefits. Using data from a randomized controlled trial, the current study examined whether computer use improves cognition in older adults with little to no previous computer experience. RESEARCH DESIGN AND METHODS: This study used data from the Personal Reminder Information and Social Management (PRISM) trial. Community-dwelling older adults with little previous computer experience (MAge = 76.15) were randomly assigned to learn and use a computer (the PRISM system, n = 150) or interact with parallel content delivered in a nondigital format (paper binder, n = 150) for 12 months. Objective and subjective cognitive outcomes were measured before (pretest) and after the intervention (posttest). Latent change score models and Bayesian analysis of variances were used to examine cognitive change at the ability and individual measure level. RESULTS: Computer training and use for 12 months did not lead to cognitive improvements at the ability level. Strong evidence against cognitive benefits at the individual measure level was also observed. DISCUSSION AND IMPLICATIONS: Casual computer use does not provide enough cognitive stimulation to improve cognition in late adulthood. Cognitive benefits observed in longitudinal studies may be mediated by other factors or influenced by confounding variables.