A Planning System Based on Markov Decision Processes to Guide People With Dementia Through Activities of Daily Living

A reinforcement learning-based optimal control approach for managing an elective surgery backlog after pandemic disruption

Contagious disease pandemics, such as COVID-19, can cause hospitals around the world to delay nonemergent elective surgeries, which results in a large surgery backlog. To develop an operational solution for providing patients timely surgical care with limited health care resources, this study proposes a stochastic control process-based method that helps hospitals make operational recovery plans to clear their surgery backlog and restore surgical activity safely. The elective surgery backlog recovery process is modeled by a general discrete-time queueing network system, which is formulated by a Markov decision process. A scheduling optimization algorithm based on the piecewise decaying [Formula: see text]-greedy reinforcement learning algorithm is proposed to make dynamic daily surgery scheduling plans considering newly arrived patients, waiting time and clinical urgency. The proposed method is tested through a set of simulated dataset, and implemented on an elective surgery backlog that built up in one large general hospital in China after the outbreak of COVID-19. The results show that, compared with the current policy, the proposed method can effectively and rapidly clear the surgery backlog caused by a pandemic while ensuring that all patients receive timely surgical care. These results encourage the wider adoption of the proposed method to manage surgery scheduling during all phases of a public health crisis.

Reinforcement learning for intelligent healthcare applications: A survey

Discovering new treatments and personalizing existing ones is one of the major goals of modern clinical research. In the last decade, Artificial Intelligence (AI) has enabled the realization of advanced intelligent systems able to learn about clinical treatments and discover new medical knowledge from the huge amount of data collected. Reinforcement Learning (RL), which is a branch of Machine Learning (ML), has received significant attention in the medical community since it has the potentiality to support the development of personalized treatments in accordance with the more general precision medicine vision. This report presents a review of the role of RL in healthcare by investigating past work, and highlighting any limitations and possible future contributions.

Artificial Intelligence for Caregivers of Persons With Alzheimer's Disease and Related Dementias: Systematic Literature Review

BACKGROUND

Artificial intelligence (AI) has great potential for improving the care of persons with Alzheimer's disease and related dementias (ADRD) and the quality of life of their family caregivers. To date, however, systematic review of the literature on the impact of AI on ADRD management has been lacking.

OBJECTIVE

This paper aims to (1) identify and examine literature on AI that provides information to facilitate ADRD management by caregivers of individuals diagnosed with ADRD and (2) identify gaps in the literature that suggest future directions for research.

METHODS

Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines for conducting systematic literature reviews, during August and September 2019, we performed 3 rounds of selection. First, we searched predetermined keywords in PubMed, Cumulative Index to Nursing and Allied Health Literature Plus with Full Text, PsycINFO, IEEE Xplore Digital Library, and the ACM Digital Library. This step generated 113 nonduplicate results. Next, we screened the titles and abstracts of the 113 papers according to inclusion and exclusion criteria, after which 52 papers were excluded and 61 remained. Finally, we screened the full text of the remaining papers to ensure that they met the inclusion or exclusion criteria; 31 papers were excluded, leaving a final sample of 30 papers for analysis.

RESULTS

Of the 30 papers, 20 reported studies that focused on using AI to assist in activities of daily living. A limited number of specific daily activities were targeted. The studies' aims suggested three major purposes: (1) to test the feasibility, usability, or perceptions of prototype AI technology; (2) to generate preliminary data on the technology's performance (primarily accuracy in detecting target events, such as falls); and (3) to understand user needs and preferences for the design and functionality of to-be-developed technology. The majority of the studies were qualitative, with interviews, focus groups, and observation being their most common methods. Cross-sectional surveys were also common, but with small convenience samples. Sample sizes ranged from 6 to 106, with the vast majority on the low end. The majority of the studies were descriptive, exploratory, and lacking theoretical guidance. Many studies reported positive outcomes in favor of their AI technology's feasibility and satisfaction; some studies reported mixed results on these measures. Performance of the technology varied widely across tasks.

CONCLUSIONS

These findings call for more systematic designs and evaluations of the feasibility and efficacy of AI-based interventions for caregivers of people with ADRD. These gaps in the research would be best addressed through interdisciplinary collaboration, incorporating complementary expertise from the health sciences and computer science/engineering-related fields.

An Acoustic-Based Smart Home System for People Suffering from Dementia

Aging-in-place can reduce the progress of dementia syndrome and improve the quality of life of the sufferers and their families. Taking into consideration the fact that numerous neurological research results suggest the use of sound as a stimulus for empowering the memory of the sufferer, an innovative information home support system for people suffering from dementia is proposed. The innovation of the proposed system is found in its application, that is to integrate a home system for assisting with person recognition via a sound-based memory aid service. Furthermore, the system addresses the needs of people suffering from dementia to recognize their familiars and have better interaction and collaboration, without the need for training. The system offers a ubiquitous recognition system, using smart devices like smart-phones or smart-wristbands. When a familiar person is detected in the house, then a sound is reproduced on the smart speakers, in order to stimulate the sufferer’s memory. The system identified all users and reproduced the appropriate sound in 100% of the cases. To the best of the authors’ knowledge, this is the first system of its kind for assisting person recognition via sound ever reported in the literature.

Strategies to Improve Activity Recognition Based on Skeletal Tracking: Applying Restrictions Regarding Body Parts and Similarity Boundaries

This paper aims to improve activity recognition systems based on skeletal tracking through the study of two different strategies (and its combination): (a) specialized body parts analysis and (b) stricter restrictions for the most easily detectable activities. The study was performed using the Extended Body-Angles Algorithm, which is able to analyze activities using only a single key sample. This system allows to select, for each considered activity, which are its relevant joints, which makes it possible to monitor the body of the user selecting only a subset of the same. But this feature of the system has both advantages and disadvantages. As a consequence, in the past we had some difficulties with the recognition of activities that only have a small subset of the joints of the body as relevant. The goal of this work, therefore, is to analyze the effect produced by the application of several strategies on the results of an activity recognition system based on skeletal tracking joint oriented devices. Strategies that we applied with the purpose of improve the recognition rates of the activities with a small subset of relevant joints. Through the results of this work, we aim to give the scientific community some first indications about which considered strategy is better.

Learning Activity Predictors from Sensor Data: Algorithms, Evaluation, and Applications

Recent progress in Internet of Things (IoT) platforms has allowed us to collect large amounts of sensing data. However, there are significant challenges in converting this large-scale sensing data into decisions for real-world applications. Motivated by applications like health monitoring and intervention and home automation we consider a novel problem called Activity Prediction, where the goal is to predict future activity occurrence times from sensor data. In this paper, we make three main contributions. First, we formulate and solve the activity prediction problem in the framework of imitation learning and reduce it to a simple regression learning problem. This approach allows us to leverage powerful regression learners that can reason about the relational structure of the problem with negligible computational overhead. Second, we present several metrics to evaluate activity predictors in the context of real-world applications. Third, we evaluate our approach using real sensor data collected from 24 smart home testbeds. We also embed the learned predictor into a mobile-device-based activity prompter and evaluate the app for 9 participants living in smart homes. Our results indicate that our activity predictor performs better than the baseline methods, and offers a simple approach for predicting activities from sensor data.

A Review of Smart House Analysis Methods for Assisting Older People Living Alone

Smart Houses are a prominent field of research referring to environments adapted to assist people in their everyday life. Older people and people with disabilities would benefit the most from the use of Smart Houses because they provide the opportunity for them to stay in their home for as long as possible. In this review, the developments achieved in the field of Smart Houses for the last 16 years are described. The concept of Smart Houses, the most used analysis methods, and current challenges in Smart Houses are presented. A brief introduction of the analysis methods is given, and their implementation is also reported.

One-Class Classification-Based Real-Time Activity Error Detection in Smart Homes

Caring for individuals with dementia is frequently associated with extreme physical and emotional stress, which often leads to depression. Smart home technology and advances in machine learning techniques can provide innovative solutions to reduce caregiver burden. One key service that caregivers provide is prompting individuals with memory limitations to initiate and complete daily activities. We hypothesize that sensor technologies combined with machine learning techniques can automate the process of providing reminder-based interventions. The first step towards automated interventions is to detect when an individual faces difficulty with activities. We propose machine learning approaches based on one-class classification that learn normal activity patterns. When we apply these classifiers to activity patterns that were not seen before, the classifiers are able to detect activity errors, which represent potential prompt situations. We validate our approaches on smart home sensor data obtained from older adult participants, some of whom faced difficulties performing routine activities and thus committed errors.

Principles for fostering the transdisciplinary development of assistive technologies

Developing useful and usable assistive technologies often presents complex (or "wicked") challenges that require input from multiple disciplines and sectors. Transdisciplinary collaboration can enable holistic understanding of challenges that may lead to innovative, impactful and transformative solutions. This paper presents generalised principles that are intended to foster transdisciplinary assistive technology development. The paper introduces the area of assistive technology design before discussing general aspects of transdisciplinary collaboration followed by an overview of relevant concepts, including approaches, methodologies and frameworks for conducting and evaluating transdisciplinary working and assistive technology design. The principles for transdisciplinary development of assistive technologies are presented and applied post hoc to the COACH project, an ambient-assisted living technology for guiding completion of activities of daily living by older adults with dementia as an illustrative example. Future work includes the refinement and validation of these principles through their application to real-world transdisciplinary assistive technology projects. Implications for rehabilitation Transdisciplinarity encourages a focus on real world 'wicked' problems. A transdisciplinary approach involves transcending disciplinary boundaries and collaborating with interprofessional and community partners (including the technology's intended users) on a shared problem. Transdisciplinarity fosters new ways of thinking about and doing research, development, and implementation, expanding the scope, applicability, and commercial viability of assistive technologies.

The potential impact of intelligent systems for mobile health self-management support: Monte Carlo simulations of text message support for medication adherence

BACKGROUND

Mobile health (mHealth) services cannot easily adapt to users' unique needs.

PURPOSE

We used simulations of text messaging (SMS) for improving medication adherence to demonstrate benefits of interventions using reinforcement learning (RL).

METHODS

We used Monte Carlo simulations to estimate the relative impact of an intervention using RL to adapt SMS adherence support messages in order to more effectively address each non-adherent patient's adherence barriers, e.g., forgetfulness versus side effect concerns. SMS messages were assumed to improve adherence only when they matched the barriers for that patient. Baseline adherence and the impact of matching messages were estimated from literature review. RL-SMS was compared in common scenarios to simple reminders, random messages, and standard tailoring.

RESULTS

RL could produce a 5-14% absolute improvement in adherence compared to current approaches. When adherence barriers are not accurately reported, RL can recognize which barriers are relevant for which patients. When barriers change, RL can adjust message targeting. RL can detect when messages are sent too frequently causing burnout.

CONCLUSIONS

RL systems could make mHealth services more effective.

Prototype Development of a Responsive Emotive Sensing System (DRESS) to aid older persons with dementia to dress independently

BACKGROUND

Prior research has critiqued the lack of attention to the stressors associated with dementia related dressing issues, stigmatizing patient clothing, and wearable technology challenges. This paper describes the conceptual development and feasibility testing of an innovative 'smart dresser' context aware affective system (DRESS) to enable dressing by people with moderate memory loss through individualized audio and visual task prompting in real time.

METHODS

Mixed method feasibility study involving qualitative focus groups with 25 Alzheimer's family caregivers experiencing dressing difficulties to iteratively inform system design and a quantitative usability trial with 10 healthy subjects in a controlled laboratory setting to assess validity of technical operations.

RESULTS

Caregivers voiced the need for tangible dressing assistance to reduce their frustration from time spent in repetitive cueing and power struggles over dressing. They contributed 6 changes that influenced the prototype development, most notably adding a dresser top iPad to mimic a familiar 'TV screen' for the audio and visual cueing. DRESS demonstrated promising overall functionality, however the validity of identification of dressing status ranged from 0% for the correct pants dressing to 100% for all shirts dressing scenarios. Adjustments were made to the detection components of the system raising the accuracy of detection of all acted dressing scenarios for pants from 50% to 82%.

CONCLUSIONS

Findings demonstrate family caregiver acceptability of the proposed system, the successful interoperability of the built system's components, and the system's ability to interpret correct and incorrect dressing actions in controlled laboratory simulations. Future research will advance the system to the alpha stage and subsequent testing with end users in real world settings.

Interdisciplinary development of manual and automated product usability assessments for older adults with dementia: lessons learned

The changes in cognitive abilities that accompany dementia can make it difficult to use everyday products that are required to complete activities of daily living. Products that are inherently more usable for people with dementia could facilitate independent activity completion, thus reducing the need for caregiver assistance. The objectives of this research were to: (1) gain an understanding of how water tap design impacted tap usability and (2) create an automated computerized tool that could assess tap usability. 27 older adults, who ranged from cognitively intact to advanced dementia, completed 1309 trials on five tap designs. Data were manually analyzed to investigate tap usability as well as used to develop an automated usability analysis tool. Researchers collaborated to modify existing techniques and to create novel ones to accomplish both goals. This paper presents lessons learned through the course of this research, which could be applicable in the development of other usability studies, automated vision-based assessments and the development of assistive technologies for cognitively impaired older adults. Collaborative interdisciplinary teamwork, which included older adult with dementia participants, was key to enabling innovative advances that achieved the projects' research goals. Implications for Rehabilitation Products that are implicitly familiar and usable by older adults could foster independent activity completion, potentially reducing reliance on a caregiver. The computer-based automated tool can significantly reduce the time and effort required to perform product usability analysis, making this type of analysis more feasible. Interdisciplinary collaboration can result in a more holistic understanding of assistive technology research challenges and enable innovative solutions.

Nugent C, Scotney B. A duration-based online reminder system

Purpose

– The purpose of this paper is to discuss an online sensor-based support system which the authors believe can be useful in such scenarios. Persons with a cognitive impairment, such as those with Alzheimer’s disease, suffer from deficiencies in cognitive skills which reduce their independence; such patients can benefit from the provision of further assistance such as reminders for carrying out instrumental activities of daily living (IADLs).

Design/methodology/approach

– The system proposed processes data from a network of sensors that have the capability of sensing user interactions and on-going IADLs in the living environment itself. A probabilistic learning model is built that computes joint probability distributions over different activities representing users’ behavioural patterns in performing activities. This probability model can underpin an intervention framework that prompts the user with the next step in the IADL when inactivity is being observed. This prompt for the next step is inferred from the conditional probability taken into consideration the IADL steps that have already been completed, in addition to contextual information relating to the time of day and the amount of time already spent on the activity. The originality of the work lies in combining partially observed sensor sequences and duration data associated with the IADLs. The prediction of the next step is then adjusted as further steps are completed and more time is spent towards the completion of the activity, thus updating the confidence that the prediction is correct. A reminder is only issued when there has been sufficient inactivity on the part of the patient and the confidence is high that the prediction is correct.

Findings

– The results of this study verify that by including duration information the prediction accuracy of the model is increased and the confidence level for the next step in the IADL is also increased. As such, there is approximately a 10 per cent rise in the prediction performance in the case of single sensor activation in comparison to an alternative approach which did not consider activity durations.

Practical implications

– Duration information to a certain extent has been widely ignored by activity recognition researchers and has received a very limited application within smart environments.

Originality/value

– This study concludes that incorporating progressive duration information into partially observed sensor sequences of IADLs has the potential to increase performance of a reminder system for patients with a cognitive impairment, such as Alzheimer’s disease.

Nugent C, Scotney B. A duration-based online reminder system

Purpose

– This paper aims to discuss an online sensor-based support system which is believed to be useful for persons with a cognitive impairment, such as those with Alzheimer’s disease, suffering from deficiencies in cognitive skills which reduce their independence. Such patients can benefit from the provision of further assistance such as reminders for carrying out instrumental activities of daily living (iADLs).

Design/methodology/approach

– The system proposed processes data from a network of sensors that have the capability of sensing user interactions and ongoing iADLs in the living environment itself. A probabilistic learning model is built that computes joint probability distributions over different activities representing users’ behavioural patterns in performing activities. This probability model can underpin an intervention framework that prompts the user with the next step in the iADL when inactivity is being observed. This prompt for the next step is inferred from the conditional probability, taking into consideration the iADL steps that have already been completed, in addition to contextual information relating to the time of day and the amount of time already spent on the activity. The originality of the work lies in combining partially observed sensor sequences and duration data associated with the iADLs. The prediction of the next step is then adjusted as further steps are completed and more time is spent towards the completion of the activity; thus, updating the confidence that the prediction is correct. A reminder is only issued when there has been sufficient inactivity on the part of the patient and the confidence is high that the prediction is correct.

Findings

– The results verify that by including duration information, the prediction accuracy of the model is increased, and the confidence level for the next step in the iADL is also increased. As such, there is approximately a 10 per cent rise in the prediction performance in the case of single-sensor activation in comparison to an alternative approach which did not consider activity durations. Thus, it is concluded that incorporating progressive duration information into partially observed sensor sequences of iADLs has the potential to increase performance of a reminder system for patients with a cognitive impairment, such as Alzheimer’s disease.

Originality/value

– Activity duration information can be a potential feature in measuring the performance of a user and distinguishing different activities. The results verify that by including duration information, the prediction accuracy of the model is increased, and the confidence level for the next step in the activity is also increased. The use of duration information in online prediction of activities can also be associated to monitoring the deterioration in cognitive abilities and in making a decision about the level of assistance required. Such improvements have significance in building more accurate reminder systems that precisely predict activities and assist its users, thus, improving the overall support provided for living independently.

A technology roadmap of assistive technologies for dementia care in Japan

The number of elderly people in Japan is growing, which raises the issue of dementia, as the probability of becoming cognitively impaired increases with age. There is an increasing need for caregivers, who are well-trained, experienced and can pay special attention to the needs of people with dementia. Technology can play an important role in helping such people and their caregivers. A lack of mutual understanding between caregivers and researchers regarding the appropriate uses of assistive technologies is another problem. A vision of person-centred care based on the use of information and communication technology to maintain residents’ autonomy and continuity in their lives is presented. Based on this vision, a roadmap and a list of challenges to realizing assistive technologies have been developed. The roadmap facilitates mutual understanding between caregivers and researchers, resulting in appropriate technologies to enhance the quality of life of people with dementia.

Self-regulated music stimulation for persons with Alzheimer's disease: impact assessment and social validation

OBJECTIVE

To assess the impact and the social rating of an active music condition (in which 10 patients with Alzheimer's disease regulated their music input) vs. a passive music condition.

METHOD

In the active condition, the patients used a simple hand response and a microswitch to activate music stimulation periods. In the passive condition, music stimulation was prearranged and continued through the sessions. The active and passive stimulation sessions were preceded and followed by control (non-stimulation) sessions.

RESULTS

The active condition sessions showed an increase in the patients' indices of positive participation (e.g., singing or music-related movements, and smiles) similar to that observed in the passive condition sessions. Social raters (140 psychology students) favored the active condition on a six-item questionnaire dealing, among others, with conditions' suitability, respect of patients' dignity and independence, and practicality.

CONCLUSION

An active music stimulation condition can be viable, effective, and socially preferable.

Examining the impact of familiarity on faucet usability for older adults with dementia

BACKGROUND

Changes in cognition caused by dementia can significantly alter how a person perceives familiarity, impacting the recognition and usability of everyday products. A person who is unable to use products cannot autonomously complete associated activities, resulting in increased dependence on a caregiver and potential move to assisted living facilities. The research presented in this paper hypothesised that products that are more familiar will result in better usability for older adults with dementia. Better product usability could, in turn, potentially support independence and autonomy.

METHODS

This research investigated the impact of familiarity on the use of five faucet designs during 1309 handwashing trials by 27 older adults, who ranged from cognitively intact to the advanced (severe) stages of dementia. Human factors methods were used to collect empirical and self-reported data to gauge faucets' usability. Participants' data were grouped according to cognition (i.e., no/mild, moderate, or severe dementia). Logistic regression, ranking by odds, and Wald tests of odds ratios were used to compare performance of the three groups on the different faucets. Qualitative data were used in the interpretation of quantitative results.

RESULTS

Results indicated that more familiar faucets correlated with lower levels of assistance from a caregiver, fewer operational errors, and greater levels of operator satisfaction. Aspects such as the ability to control water temperature and flow as well as pleasing aesthetics appeared to positively impact participants' acceptance of a faucet. The dual lever design achieved the best overall usability.

CONCLUSIONS

While work must be done to expand these findings to other products and tasks, this research provides evidence that familiarity plays a substantial role in product usability for older adults that appears to become more influential as dementia progresses. The methods used in this research could be adapted to analyse usability for other products by older adults with dementia.

Video prompting versus other instruction strategies for persons with Alzheimer's disease

BACKGROUND/AIM

Two studies assessed the effectiveness of video prompting as a strategy to support persons with mild and moderate Alzheimer's disease in performing daily activities.

METHODS

In study I, video prompting was compared to an existing strategy relying on verbal instructions. In study II, video prompting was compared to another existing strategy relying on static pictorial cues. Video prompting and the other strategies were counterbalanced across tasks and participants and compared within alternating treatments designs.

RESULTS

Video prompting was effective in all participants. Similarly effective were the other 2 strategies, and only occasional differences between the strategies were reported. Two social validation assessments showed that university psychology students and graduates rated the patients' performance with video prompting more favorably than their performance with the other strategies.

CONCLUSION

Video prompting may be considered a valuable alternative to the other strategies to support daily activities in persons with Alzheimer's disease.

Ambient Activity Recognition in Smart Environments for Cognitive Assistance

In this paper, the authors investigate the challenging key issues that emerge from research in the field of ambient intelligence in smart environments, under the context of activity recognition. The authors clearly describe the specific functional needs inherent in cognitive assistance for effective activity recognition, and then the authors present the fundamental research that addresses this problem in such a context. This paper is more of a survey and an analysis of existing works that have been studied for potential integration into our laboratories, rather than a focused evaluation report. The authors’ objective is to identify gaps in the capabilities of current techniques and to suggest the most productive lines of research to address this complex issue. As such, the contribution is of both theoretical and practical significance.

People, sensors, decisions

The ratio of healthcare professionals to care recipients is dropping at an alarming rate, particularly for the older population. It is estimated that the number of persons with Alzheimer's disease, for example, will top 100 million worldwide by the year 2050 [Alzheimer's Disease International 2009]. It will become harder and harder to provide needed health services to this population of older adults. Further, patients are becoming more aware and involved in their own healthcare decisions. This is creating a void in which technology has an increasingly important role to play as a tool to connect providers with recipients. Examples of interactive technologies range from telecare for remote regions to computer games promoting fitness in the home. Currently, such technologies are developed for specific applications and are difficult to modify to suit individual user needs. The future potential economic and social impact of technology in the healthcare field therefore lies in our ability to make intelligent devices that are customizable by healthcare professionals and their clients, that are adaptive to users over time, and that generalize across tasks and environments.

A wide application area for technology in healthcare is for assistance and monitoring in the home. As the population ages, it becomes increasingly dependent on chronic healthcare, such as assistance for tasks of everyday life (washing, cooking, dressing), medication taking, nutrition, and fitness. This article will present a summary of work over the past decade on the development of intelligent systems that provide assistance to persons with cognitive disabilities. These systems are unique in that they are all built using a common framework, a decision-theoretic model for general-purpose assistance in the home. In this article, we will show how this type of general model can be applied to a range of assistance tasks, including prompting for activities of daily living, assistance for art therapists, and stroke rehabilitation. This model is a Partially Observable Markov Decision Process (POMDP) that can be customized by end-users, that can integrate complex sensor information, and that can adapt over time. These three characteristics of the POMDP model will allow for increasing uptake and long-term efficiency and robustness of technology for assistance.

Technology-aided pictorial cues to support the performance of daily activities by persons with moderate Alzheimer's disease

We developed a technology-aided intervention strategy relying on pictorial cues alone or in combination with verbal instructions and assessed these two versions of the strategy with three persons with moderate Alzheimer's disease. In Section I of the study, the strategy version with pictorial cues plus verbal instructions was compared with an existing technology-based strategy with verbal instructions. Each strategy was used with one specific activity. In Section II of the study, the strategy version with pictorial cues alone was compared with the aforementioned strategy with verbal instructions. Again, each strategy was used with one activity. Both strategy versions were effective with all three participants. The percentages of correct activity performance observed with those versions increased to above 90, and were comparable with those obtained with the existing verbal instructions strategy. A social validation assessment of the version with pictorial cues alone and the existing strategy with verbal instructions (employing university psychology students as raters) showed differences in favor of the latter strategy in terms of practicality and in favor of the former in terms of respect of participants' dignity. The implications of the findings were discussed.

Application of cognitive rehabilitation theory to the development of smart prompting technologies

Older adults with cognitive impairments often have difficulty performing instrumental activities of daily living (IADLs). Prompting technologies have gained popularity over the last decade and have the potential to assist these individuals with IADLs in order to live independently. Although prompting techniques are routinely used by caregivers and health care providers to aid individuals with cognitive impairment in maintaining their independence with everyday activities, there is no clear consensus or gold standard regarding prompt content, method of instruction, timing of delivery, or interface of prompt delivery in the gerontology or technology literatures. In this paper, we demonstrate how cognitive rehabilitation principles can inform and advance the development of more effective assistive prompting technologies that could be employed in smart environments. We first describe cognitive rehabilitation theory (CRT) and show how it provides a useful theoretical foundation for guiding the development of assistive technologies for IADL completion. We then use the CRT framework to critically review existing smart prompting technologies to answer questions that will be integral to advancing development of effective smart prompting technologies. Finally, we raise questions for future exploration as well as challenges and suggestions for future directions in this area of research.

Technology-aided verbal instructions to help persons with mild or moderate Alzheimer's disease perform daily activities

These two studies extended previous research on the use of verbal instructions and support technology for helping persons with mild or moderate Alzheimer's disease perform daily activities. Study I included seven participants who were to carry out one of two previously targeted activities (i.e., either coffee preparation or table setting). Study II included four participants who were to carry out two new activities (i.e., preparation of a fruit salad and of a vegetable salad). The effects of activity engagement on mood (i.e., indices of happiness) were assessed by recording the participants' behavior during the activity trials and parallel non-activity periods. The participants of Study I reached percentages of correct activity performance, which normally exceeded 85. Five of them also showed higher indices of happiness during the activity trials as opposed to the non-activity periods. Three of the participants of Study II reached high percentages of correct performance on both activities available. One of these participants also showed higher indices of happiness during the activity trials. The findings were discussed in relation to previous research outcomes and in terms of their practical implications for intervention programs.

Persons with Alzheimer's disease perform daily activities using verbal-instruction technology: a maintenance assessment

OBJECTIVE

To assess whether verbal-instruction technology could help persons with mild and moderate Alzheimer's disease maintain their recaptured performance of daily activities.

METHODS

This study followed nine patients who had participated in previous studies aimed at helping them recapture one or more functional daily activities (i.e. table setting, coffee, tea or snack preparation, use of make-up and shaving). The plan was to follow each patient for at least 6 months after the intervention, unless his/her condition called for an earlier end of the study.

RESULTS

The study was interrupted after 5 months for two patients who developed serious behavioural problems and continued for 6-14 months for the other seven patients who had largely accurate performance with some adaptations of instructions/steps. Most patients also showed mood improvement during activity.

CONCLUSION

Verbal-instruction technology might be considered a critical tool to help persons with Alzheimer's disease enhance their activity and mood.

A framework for wireless monitoring of mental health conditions

Mental health management is fast becoming a major challenge worldwide as the incidence of mental illness has been increasing. It is affecting the quality of life as well as job productivity for a large number of people. Just like physical illnesses, people with mental illnesses can be monitored for a range of conditions and provided medical care as and when necessary. In this paper, we present an IT-enabled framework to support mental health monitoring. This includes comprehensive monitoring of patients for symptoms, behavior, and medication compliance. We utilize context-awareness as a way to develop a system for mental health monitoring. Several examples of future mental health monitoring are also presented.

Persons with mild and moderate Alzheimer's disease use verbal-instruction technology to manage daily activities: effects on performance and mood

OBJECTIVE

To extend the evaluation of verbal-instruction technology for helping persons with mild and moderate Alzheimer's disease recapture daily activities and improve their mood.

METHODS

Two studies targeted two activities (i.e. snack preparation/sharing and shaving) with six and three new participants, respectively. Intervention effects on activity performance were assessed through non-concurrent multiple baseline designs across participants. The impact of intervention (activity) on mood was assessed by recording indices of happiness or indices of unhappiness during activity and non-activity trials.

RESULTS

The use of a technology providing verbal instructions helped all participants perform the target activities. Performance was largely accurate with seven of the participants. Eight of the participants also showed mood improvement (i.e. increases in indices of happiness or decreases in indices of happiness) during activity.

CONCLUSION

These results suggest that the approach reported may be a useful strategy for helping persons with Alzheimer's disease enhance their activity and mood.

Persons with moderate Alzheimer's disease improve activities and mood via instruction technology

BACKGROUND

Three studies assessed the (a) effectiveness of verbal instructions presented via technology in helping persons with moderate Alzheimer's disease perform daily activities and (b) impact of activity engagement on mood.

METHODS

The 3 studies targeted coffee preparation with 2 women, use of make-up with 2 women, and use of make-up and tea preparation with 3 women. Intervention effects on activity performance were assessed through nonconcurrent multiple baseline designs across participants or multiple baseline designs across activities. The impact of activity on mood was assessed by recording indices of happiness during activity trials and parallel nonactivity periods.

RESULTS

Verbal instructions presented via technology were effective in helping all participants perform the target activities. The participants also showed mood improvement (ie, increases in indices of happiness) during the activity.

CONCLUSION

These results suggest that the approach reported may be a useful strategy for helping persons with Alzheimer's disease.

Helping persons with mild or moderate Alzheimer's disease recapture basic daily activities through the use of an instruction strategy

PURPOSE

The present three pilot studies assessed the effectiveness of verbal instructions, presented automatically through simple technology, in helping persons with mild-to-moderate Alzheimer's disease recapture basic daily activities. The activities were morning bathroom routine, dressing, and table-setting.

METHOD

The studies that focused on morning bathroom routine and on table-setting included three participants each, while the study that focused on dressing involved four participants. A non-concurrent multiple baseline design across participants was used for each study. The instructions and technology were available only during the intervention phases.

RESULTS

Data showed that the intervention strategy involving verbal instructions for the single activity steps presented automatically through technology was effective in helping all participants on each of the activities. The participants' mean percentages of correct steps across activities raised from 13 - 54 during the baseline periods to above 80 or 90 during the intervention periods.

CONCLUSIONS

The results suggest that the intervention strategy reported may represent a suitable approach for helping persons with mild or moderate Alzheimer's disease to recapture basic daily activities. New research should target other activities and check maintenance and generalization issues.

Persons with mild or moderate Alzheimer's disease managing daily activities via verbal instruction technology

Four studies assessed the effectiveness of verbal instructions presented via technology in helping persons with mild or moderate Alzheimer's disease perform daily activities. The first 2 studies were replication efforts concerning morning bathroom routine and table setting and included 4 and 2 participants, respectively. The third study targeted coffee preparation with 3 participants. The fourth study assessed maintenance and generalization of morning bathroom routine and dressing with 1 participant. Nonconcurrent multiple baseline designs served for the first 3 studies and a 5-month postintervention data collection for the fourth study. Verbal instructions for the activity steps presented via technology were effective in helping the participants of the first 3 studies reacquire basic daily activities and the participant of the fourth study retain the reacquired activities across time and settings. These results suggest that the approach reported may be a useful strategy for helping persons with Alzheimer's disease.

The COACH prompting system to assist older adults with dementia through handwashing: an efficacy study

BACKGROUND

Many older adults with dementia require constant assistance from a caregiver when completing activities of daily living (ADL). This study examines the efficacy of a computerized device intended to assist people with dementia through ADL, while reducing caregiver burden. The device, called COACH, uses artificial intelligence to autonomously guide an older adult with dementia through the ADL using audio and/or audio-video prompts.

METHODS

Six older adults with moderate-to-severe dementia participated in this study. Handwashing was chosen as the target ADL. A single subject research design was used with two alternating baseline (COACH not used) and intervention (COACH used) phases. The data were analyzed to investigate the impact of COACH on the participants' independence and caregiver burden as well as COACH's overall performance for the activity of handwashing.

RESULTS

Participants with moderate-level dementia were able to complete an average of 11% more handwashing steps independently and required 60% fewer interactions with a human caregiver when COACH was in use. Four of the participants achieved complete or very close to complete independence. Interestingly, participants' MMSE scores did not appear to robustly coincide with handwashing performance and/or responsiveness to COACH; other idiosyncrasies of each individual seem to play a stronger role. While the majority (78%) of COACH's actions were considered clinically correct, areas for improvement were identified.

CONCLUSION

The COACH system shows promise as a tool to help support older adults with moderate-levels of dementia and their caregivers. These findings reinforce the need for flexibility and dynamic personalization in devices designed to assist older adults with dementia. After addressing identified improvements, the authors plan to run clinical trials with a sample of community-dwelling older adults and caregivers.

Value-directed human behavior analysis from video using partially observable Markov decision processes

This paper presents a method for learning decision theoretic models of human behaviors from video data. Our system learns relationships between the movements of a person, the context in which they are acting, and a utility function. This learning makes explicit that the meaning of a behavior to an observer is contained in its relationship to actions and outcomes. An agent wishing to capitalize on these relationships must learn to distinguish the behaviors according to how they help the agent to maximize utility. The model we use is a partially observable Markov decision process, or POMDP. The video observations are integrated into the POMDP using a dynamic Bayesian network that creates spatial and temporal abstractions amenable to decision making at the high level. The parameters of the model are learned from training data using an a posteriori constrained optimization technique based on the expectation-maximization algorithm. The system automatically discovers classes of behaviors and determines which are important for choosing actions that optimize over the utility of possible outcomes. This type of learning obviates the need for labeled data from expert knowledge about which behaviors are significant and removes bias about what behaviors may be useful to recognize in a particular situation. We show results in three interactions: a single player imitation game, a gestural robotic control problem, and a card game played by two people.

An intelligent powered wheelchair to enable mobility of cognitively impaired older adults: an anticollision system

Older adults with cognitive impairments are generally prohibited from using powered wheelchairs, because of the high risk of collisions with people and objects. This paper describes and presents the preliminary results of a system that uses an infrared sensor to provide anticollision and a prompting system for a powered wheelchair that helps guide the user safely past obstacles. Trials with the prototyped system detected collisions and stopped the chair in 95% of trials with an object and generated no false alarms.