skip to main content

Title: CAL: A Smart Home Environment for Monitoring Cognitive Decline
The increased growth of the aging population (i.e., 65 years or older) has led to emerging technologies in health care that provide in-home support to patients using devices throughout the household. Such smart home environments can monitor and interact with patients and their doctors/caregivers to augment patient medical data for diagnosis than can be generated via traditional doctor visits. Moreover, smart homes are enabling older adults to stay at home longer as opposed to permanent moves to assisted living or nursing facilities, increasing health and well-being and decreasing overall costs to the individual and society at large. This paper proposes Cognitive Assisted Living (CAL), a cyber-physical system comprising a network of embedded devices for collecting and analyzing patient speech patterns over time for monitoring cognitive function beginning in the early stages of Alzheimer’s disease. Specifically, CAL will analyze patient speech patterns and spatial abilities, via a set of daily interactions, to provide a longitudinal analysis of speech deterioration, a significant indicator of cognitive decline resulting from Alzheimer’s disease. Understanding the rate of cognitive decline can enable caregivers and health care professionals to better manage the patient’s daily care and medical requirements. Additionally, the patient’s cognitive state can be shared across household devices to more » increase the patient’s comfort and better accommodate lifestyle changes. To these ends, we describe the architecture of the proposed system, the methods to which we will detect cognitive decline, and specify how the system will provide continuing fault tolerance and data security at run time. « less
Authors:
; ; ;
Award ID(s):
1657061
Publication Date:
NSF-PAR ID:
10063903
Journal Name:
Proceedings of the International Conference on Distributed Computing Systems
ISSN:
1063-6927
Sponsoring Org:
National Science Foundation
More Like this
  1. Digital health technology is becoming more ubiquitous in monitoring individuals’ health as both device functionality and overall prevalence increase. However, as individuals age, challenges arise with using this technology particularly when it involves neurodegenerative issues (e.g., for individuals with Parkinson’s disease, Alzheimer’s disease, and ALS). Traditionally, neurodegenerative diseases have been assessed in clinical settings using pen-and-paper style assessments; however, digital health systems allow for the collection of far more data than we ever could achieve using traditional methods. The objective of this work is the formation and implementation of a neurocognitive digital health system designed to go beyond what pen-and-paper based solutions can do through the collection of (a) objective, (b) longitudinal, and (c) symptom-specific data, for use in (d) personalized intervention protocols. This system supports the monitoring of all neurocognitive functions (e.g., motor, memory, speech, executive function, sensory, language, behavioral and psychological function, sleep, and autonomic function), while also providing methodologies for personalized intervention protocols. The use of specifically designed tablet-based assessments and wearable devices allows for the collection of objective digital biomarkers that aid in accurate diagnosis and longitudinal monitoring, while patient reported outcomes (e.g., by the diagnosed individual and caregivers) give additional insights for use in themore »formation of personalized interventions. As many interventions are a one-size-fits-all concept, digital health systems should be used to provide a far more comprehensive understanding of neurodegenerative conditions, to objectively evaluate patients, and form personalized intervention protocols to create a higher quality of life for individuals diagnosed with neurodegenerative diseases.« less
  2. The number of patients diagnosed with Alzheimer's disease is significantly increasing, given the boom in the aging population (i.e., 65 years and older). There exist approximately 5.5 million people in the United States that have been diagnosed with Alzheimer's, and as a result friends and family often need to provide care and support (estimated at 15 million people to the cost of $1.1 trillion). Common symptoms of Alzheimer's disease include memory loss, drastic behavioral change, depression, and loss in cognitive and/or spatial abilities. To support the growing need for caregivers, this project developed a prototype virtual reality (VR) environment for enabling caregivers to experience typical scenarios, as well as common strategies for managing each scenario, that they may experience when providing care and support, thereby providing. For instance, a patient may turn on a gas stove and then leave, forgetting that the stove is on. The caregiver then would be required to turn the stove off, to minimize any potential dangers. The prototype environment, CARETAKVR, was developed as an undergraduate research project for learning the process of research as well as the Unity programming environment and VR. The prototype provides a gamified training tool, masking scenarios as objectives and successmore »with a score, to enable the potential caregiver to feel rewarded for correctly supporting the patient. The virtual patient is controlled via artificial intelligence and follows an initial set of guidelines to behave as a patient with early-stage Alzheimer's may behave. The caregiver is provided with a set of tasks to perform, in VR space, to achieve their goals for each scenario. Common tasks include Check Refrigerator, Check Stove, and Comfort Patient. This project has been demonstrated to colleagues in the health care domain and has seeded future collaborations to iterate the capabilities of this tool. All project artifacts have been open-sourced and are available online.« less
  3. Today, various sensor technologies have been introduced to help people keep track of their daily living activities. For example, a wide range of sensors were integrated in applications to develop a smart home, a mobile emergency response system and a fall detection system. Sensor technologies were also employed in clinical settings for monitoring an early sign or onset of Alzheimer’s diseases, dementia, abnormal sleep disorder, and heart rate problems. However, there has been a lack of attention paid to comprehensive reviews, valuable especially for young, early-career scholars who just developed research interests in this area. This paper reviewed the existing sensor technologies by considering various contexts such as sensor features, data of interests, locations of sensors, and the number of sensors. For instance, sensor technologies provided various features that enabled people to monitor biomechanics of human movement (e.g., walking speed), use of household goods (e.g., switch on/off of home appliances), sounds (e.g., sounds in a particular room), and surrounding environments (e.g., temperature and humidity). Sensor technologies were widely used to examine various data, such as biomarkers for health, dietary habits, leisure activities, and hygiene status. Sensors were installed in various locations to cover wide-open area (e.g., ceilings, wall, and hallway),more »specific area (e.g., a bedroom and a dining room), and specific objects (e.g., mattresses and windows). Different sets of sensors were employed to keep track of activities of daily living, which ranged from a single sensor to multiple sensors to cover throughout the home. This comprehensive reviews for sensor technology implementations are anticipated to help many researchers and professionals to design, develop, and use sensor technology applications adequately in the target user’s contexts by promoting safety, usability, and accessibility.

    « less
  4. Introduction: Alzheimer’s disease (AD) causes progressive irreversible cognitive decline and is the leading cause of dementia. Therefore, a timely diagnosis is imperative to maximize neurological preservation. However, current treatments are either too costly or limited in availability. In this project, we explored using retinal vasculature as a potential biomarker for early AD diagnosis. This project focuses on stage 3 of a three-stage modular machine learning pipeline which consisted of image quality selection, vessel map generation, and classification [1]. The previous model only used support vector machine (SVM) to classify AD labels which limited its accuracy to 82%. In this project, random forest and gradient boosting were added and, along with SVM, combined into an ensemble classifier, raising the classification accuracy to 89%. Materials and Methods: Subjects classified as AD were those who were diagnosed with dementia in “Dementia Outcome: Alzheimer’s disease” from the UK Biobank Electronic Health Records. Five control groups were chosen with a 5:1 ratio of control to AD patients where the control patients had the same age, gender, and eye side image as the AD patient. In total, 122 vessel images from each group (AD and control) were used. The vessel maps were then segmented from fundusmore »images through U-net. A t-test feature selection was first done on the training folds and the selected features was fed into the classifiers with a p-value threshold of 0.01. Next, 20 repetitions of 5-fold cross validation were performed where the hyperparameters were solely tuned on the training data. An ensemble classifier consisting of SVM, gradient boosting tree, and random forests was built and the final prediction was made through majority voting and evaluated on the test set. Results and Discussion: Through ensemble classification, accuracy increased by 4-12% relative to the individual classifiers, precision by 9-15%, sensitivity by 2-9%, specificity by at least 9-16%, and F1 score by 712%. Conclusions: Overall, a relatively high classification accuracy was achieved using machine learning ensemble classification with SVM, random forest, and gradient boosting. Although the results are very promising, a limitation of this study is that the requirement of needing images of sufficient quality decreased the amount of control parameters that can be implemented. However, through retinal vasculature analysis, this project shows machine learning’s high potential to be an efficient, more cost-effective alternative to diagnosing Alzheimer’s disease. Clinical Application: Using machine learning for AD diagnosis through retinal images will make screening available for a broader population by being more accessible and cost-efficient. Mobile device based screening can also be enabled at primary screening in resource-deprived regions. It can provide a pathway for future understanding of the association between biomarkers in the eye and brain.« less
  5. Modern medical devices aim at providing invasive e-health care services to patients with long-term conditions. Typically, these services are implemented as embedded software applications that remotely and automatically control the opera- tions of the devices according to the patient’s condition as mon- itored by the underlying sensors. Such applications are neither safe nor secure mainly because of unreliable sensors, which may provide incorrect input data either due to its malfunctioning or due to some accidental (by privileged user) or intentional (by adversary) interference. Hence, the incorrect sensor data may lead to identification of inaccurate patient condition, which may threaten the patient’s life. To ensure safety and security of e- health applications, current approaches employ data analysis techniques to monitor sensor data and alarm when some unusual value is detected and employ access control strategies to ensure that controller decisions are consistent with sensor input data. However, such approaches fail to detect stealthy attacks, e.g. bad data (false data injection) and bad computations because they do not understand what the application or device is trying to do. To this end, we evaluate our existing approach (i.e., ARMET) to assure safety and security of an emerging and critically real-time application domain ofmore »e-health. The approach is based on the specification of the application and device, which has a design and a run-time component. Given an application specification, the design component employs logical verification methods to assure that the application design is resilient to some bad data, i.e., there are no sensor input data values with meaningful threshold which are admissible to the specification but are not true. Given the specification, the runtime component monitors application’s execution and assures that the execution is consistent with the specification and alarms whenever it detects a violation, i.e., there is a bad computation. We evaluate the methodology through its application to an example medical e-health application that controls and monitors blood glucose through an insulin pump.« less