Learning and Improving Alzheimer's Patient-Caregiver Relationships Via Smart Healthcare Technology

Collaborative Research: Learning and Improving Alzheimer's Patient-Caregiver Relationships Via Smart Healthcare Technology

The purpose of this project is to develop a monitoring, modeling, and interactive recommendation solution (for caregivers) for in-home dementia patient care that focuses on caregiver-patient relationships. This includes monitoring for mood and stress and analyzing the significance of monitoring those attributes to dementia patient care and subsequent behavior dynamics between the patient and caregiver. In addition, novel and adaptive behavioral suggestions at the right moments aims at helping improve familial interactions related to caregiving, which over time should ameliorate the stressful effects of the patient's illness and reduce strain on caregivers. The technical solution consists of a core set of statistical learning based techniques for automated generation of specialized modules required by in-home dementia patient care. There are three main technical components in the solution. The first obtains textual content and prosody from voice and uses advanced machine learning techniques to create classification models. This approach not only monitors patients' behavior, but also caregivers', and infers the underlying dynamics of their interactions, such as changes in mood and stress. The second is the automated creation of classifiers and inference modules tailored to the particular patients and dementia conditions (such as different stages of dementia). The third is an adaptive recommendation system that closes the loop of an in-home behavior monitoring system.

The purpose of this project is to develop a monitoring, modeling, and interactive recommendation solution (for caregivers) for in-home dementia patient care that focuses on caregiver-patient relationships. This includes monitoring for mood and stress and analyzing the significance of monitoring those attributes to dementia patient care and subsequent behavior dynamics between the patient and caregiver. In addition, novel and adaptive behavioral suggestions will be provided to family caregivers via text messages on project Smart phones at the right moments aimed to help improve familial interactions related to caregiving, which over time should ameliorate the stressful effects of the patient's illness and reduce strain on caregivers. The technical solution consists of a core set of statistical learning based techniques for automated generation of specialized modules required by in-home dementia patient care. There are three main technical components in the solution. - The first obtains textual content and prosody from voice and uses advanced machine learning techniques to create classification models. This approach not only monitors patients' behavior, but also caregivers', and infers the underlying dynamics of their interactions, such as changes in mood and stress. - The second is the automated creation of classifiers and inference modules tailored to the particular patients and dementia conditions (such as different stages of dementia). - The third is an adaptive recommendation system that closes the loop of an in-home behavior monitoring system.

All dementia/caregiver dyads will have in-home acoustic monitoring to classify mood and will be provided mindfulness-based stress reduction recommendations via a smart phone.

The purpose of this project is to develop a monitoring, modeling, and interactive recommendation solution (for caregivers) for in-home dementia patient care that focuses on caregiver-patient relationships. This includes monitoring for mood and stress and analyzing the significance of monitoring those attributes to dementia patient care and subsequent behavior dynamics between the patient and caregiver. In addition, novel and adaptive behavioral suggestions will be provided to family caregivers via text messages on project Smart phones at the right moments aimed to help improve familial interactions related to caregiving, which over time should ameliorate the stressful effects of the patient's illness and reduce strain on caregivers.

The acoustic monitoring will occur for 1 month to establish baseline interactions between the family caregiver and the persons with dementia. Acoustic monitoring and text message recommendations will occur over the subsequent 3 months.

Depression Anxiety Stress Scale (DASS): The DASS is a set of three self-report scales designed to measure the negative emotional states of depression, anxiety and stress. The DASS was constructed not merely as another set of scales to measure conventionally defined emotional states, but to further the process of defining, understanding, and measuring the ubiquitous and clinically significant emotional states usually described as depression, anxiety and stress. As the scales of the DASS have been shown to have high internal consistency and to yield meaningful discriminations in a variety of settings, the scales should meet the needs of both researchers and clinicians who wish to measure current state or change in state over time (e.g., in the course of treatment) on the three dimensions of depression, anxiety and stress. Minimum score: 0; Maximum score: 168; A higher score indicates higher levels of depression, anxiety and stress.

The Revised Memory and Behavior Problems Checklist (RMBPC) is a 24-item, caregiver-report measure of observable behavioral problems in dementia patients and the caregiver's stress reactions to these behavioral disturbances. The instrument provides a total score and 3 subscale scores for patient behavioral problems (memory-related, depression, and disruptive behaviors) and corresponding scores for caregiver reactions to each of these. Overall scale internal consistency of the instrument is reported as .84 for patient behavior and .90 for caregiver reaction and the instrument has confirmed validity through comparison of instrument scores with measures of depression, cognitive impairment, and caregiver burden Minimum score: 0; Maximum score: 120. A higher score indicates higher levels of caregiver reaction to dementia behaviors.

The 16-item, Difficulties in Emotion Regulation Scale (DERS-16) will be used to measure caregivers' ability to regulate emotions at baseline and end of study. The scale used is the brief version of a theoretically-driven, valid, and reliable self-report tool used to measure difficulties with emotion regulation. The brief version will be more easily administered with the study population and has been shown to be valid and reliable [41]. Minimum score: 16; Maximum score: 80. A higher score indicates higher levels of caregiver emotional reactivity.

Caregivers will be asked to complete the 39-item Five Facet Mindfulness Questionnaire to measure their capacity for five different domains of mindfulness practice at baseline and end of study. The five facets include non-reactivity to the inner experience, non-judgment of the inner experience, acting with awareness, observing, and describing internal states. The questionnaire has good reliability and validity Minimum score: 39; Maximum score: 195. A higher score indicates higher levels of caregiver capacity for mindfulness practices.

Modified Caregiver Strain Index (MCSI): It is a 13-item self-report measure that examines both subjective and objective elements of caregiver strain. The MCSI showed excellent inter-item and test-retest reliability and was correlated in expected directions with relevant criteria [32]. It has excellent reliability and validity, displays adequate clinical sensitivity, has an established cut-off for determining functional/dysfunctional systems, and has been used successfully on a variety of mental health outcomes [28]. We will use a practice tracking worksheet to assess how much the caregivers practice the exercises over the course of the study. Minimum score: 0; Maximum score: 26. High scores indicates higher caregiver strain.

Family Assessment Device (FAD): The FAD is a self-report measure that is given as a set of seven subscales of varied length. Each subscale measures a different dimension of family function. Scores for each dimension (problem solving, communication, roles, affective responsiveness, affective involvement, behavior control, and general functioning) are calculated separately as the mean of the items in that subscale. The information obtained through the FAD allows for the elucidation of the structure and organization of the family system, as well as the identification of common patterns of interaction among family members. The FAD is heavily used in research related to the function of family systems, and it has demonstrated excellent validity and reliability in both non-clinical and clinical populations. Minimum score:0 ; Maximum score: 212. A higher score indicates greater levels of family functioning.

Determine the accuracy of dementia/caregiver dyad mood classification using the acoustic monitoring system. Percentage of agreement between participant identified mood (via self-report) and mood classifier system identified mood (via acoustic monitoring).

Determine the functionality of the text message recommendation system. Percentage of recommendations that are implemented at time of message delivery. Identification of common reasons for improper implementation.

Determine usefulness of behavioral recommendation messages as reported by caregivers via surveys and interviews. Participants will rate behavioral recommendations on a scale from 0(not useful)-10(very useful). A high score indicates the recommendation was very useful for them. Participants will also participate in an interview at study of completion (average of 4 months) to discuss how useful and acceptable the recommendations were for them.

Measure of caregiver self-reported loneliness via 0(none)-10(highest) scale. A high score indicates greater levels of loneliness.

Measure of caregiver self-reported physical health via 0(none)-10(highest) scale. A low score indicates poor self-reported physical health.

Measure of caregiver self-reported emotional health via 0(none)-10(highest) scale. A low score indicates poor self-reported emotional health.

Inclusion Criteria for persons with dementia: Females and males Age 60-90 years Physician documentation of dementia: Alzheimer's disease, vascular, mixed or unspecified type Community-dwelling (living in the home) Fluent in English Inclusion criteria for family caregivers: Age 21 years or older Informal, unpaid caregiver who resides with the care recipient Fluent in English Functioning home Wifi Scoring above a 3 on the Revised Memory and Behavior Problems Checklist, a clinical cut-off point used to determine caregiver stress. Exclusion Criteria for persons with dementia: Presence of acute illness as this could lead to delirium Alcohol abuse or dependence within the past 2 years (DSM-IV criteria) History of significant psychiatric illness (e.g., schizophrenia).

Rose KM, Coop Gordon K, Schlegel EC, Mccall M, Gao Y, Ma M, Lenger KA, Ko E, Wright KD, Wang H, Stankovic J. Smarthealth technology study protocol to improve relationships between older adults with dementia and family caregivers. J Adv Nurs. 2021 May;77(5):2519-2529. doi: 10.1111/jan.14714. Epub 2021 Feb 11.