Detecting Sleep and Nonwear in 24-h Wrist Accelerometer Data from the National Health and Nutrition Examination Survey.

INTRODUCTION: Estimating physical activity, sedentary behavior, and sleep from wrist-worn accelerometer data requires reliable detection of sensor nonwear and sensor wear during both sleep and wake. PURPOSE: This study aimed to develop an algorithm that simultaneously identifies sensor wake-wear, sleep-wear, and nonwear in 24-h wrist accelerometer data collected with or without filtering. METHODS: Using sensor data labeled with polysomnography ( n = 21) and directly observed wake-wear data ( n = 31) from healthy adults, and nonwear data from sensors left at various locations in a home ( n = 20), we developed an algorithm to detect nonwear, sleep-wear, and wake-wear for "idle sleep mode" (ISM) filtered data collected in the 2011-2014 National Health and Nutrition Examination Survey. The algorithm was then extended to process original raw data collected from devices without ISM filtering. Both algorithms were further validated using a polysomnography-based sleep and wake-wear data set ( n = 22) and diary-based wake-wear and nonwear labels from healthy adults ( n = 23). Classification performance (F1 scores) was compared with four alternative approaches. RESULTS: The F1 score of the ISM-based algorithm on the training data set using leave-one-subject-out cross-validation was 0.95 ± 0.13. Validation on the two independent data sets yielded F1 scores of 0.84 ± 0.60 for the data set with sleep-wear and wake-wear and 0.94 ± 0.04 for the data set with wake-wear and nonwear. The F1 score when using original, raw data was 0.96 ± 0.08 for the training data sets and 0.86 ± 0.18 and 0.97 ± 0.04 for the two independent validation data sets. The algorithm performed comparably or better than the alternative approaches on the data sets. CONCLUSIONS: A novel machine-learning algorithm was designed to recognize wake-wear, sleep-wear, and nonwear in 24-h wrist-worn accelerometer data that are applicable for ISM-filtered data or original raw data.

Signaligner Pro: A Tool to Explore and Annotate Multi-day Raw Accelerometer Data.

Human activity recognition using wearable accelerometers can enable in-situ detection of physical activities to support novel human-computer interfaces. Many of the machine-learning-based activity recognition algorithms require multi-person, multi-day, carefully annotated training data with precisely marked start and end times of the activities of interest. To date, there is a dearth of usable tools that enable researchers to conveniently visualize and annotate multiple days of high-sampling-rate raw accelerometer data. Thus, we developed Signaligner Pro, an interactive tool to enable researchers to conveniently explore and annotate multi-day high-sampling rate raw accelerometer data. The tool visualizes high-sampling-rate raw data and time-stamped annotations generated by existing activity recognition algorithms and human annotators; the annotations can then be directly modified by the researchers to create their own, improved, annotated datasets. In this paper, we describe the tool's features and implementation that facilitate convenient exploration and annotation of multi-day data and demonstrate its use in generating activity annotations.

Machine learning model for early prediction of acute kidney injury (AKI) in pediatric critical care.

BACKGROUND: Acute kidney injury (AKI) in pediatric critical care patients is diagnosed using elevated serum creatinine, which occurs only after kidney impairment. There are no treatments other than supportive care for AKI once it has developed, so it is important to identify patients at risk to prevent injury. This study develops a machine learning model to learn pre-disease patterns of physiological measurements and predict pediatric AKI up to 48 h earlier than the currently established diagnostic guidelines. METHODS: EHR data from 16,863 pediatric critical care patients between 1 month to 21 years of age from three independent institutions were used to develop a single machine learning model for early prediction of creatinine-based AKI using intelligently engineered predictors, such as creatinine rate of change, to automatically assess real-time AKI risk. The primary outcome is prediction of moderate to severe AKI (Stage 2/3), and secondary outcomes are prediction of any AKI (Stage 1/2/3) and requirement of renal replacement therapy (RRT). Predictions generate alerts allowing fast assessment and reduction of AKI risk, such as: "patient has 90% risk of developing AKI in the next 48 h" along with contextual information and suggested response such as "patient on aminoglycosides, suggest check level and review dose and indication". RESULTS: The model was successful in predicting Stage 2/3 AKI prior to detection by conventional criteria with a median lead-time of 30 h at AUROC of 0.89. The model predicted 70% of subsequent RRT episodes, 58% of Stage 2/3 episodes, and 41% of any AKI episodes. The ratio of false to true alerts of any AKI episodes was approximately one-to-one (PPV 47%). Among patients predicted, 79% received potentially nephrotoxic medication after being identified by the model but before development of AKI. CONCLUSIONS: As the first multi-center validated AKI prediction model for all pediatric critical care patients, the machine learning model described in this study accurately predicts moderate to severe AKI up to 48 h in advance of AKI onset. The model may improve outcome of pediatric AKI by providing early alerting and actionable feedback, potentially preventing or reducing AKI by implementing early measures such as medication adjustment.

Measuring Criterion Validity of Microinteraction Ecological Momentary Assessment (Micro-EMA): Exploratory Pilot Study With Physical Activity Measurement.

BACKGROUND: Ecological momentary assessment (EMA) is an in situ method of gathering self-report on behaviors using mobile devices. In typical phone-based EMAs, participants are prompted repeatedly with multiple-choice questions, often causing participation burden. Alternatively, microinteraction EMA (micro-EMA or µEMA) is a type of EMA where all the self-report prompts are single-question surveys that can be answered using a 1-tap glanceable microinteraction conveniently on a smartwatch. Prior work suggests that µEMA may permit a substantially higher prompting rate than EMA, yielding higher response rates and lower participation burden. This is achieved by ensuring µEMA prompt questions are quick and cognitively simple to answer. However, the validity of participant responses from µEMA self-report has not yet been formally assessed. OBJECTIVE: In this pilot study, we explored the criterion validity of µEMA self-report on a smartwatch, using physical activity (PA) assessment as an example behavior of interest. METHODS: A total of 17 participants answered 72 µEMA prompts each day for 1 week using a custom-built µEMA smartwatch app. At each prompt, they self-reported whether they were doing sedentary, light/standing, moderate/walking, or vigorous activities by tapping on the smartwatch screen. Responses were compared with a research-grade activity monitor worn on the dominant ankle simultaneously (and continuously) measuring PA. RESULTS: Participants had an 87.01% (5226/6006) µEMA completion rate and a 74.00% (5226/7062) compliance rate taking an average of only 5.4 (SD 1.5) seconds to answer a prompt. When comparing µEMA responses with the activity monitor, we observed significantly higher (P<.001) momentary PA levels on the activity monitor when participants self-reported engaging in moderate+vigorous activities compared with sedentary or light/standing activities. The same comparison did not yield any significant differences in momentary PA levels as recorded by the activity monitor when the µEMA responses were randomly generated (ie, simulating careless taps on the smartwatch). CONCLUSIONS: For PA measurement, high-frequency µEMA self-report could be used to capture information that appears consistent with that of a research-grade continuous sensor for sedentary, light, and moderate+vigorous activity, suggesting criterion validity. The preliminary results show that participants were not carelessly answering µEMA prompts by randomly tapping on the smartwatch but were reporting their true behavior at that moment. However, more research is needed to examine the criterion validity of µEMA when measuring vigorous activities.

Relationship between pain, fatigue, and physical activity levels during a technology-based physical activity intervention.

Objective: The majority of individuals with spinal cord injury (SCI) experience chronic pain. Chronic pain can be difficult to manage because of variability in the underlying pain mechanisms. More insight regarding the relationship between pain and physical activity (PA) is necessary to understand pain responses during PA. The objective of this study is to explore possible relationships between PA levels and secondary conditions including pain and fatigue.Design: Prospective cohort analysis of a pilot study.Setting: Community.Participants: Twenty individuals with SCI took part in the study, and sixteen completed the study.Interventions: Mobile-health (mHealth) based PA intervention for two-months during the three-month study.Outcome measures: Chronic Pain Grade Scale (CPGS) questionnaire, The Wheelchair User's Shoulder Pain Index (WUSPI), Fatigue Severity Scale (FSS), and PA levels measured by the mHealth system.Results: A positive linear relationship was found between light-intensity PA and task-specific pain. However, the relationship between moderate-intensity PA and pain interference was best represented by a curvilinear relationship (polynomial regression of second order). Light-intensity PA showed positive, linear correlation with fatigue at baseline. Moderate-intensity PA was not associated with fatigue during any phase of the study.Conclusion: Our results indicated that PA was associated with chronic pain, and the relationship differed based on intensity and amount of PA performed. Further research is necessary to refine PA recommendations for individuals with SCI who experience chronic pain.Trial registration: ClinicalTrials.gov identifier: NCT03773692.

Posture and Physical Activity Detection: Impact of Number of Sensors and Feature Type.

Studies using wearable sensors to measure posture, physical activity (PA), and sedentary behavior typically use a single sensor worn on the ankle, thigh, wrist, or hip. Although the use of single sensors may be convenient, using multiple sensors is becoming more practical as sensors miniaturize. PURPOSE: We evaluated the effect of single-site versus multisite motion sensing at seven body locations (both ankles, wrists, hips, and dominant thigh) on the detection of physical behavior recognition using a machine learning algorithm. We also explored the effect of using orientation versus orientation-invariant features on performance. METHODS: Performance (F1 score) of PA and posture recognition was evaluated using leave-one-subject-out cross-validation on a 42-participant data set containing 22 physical activities with three postures (lying, sitting, and upright). RESULTS: Posture and PA recognition models using two sensors had higher F1 scores (posture, 0.89 ± 0.06; PA, 0.53 ± 0.08) than did models using a single sensor (posture, 0.78 ± 0.11; PA, 0.43 ± 0.03). Models using two nonwrist sensors for posture recognition (F1 score, 0.93 ± 0.03) outperformed two-sensor models including one or two wrist sensors (F1 score, 0.85 ± 0.06). However, two-sensor models for PA recognition with at least one wrist sensor (F1 score, 0.60 ± 0.05) outperformed other two-sensor models (F1 score, 0.47 ± 0.02). Both posture and PA recognition F1 scores improved with more sensors (up to seven; 0.99 for posture and 0.70 for PA), but with diminishing performance returns. Models performed best when including orientation-based features. CONCLUSIONS: Researchers measuring posture should consider multisite sensing using at least two nonwrist sensors, and researchers measuring PA should consider multisite sensing using at least one wrist sensor and one nonwrist sensor. Including orientation-based features improved both posture and PA recognition.

Designing Videogames to Crowdsource Accelerometer Data Annotation for Activity Recognition Research.

Human activity recognition using wearable accelerometers can enable in-situ detection of physical activities to support novel human-computer interfaces and interventions. However, developing valid algorithms that use accelerometer data to detect everyday activities often requires large amounts of training datasets, precisely labeled with the start and end times of the activities of interest. Acquiring annotated data is challenging and time-consuming. Applied games, such as human computation games (HCGs) have been used to annotate images, sounds, and videos to support advances in machine learning using the collective effort of "non-expert game players." However, their potential to annotate accelerometer data has not been formally explored. In this paper, we present two proof-of-concept, web-based HCGs aimed at enabling game players to annotate accelerometer data. Using results from pilot studies with Amazon Mechanical Turk players, we discuss key challenges, opportunities, and, more generally, the potential of using applied videogames for annotating raw accelerometer data to support activity recognition research.

Correction: Mobile health-based physical activity intervention for individuals with spinal cord injury in the community: A pilot study.

[This corrects the article DOI: 10.1371/journal.pone.0223762.].

Mobile health-based physical activity intervention for individuals with spinal cord injury in the community: A pilot study.

Low levels of physical activity (PA) and high levels of sedentary behavior in individuals with spinal cord injury (SCI) have been associated with secondary conditions such as pain, fatigue, weight gain, and deconditioning. One strategy for promoting regular PA is to provide people with an accurate estimate of everyday PA level. The objective of this research was to use a mobile health-based PA measurement system to track PA levels of individuals with SCI in the community and provide them with a behavior-sensitive, just-in-time-adaptive intervention (JITAI) to improve their PA levels. The first, second, and third phases of the study, each with a duration of one month, involved collecting baseline PA levels, providing near-real-time feedback on PA level (PA Feedback), and providing PA Feedback with JITAI, respectively. PA levels in terms of energy expenditure in kilocalories, and minutes of light- and moderate- or vigorous-intensity PA were assessed by an activity monitor during the study. Twenty participants with SCI took part in this research study with a mean (SD) age of 39.4 (12.8) years and 12.4 (12.5) years since injury. Sixteen participants completed the study. Sixteen were male, 16 had paraplegia, and 12 had complete injury. Within-participant comparisons indicated that only two participants had higher energy expenditure (>10%) or lower energy expenditure (<-10%) during PA Feedback with JITAI compared to the baseline. However, eleven participants (69.0%) had higher light- and/or moderate-intensity PA during PA Feedback with JITAI compared to the baseline. To our knowledge, this is the first study to test a PA JITAI for individuals with SCI that responds automatically to monitored PA levels. The results of this pilot study suggest that a sensor-enabled mobile JITAI has potential to improve PA levels of individuals with SCI. Future research should investigate the efficacy of JITAI through a clinical trial.

Pattern recognition of magnetic resonance imaging-based gray matter volume measurements classifies bipolar disorder and major depressive disorder.

BACKGROUND: Bipolar Disorder (BD) cannot be reliably distinguished from Major Depressive Disorder (MDD) until the first manic or hypomanic episode. Consequently, many patients with BD are treated with antidepressants without mood stabilizers, a strategy that is often ineffective and carries a risk of inducing a manic episode. We previously reported reduced cortical thickness in right precuneus, right caudal middle-frontal cortex and left inferior parietal cortex in BD compared with MDD. METHODS: This study extends our previous work by performing individual level classification of BD or MDD in an expanded, currently unmedicated, cohort using gray matter volume (GMV) based on Magnetic Resonance Imaging and a Support Vector Machine. All patients were in a Major Depressive Episode and a leave-two-out analysis was performed. RESULTS: Nineteen out of 26 BD subjects and 20 out of 26 MDD subjects were correctly identified, for a combined accuracy of 75%. The three brain regions contributing to the classification were higher GMV in bilateral supramarginal gyrus and occipital cortex indicating MDD, and higher GMV in right dorsolateral prefrontal cortex indicating BD. LIMITATIONS: This analysis included scans performed with two different headcoils and scan sequences, which limited the interpretability of results in an independent cohort analysis. CONCLUSIONS: Our results add to previously published data which suggest that regional gray matter volume should be investigated further as a clinical diagnostic tool to predict BD before the appearance of a manic or hypomanic episode.

A diffusion tensor imaging study of suicide attempters.

BACKGROUND: Few studies have examined white matter abnormalities in suicide attempters using diffusion tensor imaging (DTI). This study sought to identify white matter regions altered in individuals with a prior suicide attempt. METHODS: DTI scans were acquired in 13 suicide attempters with major depressive disorder (MDD), 39 non-attempters with MDD, and 46 healthy participants (HP). Fractional anisotropy (FA) and apparent diffusion coefficient (ADC) were determined in the brain using two methods: region of interest (ROI) and tract-based spatial statistics (TBSS). ROIs were limited a priori to white matter adjacent to the caudal anterior cingulate cortex, rostral anterior cingulate cortex, dorsomedial prefrontal cortex, and medial orbitofrontal cortex. RESULTS: Using the ROI approach, suicide attempters had lower FA than MDD non-attempters and HP in the dorsomedial prefrontal cortex. Uncorrected TBSS results confirmed a significant cluster within the right dorsomedial prefrontal cortex indicating lower FA in suicide attempters compared to non-attempters. There were no differences in ADC when comparing suicide attempters, non-attempters and HP groups using ROI or TBSS methods. CONCLUSIONS: Low FA in the dorsomedial prefrontal cortex was associated with a suicide attempt history. Converging findings from other imaging modalities support this finding, making this region of potential interest in determining the diathesis for suicidal behavior.

Prediction of selective serotonin reuptake inhibitor response using diffusion-weighted MRI.

Pre-treatment differences in serotonergic binding between those who remit to antidepressant treatment and those who do not have been found using Positron Emission Tomography (PET). To investigate these differences, an exploratory study was performed using a second imaging modality, diffusion-weighted MRI (DW-MRI). Eighteen antidepressant-free subjects with Major Depressive Disorder received a 25-direction DW-MRI scan prior to 8 weeks of selective serotonin reuptake inhibitor treatment. Probabilistic tractography was performed between the midbrain/raphe and two target regions implicated in depression pathophysiology (amygdala and hippocampus). Average fractional anisotropy (FA) within the derived tracts was compared between SSRI remitters and non-remitters, and correlation between pre-treatment FA values and SSRI treatment outcome was assessed. Results indicate that average FA in DW-MRI-derived tracts to the right amygdala was significantly lower in non-remitters (0.55 ± 0.04) than remitters (0.61 ± 0.04, p < 0.01). In addition, there was a significant correlation between average FA in tracts to the right amygdala and SSRI treatment response. These relationships were found at a trend level when using the left amygdala as a tractography target. No significant differences were observed when using the hippocampus as target. These regional differences, consistent with previous PET findings, suggest that the integrity and/or number of white matter fibers terminating in the right amygdala may be compromised in SSRI non-remitters. Further, this study points to the benefits of multimodal imaging and suggests that DW-MRI may provide a pre-treatment signature of SSRI depression remission at 8 weeks.