Search

BackgroundResearch has shown the feasibility of human activity recognition using wearable accelerometer devices. Different studies have used varying numbers and placements for data collection using sensors. ObjectiveThis study aims to compare accuracy performance between multiple and variable placements of accelerometer devices in categorizing the type of physical activity and corresponding energy expenditure in older adults. MethodsIn total, 93 participants (mean age 72.2 years, SD 7.1) completed a total of 32 activities of daily life in a laboratory setting. Activities were classified as sedentary versus nonsedentary, locomotion versus nonlocomotion, and lifestyle versus nonlifestyle activities (eg, leisure walk vs computer work). A portable metabolic unit was worn during each activity to measure metabolic equivalents (METs). Accelerometers were placed on 5 different body positions: wrist, hip, ankle, upper arm, and thigh. Accelerometer data from each body position and combinations of positions were used to develop random forest models to assess activity category recognition accuracy and MET estimation. ResultsModel performance for both MET estimation and activity category recognition were strengthened with the use of additional accelerometer devices. However, a single accelerometer on the ankle, upper arm, hip, thigh, or wrist had only a 0.03-0.09 MET increase in prediction error compared with wearing all 5 devices. Balanced accuracy showed similar trends with slight decreases in balanced accuracy for the detection of locomotion (balanced accuracy decrease range 0-0.01), sedentary (balanced accuracy decrease range 0.05-0.13), and lifestyle activities (balanced accuracy decrease range 0.04-0.08) compared with all 5 placements. The accuracy of recognizing activity categories increased with additional placements (accuracy decrease range 0.15-0.29). Notably, the hip was the best single body position for MET estimation and activity category recognition. ConclusionsAdditional accelerometer devices slightly enhance activity recognition accuracy and MET estimation in older adults. However, given the extra burden of wearing additional devices, single accelerometers with appropriate placement appear to be sufficient for estimating energy expenditure and activity category recognition in older adults.

BackgroundChronic pain, including arthritis, affects about 100 million adults in the United States. Complexity and diversity of the pain experience across time and people and its fluctuations across and within days show the need for valid pain reports that do not rely on patient’s long-term recall capability. Smartwatches can be used as digital ecological momentary assessment (EMA) tools for real-time collection of pain scores. Smartwatches are generally less expensive than smartphones, are highly portable, and have a simpler user interface, providing an excellent medium for continuous data collection and enabling a higher compliance rate. ObjectiveThe aim of this study was to explore the attitudes and perceptions of older adults towards design and technological aspects of a smartwatch framework for measuring patient report outcomes (PRO) as an EMA tool. MethodsA focus group session was conducted to explore the perception of participants towards smartwatch technology and its utility for PRO assessment. Participants included older adults (age 65+), with unilateral or bilateral symptomatic knee osteoarthritis. A preliminary user interface with server communication capability was developed and deployed on 10 Samsung Gear S3 smartwatches and provided to the users during the focus group. Pain was designated as the main PRO, while fatigue, mood, and sleep quality were included as auxiliary PROs. Pre-planned topics included participants’ attitude towards the smartwatch technology, usability of the custom-designed app interface, and suitability of the smartwatch technology for PRO assessment. Discussions were transcribed, and content analysis with theme characterization was performed to identify and code the major themes. ResultsWe recruited 19 participants (age 65+) who consented to take part in the focus group study. The overall attitude of the participants toward the smartwatch technology was positive. They showed interest in the direct phone-call capability, availability of extra apps such as the weather apps and sensors for tracking health and wellness such as accelerometer and heart rate sensor. Nearly three-quarters of participants showed willingness to participate in a one-year study to wear the watch daily. Concerns were raised regarding usability, including accessibility (larger icons), notification customization, and intuitive interface design (unambiguous icons and assessment scales). Participants expressed interest in using smartwatch technology for PRO assessment and the availability of methods for sharing data with health care providers. ConclusionsAll participants had overall positive views of the smartwatch technology for measuring PROs to facilitate patient-provider communications and to provide more targeted treatments and interventions in the future. Usability concerns were the major issues that will require special consideration in future smartwatch PRO user interface designs, especially accessibility issues, notification design, and use of intuitive assessment scales.

BackgroundWearable accelerometers have greatly improved measurement of physical activity, and the increasing popularity of smartwatches with inherent acceleration data collection suggest their potential use in the physical activity research domain; however, their use needs to be validated. ObjectiveThis study aimed to assess the validity of accelerometer data collected from a Samsung Gear S smartwatch (SGS) compared with an ActiGraph GT3X+ (GT3X+) activity monitor. The study aims were to (1) assess SGS validity using a mechanical shaker; (2) assess SGS validity using a treadmill running test; and (3) compare individual activity recognition, location of major body movement detection, activity intensity detection, locomotion recognition, and metabolic equivalent scores (METs) estimation between the SGS and GT3X+. MethodsTo validate and compare the SGS accelerometer data with GT3X+ data, we collected data simultaneously from both devices during highly controlled, mechanically simulated, and less-controlled natural wear conditions. First, SGS and GT3X+ data were simultaneously collected from a mechanical shaker and an individual ambulating on a treadmill. Pearson correlation was calculated for mechanical shaker and treadmill experiments. Finally, SGS and GT3X+ data were simultaneously collected during 15 common daily activities performed by 40 participants (n=12 males, mean age 55.15 [SD 17.8] years). A total of 15 frequency- and time-domain features were extracted from SGS and GT3X+ data. We used these features for training machine learning models on 6 tasks: (1) individual activity recognition, (2) activity intensity detection, (3) locomotion recognition, (4) sedentary activity detection, (5) major body movement location detection, and (6) METs estimation. The classification models included random forest, support vector machines, neural networks, and decision trees. The results were compared between devices. We evaluated the effect of different feature extraction window lengths on model accuracy as defined by the percentage of correct classifications. In addition to these classification tasks, we also used the extracted features for METs estimation. ResultsThe results were compared between devices. Accelerometer data from SGS were highly correlated with the accelerometer data from GT3X+ for all 3 axes, with a correlation ≥.89 for both the shaker test and treadmill test and ≥.70 for all daily activities, except for computer work. Our results for the classification of activity intensity levels, locomotion, sedentary, major body movement location, and individual activity recognition showed overall accuracies of 0.87, 1.00, 0.98, 0.85, and 0.64, respectively. The results were not significantly different between the SGS and GT3X+. Random forest model was the best model for METs estimation (root mean squared error of .71 and r-squared value of .50). ConclusionsOur results suggest that a commercial brand smartwatch can be used in lieu of validated research grade activity monitors for individual activity recognition, major body movement location detection, activity intensity detection, and locomotion detection tasks.

Critical care patients experience varying levels of pain during their stay in the intensive care unit, often requiring administration of analgesics and sedation. Such medications generally exacerbate the already sedentary physical activity profiles of critical care patients, contributing to delayed recovery. Thus, it is important not only to minimize pain levels, but also to optimize analgesic strategies in order to maximize mobility and activity of ICU patients. Currently, we lack an understanding of the relation between pain and physical activity on a granular level. In this study, we examined the relationship between nurse assessed pain scores and physical activity as measured using a wearable accelerometer device. We found that average, standard deviation, and maximum physical activity counts are significantly higher before high pain reports compared to before low pain reports during both daytime and nighttime, while percentage of time spent immobile was not significantly different between the two pain report groups. Clusters detected among patients using extracted physical activity features were significant in adjusted logistic regression analysis for prediction of pain report group.

The Clock Drawing Test, where the participant is asked to draw a clock from memory and copy a model clock, is widely used for screening of cognitive impairment. The digital version of the clock test, the digital clock drawing test (dCDT), employs accelerometer and pressure sensors of a digital pen to capture time and pressure information from a participant's performance in a granular digital format. While visual features of the clock drawing test have previously been studied, little is known about the relationship between demographic and cognitive impairment characteristics with dCDT latency and graphomotor features. Here, we examine dCDT feature clusters with respect to sociodemographic and cognitive impairment outcomes. Our results show that the clusters are not significantly different in terms of age and gender, but did significantly differ in terms of education, Mini-Mental State Exam scores, and cognitive impairment diagnoses.This study shows that features extracted from digital clock drawings can provide important information regarding cognitive reserve and cognitive impairments.

Physiological timeseries such as vital signs contain important information about a patient and are used in different clinical application; however, they suffer from missing values and sampling irregularity. In recent years, Gaussian Processes have been used as sophisticated nonlinear value imputation methods on time series, however there is a lack of comparison to other simpler methods. This paper compares the ability of five methods that can be used in missing data imputation in physiological time series. These models are linear interpolation as the baseline, cubic spline interpolation, and three non-linear methods: Single Task Gaussian Processes, Multi-Task Gaussian Processes, and Multivariate Imputation Chained Equations. We used seven intraoperative physiological time series from 27,481 patients. Piecewise aggregate approximation was employed as a dimensionality reduction and resampling strategy. Linear interpolation and cubic splining show overall superiority in prediction of the missing values, compared to the other complex models. The performance of the kernel-based methods suggest that they are highly sensitive to the kernel width and require incorporation of domain knowledge for fine-tuning.

Patients staying in the Intensive Care Unit (ICU) have a severely disrupted circadian rhythm. Due to patients' critical medical condition, ICU physicians and nurses have to provide round-the-clock clinical care, further disrupting patients' circadian rhythm. Mistimed family visits during rest-time can also disrupt patients' circadian rhythm. Currently, such effects are only reported based on hospital visitation policies rather than the actual number of visitors and care providers in the room. To quantify visitation disruptions, we used a deep Mask R-CNN model, a deep learning framework for object instance segmentation to detect and quantify the number of individuals in the ICU unit. This study represents the first effort to automatically quantify visitations in an ICU room, which could have implications in terms of policy adjustment, as well as circadian rhythm investigation. Our model achieved precision of 0.97 and recall of 0.67, with F1 score of 0.79 for detecting disruptions in the ICU units.

Early mobilization of critically ill patients in the Intensive Care Unit (ICU) can prevent adverse outcomes such as delirium and post-discharge physical impairment. To date, no studies have characterized activity of sepsis patients in the ICU using granular actigraphy data. This study characterizes the activity of sepsis patients in the ICU to aid in future mobility interventions. We have compared the actigraphy features of 24 patients in four groups: Chronic Critical Illness (CCI) sepsis patients in the ICU, Rapid Recovery (RR) sepsis patients in the ICU, non-sepsis ICU patients (control-ICU), and healthy subjects. We used a total of 15 statistical and circadian rhythm features extracted from the patients' actigraphy data collected over a five-day period. Our results show that the four groups are significantly different in terms of activity features. In addition, we observed that the CCI and control-ICU patients show less regularity in their circadian rhythm compared to the RR patients. These results show the potential of using actigraphy data for guiding mobilization practices, classifying sepsis recovery subtype, as well as for tracking patients' recovery.

Electronic Health Records (EHR) are mainly designed to record relevant patient information during their stay in the hospital for administrative purposes. They additionally provide an efficient and inexpensive source of data for medical research, such as patient outcome prediction. In this study, we used preoperative Electronic Health Records to predict postoperative delirium. We compared the performance of seven machine learning models on delirium prediction: linear models, generalized additive models, random forests, support vector machine, neural networks, and extreme gradient boosting. Among the models evaluated in this study, random forests and generalized additive model outperformed the other models in terms of the overall performance metrics for prediction of delirium, particularly with respect to sensitivity. We found that age, alcohol or drug abuse, socioeconomic status, underlying medical issue, severity of medical problem, and attending surgeon can affect the risk of delirium.