Methodology for Establishing a Community-Wide Life Laboratory for Capturing Unobtrusive and Continuous Remote Activity and Health Data.

An end-to-end suite of technologies has been established for the unobtrusive and continuous monitoring of health and activity changes occurring in the daily life of older adults over extended periods of time. The technology is aggregated into a system that incorporates the principles of being minimally obtrusive, while generating secure, privacy protected, continuous objective data in real-world (home-based) settings for months to years. The system includes passive infrared presence sensors placed throughout the home, door contact sensors installed on exterior doors, connected physiological monitoring devices (such as scales), medication boxes, and wearable actigraphs. Driving sensors are also installed in participants' cars and computer (PC, tablet or smartphone) use is tracked. Data is annotated via frequent online self-report options that provide vital information with regard to the data that is difficult to infer via sensors such as internal states (e.g., pain, mood, loneliness), as well as data referent to activity pattern interpretation (e.g., visitors, rearranged furniture). Algorithms have been developed using the data obtained to identify functional domains key to health or disease activity monitoring, including mobility (e.g., room transitions, steps, gait speed), physiologic function (e.g., weight, body mass index, pulse), sleep behaviors (e.g., sleep time, trips to the bathroom at night), medication adherence (e.g., missed doses), social engagement (e.g., time spent out of home, time couples spend together), and cognitive function (e.g., time on computer, mouse movements, characteristics of online form completion, driving ability). Change detection of these functions provides a sensitive marker for the application in health surveillance of acute illnesses (e.g., viral epidemic) to the early detection of prodromal dementia syndromes. The system is particularly suitable for monitoring the efficacy of clinical interventions in natural history studies of geriatric syndromes and in clinical trials.

Weekly observations of online survey metadata obtained through home computer use allow for detection of changes in everyday cognition before transition to mild cognitive impairment.

INTRODUCTION: Subtle changes in instrumental activities of daily living often accompany the onset of mild cognitive impairment (MCI) but are difficult to measure using conventional tests. METHODS: Weekly online survey metadata metrics, annual neuropsychological tests, and an instrumental activity of daily living questionnaire were examined in 110 healthy older adults with intact cognition (mean age = 85 years) followed up for up to 3.6 years; 29 transitioned to MCI during study follow-up. RESULTS: In the baseline period, incident MCI participants completed their weekly surveys 1.4 hours later in the day than stable cognitively intact participants, P = .03, d = 0.47. Significant associations were found between earlier survey start time of day and higher memory (r = -0.34; P < .001) and visuospatial test scores (r = -0.37; P < .0001). Longitudinally, incident MCI participants showed an increase in survey completion time by 3 seconds per month for more than the year before diagnosis compared with stable cognitively intact participants (ß = 0.12, SE = 0.04, t = 2.8; P = .006). DISCUSSION: Weekly online survey metadata allowed for detection of changes in everyday cognition before transition to MCI.

Internet Searches and Their Relationship to Cognitive Function in Older Adults: Cross-Sectional Analysis.

BACKGROUND: Alzheimer disease (AD) is a very challenging experience for all those affected. Unfortunately, detection of Alzheimer disease in its early stages when clinical treatments may be most effective is challenging, as the clinical evaluations are time-consuming and costly. Recent studies have demonstrated a close relationship between cognitive function and everyday behavior, an avenue of research that holds great promise for the early detection of cognitive decline. One area of behavior that changes with cognitive decline is language use. Multiple groups have demonstrated a close relationship between cognitive function and vocabulary size, verbal fluency, and semantic ability, using conventional in-person cognitive testing. An alternative to this approach which is inherently ecologically valid may be to take advantage of automated computer monitoring software to continually capture and analyze language use while on the computer. OBJECTIVE: The aim of this study was to understand the relationship between Internet searches as a measure of language and cognitive function in older adults. We hypothesize that individuals with poorer cognitive function will search using fewer unique terms, employ shorter words, and use less obscure words in their searches. METHODS: Computer monitoring software (WorkTime, Nestersoft Inc) was used to continuously track the terms people entered while conducting searches in Google, Yahoo, Bing, and Ask.com. For all searches, punctuation, accents, and non-ASCII characters were removed, and the resulting search terms were spell-checked before any analysis. Cognitive function was evaluated as a z-normalized summary score capturing five unique cognitive domains. Linear regression was used to determine the relationship between cognitive function and Internet searches by controlling for variables such as age, sex, and education. RESULTS: Over a 6-month monitoring period, 42 participants (mean age 81 years [SD 10.5], 83% [35/42] female) conducted 2915 searches using these top search engines. Participants averaged 3.08 words per search (SD 1.6) and 5.77 letters per word (SD 2.2). Individuals with higher cognitive function used more unique terms per search (beta=.39, P=.002) and employed less common terms in their searches (beta=1.39, P=.02). Cognitive function was not significantly associated with the length of the words used in the searches. CONCLUSIONS: These results suggest that early decline in cognitive function may be detected from the terms people search for when they use the Internet. By continuously tracking basic aspects of Internet search terms, it may be possible to detect cognitive decline earlier than currently possible, thereby enabling proactive treatment and intervention.

Variability in medication taking is associated with cognitive performance in nondemented older adults.

Interventions to slow cognitive decline typically can do little to reverse decline. Thus, early detection methods are critical. However, tools like cognitive testing are time consuming and require costly expertise. Changes in activities of daily living such as medication adherence may herald the onset of cognitive decline before clinical standards. Here, we determine the relationship between medication adherence and cognitive function in preclinical older adults. We objectively assessed medication adherence in 38 older adults (mean age 86.7 ± 6.9 years). Our results demonstrate that individuals with lower cognitive function have more spread in the timing of taking their medications (P = .014) and increase the spread in the timing of taking their medications over time (P = .012). These results demonstrate that continuous monitoring of medication adherence may provide the opportunity to identify patients experiencing slow cognitive decline in the earliest stages when pharmacologic or behavioral interventions may be most effective.

A Smart-Home System to Unobtrusively and Continuously Assess Loneliness in Older Adults.

Loneliness is a common condition in older adults and is associated with increased morbidity and mortality, decreased sleep quality, and increased risk of cognitive decline. Assessing loneliness in older adults is challenging due to the negative desirability biases associated with being lonely. Thus, it is necessary to develop more objective techniques to assess loneliness in older adults. In this paper, we describe a system to measure loneliness by assessing in-home behavior using wireless motion and contact sensors, phone monitors, and computer software as well as algorithms developed to assess key behaviors of interest. We then present results showing the accuracy of the system in detecting loneliness in a longitudinal study of 16 older adults who agreed to have the sensor platform installed in their own homes for up to 8 months. We show that loneliness is significantly associated with both time out-of-home ([Formula: see text] and [Formula: see text]) and number of computer sessions ([Formula: see text] and [Formula: see text]). [Formula: see text] for the model was 0.35. We also show the model's ability to predict out-of-sample loneliness, demonstrating that the correlation between true loneliness and predicted out-of-sample loneliness is 0.48. When compared with the University of California at Los Angeles loneliness score, the normalized mean absolute error of the predicted loneliness scores was 0.81 and the normalized root mean squared error was 0.91. These results represent first steps toward an unobtrusive, objective method for the prediction of loneliness among older adults, and mark the first time multiple objective behavioral measures that have been related to this key health outcome.