Analyzing Sensor-Based Time Series Data to Track Changes in Physical Activity during Inpatient Rehabilitation

Time series data collected from sensors can be analyzed to monitor changes in physical activity as an individual makes a substantial lifestyle change, such as recovering from an injury or illness. In an inpatient rehabilitation setting, approaches to detect and explain changes in longitudinal physical activity data collected from wearable sensors can provide value as a monitoring, research, and motivating tool. We adapt and expand our Physical Activity Change Detection (PACD) approach to analyze changes in patient activity in such a setting. We use Fitbit Charge Heart Rate devices with two separate populations to continuously record data to evaluate PACD, nine participants in a hospitalized inpatient rehabilitation group and eight in a healthy control group. We apply PACD to minute-by-minute Fitbit data to quantify changes within and between the groups. The inpatient rehabilitation group exhibited greater variability in change throughout inpatient rehabilitation for both step count and heart rate, with the greatest change occurring at the end of the inpatient hospital stay, which exceeded day-to-day changes of the control group. Our additions to PACD support effective change analysis of wearable sensor data collected in an inpatient rehabilitation setting and provide insight to patients, clinicians, and researchers.

[1]  B. Dobkin,et al.  SIRRACT , 2015, Neurorehabilitation and neural repair.

[2]  Diane J. Cook,et al.  Modeling patterns of activities using activity curves , 2016, Pervasive Mob. Comput..

[3]  George D Fulk,et al.  Accuracy of 2 Activity Monitors in Detecting Steps in People With Stroke and Traumatic Brain Injury , 2013, Physical Therapy.

[4]  Ben J. A. Kröse,et al.  Longitudinal ambient sensor monitoring for functional health assessments: a case study , 2014, UbiComp Adjunct.

[5]  Maria Hagströmer,et al.  The International Physical Activity Questionnaire modified for the elderly: aspects of validity and feasibility , 2010, Public Health Nutrition.

[6]  Matthew P. Buman,et al.  Validation of Consumer-Based Hip and Wrist Activity Monitors in Older Adults With Varied Ambulatory Abilities , 2017, The journals of gerontology. Series A, Biological sciences and medical sciences.

[7]  Jesse Hoey,et al.  Sensor-Based Activity Recognition , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[8]  Jie J Cao,et al.  Predicting maximum heart rate among patients with coronary heart disease receiving beta-adrenergic blockade therapy. , 2004, American heart journal.

[9]  Mohan S. Kankanhalli,et al.  An evaluation of wearable activity monitoring devices , 2013, PDM '13.

[10]  Kristan A. Leech,et al.  Feasibility of Focused Stepping Practice During Inpatient Rehabilitation Poststroke and Potential Contributions to Mobility Outcomes , 2015, Neurorehabilitation and neural repair.

[11]  B. Dolezal,et al.  Validation of Biofeedback Wearables for Photoplethysmographic Heart Rate Tracking. , 2016, Journal of sports science & medicine.

[12]  Tan-Hsu Tan,et al.  Indoor activity monitoring system for elderly using RFID and Fitbit Flex wristband , 2014, IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI).

[13]  Sergio Tufik,et al.  Comment on: Use of a Fitness Tracker to Promote Physical Activity in Children with Acute Lymphoblastic Leukemia , 2016, Pediatric blood & cancer.

[14]  M. Braga,et al.  Exploratory Data Analysis , 2018, Encyclopedia of Social Network Analysis and Mining. 2nd Ed..

[15]  W. McIlroy,et al.  Use of Accelerometer-Based Feedback of Walking Activity for Appraising Progress With Walking-Related Goals in Inpatient Stroke Rehabilitation , 2015, Neurorehabilitation and neural repair.

[16]  M. J. Pletcher,et al.  Continuous daily assessment of multiple sclerosis disability using remote step count monitoring , 2017, Journal of Neurology.

[17]  Diane J. Cook,et al.  Detecting Health and Behavior Change by Analyzing Smart Home Sensor Data , 2016, 2016 IEEE International Conference on Smart Computing (SMARTCOMP).

[18]  Nigel Collier,et al.  Change-Point Detection in Time-Series Data by Relative Density-Ratio Estimation , 2012, Neural Networks.

[19]  Gregory M Dominick,et al.  Physical Activity Assessment Between Consumer- and Research-Grade Accelerometers: A Comparative Study in Free-Living Conditions , 2016, JMIR mHealth and uHealth.

[20]  B. Hamilton.  A uniform national data system for medical rehabilitation. , 1987 .

[21]  Ilkka Korhonen,et al.  Wearable Monitoring of Physical Functioning and Disability Changes, Circadian Rhythms and Sleep Patterns in Nursing Home Residents , 2016, IEEE Journal of Biomedical and Health Informatics.

[22]  John Hansen,et al.  Evaluation of Commercial Self-Monitoring Devices for Clinical Purposes: Results from the Future Patient Trial, Phase I , 2017, Sensors.

[23]  Hirofumi Tanaka,et al.  Age-predicted maximal heart rate revisited. , 2001, Journal of the American College of Cardiology.

[24]  Hisashi Kashima,et al.  Unsupervised Change Analysis Using Supervised Learning , 2008, PAKDD.

[25]  S. Borson,et al.  The Mini‐Cog: a cognitive ‘vital signs’ measure for dementia screening in multi‐lingual elderly , 2000, International journal of geriatric psychiatry.

[26]  L. Neubeck,et al.  Validation of Fitbit-Flex as a measure of free-living physical activity in a community-based phase III cardiac rehabilitation population , 2016, European journal of preventive cardiology.

[27]  Shuang Wang,et al.  Activity Density Map Visualization and Dissimilarity Comparison for Eldercare Monitoring , 2012, IEEE Transactions on Information Technology in Biomedicine.

[28]  B. Dobkin.  Wearable motion sensors to continuously measure real-world physical activities. , 2013, Current opinion in neurology.

[29]  Jyrki Lötjönen,et al.  Circadian activity rhythm in demented and non‐demented nursing‐home residents measured by telemetric actigraphy , 2005, Journal of sleep research.

[30]  Diane J. Cook,et al.  Using wrist-worn sensors to measure and compare physical activity changes for patients undergoing rehabilitation , 2017, 2017 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops).

[31]  Diane J. Cook,et al.  Unsupervised detection and analysis of changes in everyday physical activity data , 2016, J. Biomed. Informatics.

[32]  Masashi Sugiyama,et al.  Change-Point Detection in Time-Series Data by Relative Density-Ratio Estimation , 2011 .

[33]  Diane J. Cook,et al.  Using Smart Homes to Detect and Analyze Health Events , 2016, Computer.

[34]  F. E. Grubbs.  Procedures for Detecting Outlying Observations in Samples , 1969 .

[35]  Janice S. Withycombe,et al.  Use of a Fitness Tracker to Promote Physical Activity in Children With Acute Lymphoblastic Leukemia , 2016, Pediatric blood & cancer.

[36]  Guy Faulkner,et al.  Is this Bit Fit? Measuring the Quality of the Fitbit Step-Counter , 2012 .

[37]  U. Wisløff,et al.  Accuracy of Heart Rate Watches: Implications for Weight Management , 2016, PloS one.

[38]  C. Caspersen,et al.  Physical activity, exercise, and physical fitness: definitions and distinctions for health-related research. , 1985, Public health reports.