Prediction of oxygen uptake dynamics by machine learning analysis of wearable sensors during activities of daily living.
Ontology highlight
ABSTRACT:
SUBMITTER: Beltrame T
PROVIDER: S-EPMC5381118 | biostudies-literature | 2017 Apr
REPOSITORIES: biostudies-literature
Publications
Prediction of oxygen uptake dynamics by machine learning analysis of wearable sensors during activities of daily living.
Beltrame T T Amelard R R Wong A A Hughson R L RL
Scientific reports 20170405
Currently, oxygen uptake () is the most precise means of investigating aerobic fitness and level of physical activity; however, can only be directly measured in supervised conditions. With the advancement of new wearable sensor technologies and data processing approaches, it is possible to accurately infer work rate and predict during activities of daily living (ADL). The main objective of this study was to develop and verify the methods required to predict and investigate the dynamics during AD ...[more]
Similar Datasets
Project description:Physical activity levels are related through algorithms to the energetic demand, with no information regarding the integrity of the multiple physiological systems involved in the energetic supply. Longitudinal analysis of the oxygen uptake (V?o2) by wearable sensors in realistic settings might permit development of a practical tool for the study of the longitudinal aerobic system dynamics (i.e., V?o2 kinetics). This study evaluated aerobic system dynamics based on predicted V?o2 data obtained from wearable sensors during unsupervised activities of daily living (?ADL). Thirteen healthy men performed a laboratory-controlled moderate exercise protocol and were monitored for ?6 h/day for 4 days (?ADL data). Variables derived from hip accelerometer (ACCHIP), heart rate monitor, and respiratory bands during ?ADL were extracted and processed by a validated random forest regression model to predict V?o2. The aerobic system analysis was based on the frequency-domain analysis of ACCHIP and predicted V?o2 data obtained during ?ADL. Optimal samples for frequency domain analysis (constrained to ?0.01 Hz) were selected when ACCHIP was higher than 0.05 g at a given frequency (i.e., participants were active). The temporal characteristics of predicted V?o2 data during ?ADL correlated with the temporal characteristics of measured V?o2 data during laboratory-controlled protocol ([Formula: see text]?=?0.82, P < 0.001, n?=?13). In conclusion, aerobic system dynamics can be investigated during unsupervised activities of daily living by wearable sensors. Although speculative, these algorithms have the potential to be incorporated into wearable systems for early detection of changes in health status in realistic environments by detecting changes in aerobic response dynamics. NEW & NOTEWORTHY The early detection of subclinical aerobic system impairments might be indicative of impaired physiological reserves that impact the capacity for physical activity. This study is the first to use wearable sensors in unsupervised activities of daily living in combination with novel machine learning algorithms to investigate the aerobic system dynamics with the potential to contribute to models of functional health status and guide future individualized health care in the normal population.
| S-EPMC5867367 | biostudies-literature
Project description:Levodopa-induced dyskinesias are abnormal involuntary movements experienced by the majority of persons with Parkinson's disease (PwP) at some point over the course of the disease. Choreiform as the most common phenomenology of levodopa-induced dyskinesias can be managed by adjusting the dose/frequency of PD medication(s) based on a PwP's motor fluctuations over a typical day. We developed a sensor-based assessment system to provide such information. We used movement data collected from the upper and lower extremities of 15 PwPs along with a deep recurrent model to estimate dyskinesia severity as they perform different activities of daily living (ADL). Subjects performed a variety of ADLs during a 4-h period while their dyskinesia severity was rated by the movement disorder experts. The estimated dyskinesia severity scores from our model correlated highly with the expert-rated scores (r = 0.87 (p < 0.001)), which was higher than the performance of linear regression that is commonly used for dyskinesia estimation (r = 0.81 (p < 0.001)). Our model provided consistent performance at different ADLs with minimum r = 0.70 (during walking) to maximum r = 0.84 (drinking) in comparison to linear regression with r = 0.00 (walking) to r = 0.76 (cutting food). These findings suggest that when our model is applied to at-home sensor data, it can provide an accurate picture of changes of dyskinesia severity facilitating effective medication adjustments.
| S-EPMC8041801 | biostudies-literature
Project description:The number of people diagnosed with dementia is expected to rise in the coming years. Given that there is currently no definite cure for dementia and the cost of care for this condition soars dramatically, slowing the decline and maintaining independent living are important goals for supporting people with dementia. This paper discusses a study that is called Technology Integrated Health Management (TIHM). TIHM is a technology assisted monitoring system that uses Internet of Things (IoT) enabled solutions for continuous monitoring of people with dementia in their own homes. We have developed machine learning algorithms to analyse the correlation between environmental data collected by IoT technologies in TIHM in order to monitor and facilitate the physical well-being of people with dementia. The algorithms are developed with different temporal granularity to process the data for long-term and short-term analysis. We extract higher-level activity patterns which are then used to detect any change in patients' routines. We have also developed a hierarchical information fusion approach for detecting agitation, irritability and aggression. We have conducted evaluations using sensory data collected from homes of people with dementia. The proposed techniques are able to recognise agitation and unusual patterns with an accuracy of up to 80%.
| S-EPMC5933790 | biostudies-literature
Project description:ObjectiveTracking seizures is crucial for epilepsy monitoring and treatment evaluation. Current epilepsy care relies on caretaker seizure diaries, but clinical seizure monitoring may miss seizures. Wearable devices may be better tolerated and more suitable for long-term ambulatory monitoring. This study evaluates the seizure detection performance of custom-developed machine learning (ML) algorithms across a broad spectrum of epileptic seizures utilizing wrist- and ankle-worn multisignal biosensors.MethodsWe enrolled patients admitted to the epilepsy monitoring unit and asked them to wear a wearable sensor on either their wrists or ankles. The sensor recorded body temperature, electrodermal activity, accelerometry (ACC), and photoplethysmography, which provides blood volume pulse (BVP). We used electroencephalographic seizure onset and offset as determined by a board-certified epileptologist as a standard comparison. We trained and validated ML for two different algorithms: Algorithm 1, ML methods for developing seizure type-specific detection models for nine individual seizure types; and Algorithm 2, ML methods for building general seizure type-agnostic detection, lumping together all seizure types.ResultsWe included 94 patients (57.4% female, median age = 9.9 years) and 548 epileptic seizures (11 066 h of sensor data) for a total of 930 seizures and nine seizure types. Algorithm 1 detected eight of nine seizure types better than chance (area under the receiver operating characteristic curve [AUC-ROC] = .648-.976). Algorithm 2 detected all nine seizure types better than chance (AUC-ROC = .642-.995); a fusion of ACC and BVP modalities achieved the best AUC-ROC (.752) when combining all seizure types together.SignificanceAutomatic seizure detection using ML from multimodal wearable sensor data is feasible across a broad spectrum of epileptic seizures. Preliminary results show better than chance seizure detection. The next steps include validation of our results in larger datasets, evaluation of the detection utility tool for additional clinical seizure types, and integration of additional clinical information.
| S-EPMC8457135 | biostudies-literature
Project description:Oxygen consumption ([Formula: see text]) provides established clinical and physiological indicators of cardiorespiratory function and exercise capacity. However, [Formula: see text] monitoring is largely limited to specialized laboratory settings, making its widespread monitoring elusive. Here we investigate temporal prediction of [Formula: see text] from wearable sensors during cycle ergometer exercise using a temporal convolutional network (TCN). Cardiorespiratory signals were acquired from a smart shirt with integrated textile sensors alongside ground-truth [Formula: see text] from a metabolic system on 22 young healthy adults. Participants performed one ramp-incremental and three pseudorandom binary sequence exercise protocols to assess a range of [Formula: see text] dynamics. A TCN model was developed using causal convolutions across an effective history length to model the time-dependent nature of [Formula: see text]. Optimal history length was determined through minimum validation loss across hyperparameter values. The best performing model encoded 218 s history length (TCN-VO2 A), with 187, 97, and 76 s yielding <3% deviation from the optimal validation loss. TCN-VO2 A showed strong prediction accuracy (mean, 95% CI) across all exercise intensities (-22 ml min-1, [-262, 218]), spanning transitions from low-moderate (-23 ml min-1, [-250, 204]), low-high (14 ml min-1, [-252, 280]), ventilatory threshold-high (-49 ml min-1, [-274, 176]), and maximal (-32 ml min-1, [-261, 197]) exercise. Second-by-second classification of physical activity across 16,090 s of predicted [Formula: see text] was able to discern between vigorous, moderate, and light activity with high accuracy (94.1%). This system enables quantitative aerobic activity monitoring in non-laboratory settings, when combined with tidal volume and heart rate reserve calibration, across a range of exercise intensities using wearable sensors for monitoring exercise prescription adherence and personal fitness.
| S-EPMC8586225 | biostudies-literature
Project description:BackgroundLimitations in instrumental activities of daily living (IADL) hinder a person's ability to live independently in the community and self-manage their conditions, but its impact on hospital readmission has not been firmly established.ObjectiveTo test the importance of IADL dependency as a predictor of 30-day readmissions and quantify its impact relative to other morbidities.DesignA retrospective cohort study of the population-based Health and Retirement Study linked to Medicare claims data. Random forest was used to rank each predictor variable in terms of its ability to predict readmission. Classification and regression tree (CART) was used to identify complex multimorbidity combinations associated with high or low risk of readmission. Generalized linear regression was used to estimate the adjusted relative risk of readmission for IADL limitations.SubjectsHospitalizations of adults age 65 and older (n = 20,007), from 6617 unique subjects.Main measuresThe main outcome was 30-day all-cause unplanned readmission. The main predictor of interest was self-reported IADL limitation. Other key predictors were self-reported complex multimorbidity including chronic diseases, geriatric syndromes, and activities of daily living (ADL) limitations, along with demographic, socioeconomic, and behavioral factors.Key resultsThe overall 30-day readmission rate in the study was 16.4%. Random forest analysis ranked ADLs and IADL limitations as the two most important predictors of 30-day readmission. CART identified hospitalizations of patients with IADL limitations and diabetes as a subgroup at the highest risk of readmission (26% readmitted). Multivariable regression analyses showed that ADL limitations were associated with 1.17 (1.06-1.29) times higher risk of readmission even after adjusting for other patient covariates. Risk prediction was modest though for even the best model (AUC = 0.612).ConclusionsIADL limitations are key predictors of 30-day readmission as demonstrated using several machine learning methods. Routine assessment of functional abilities in hospital settings could help identify those most at risk.
| S-EPMC7573020 | biostudies-literature
Project description:Dementia is a neurological and cognitive condition that affects millions of people around the world. At any given time in the United Kingdom, 1 in 4 hospital beds are occupied by a person with dementia, while about 22% of these hospital admissions are due to preventable causes. In this paper we discuss using Internet of Things (IoT) technologies and in-home sensory devices in combination with machine learning techniques to monitor health and well-being of people with dementia. This will allow us to provide more effective and preventative care and reduce preventable hospital admissions. One of the unique aspects of this work is combining environmental data with physiological data collected via low cost in-home sensory devices to extract actionable information regarding the health and well-being of people with dementia in their own home environment. We have worked with clinicians to design our machine learning algorithms where we focused on developing solutions for real-world settings. In our solutions, we avoid generating too many alerts/alarms to prevent increasing the monitoring and support workload. We have designed an algorithm to detect Urinary Tract Infections (UTI) which is one of the top five reasons of hospital admissions for people with dementia (around 9% of hospital admissions for people with dementia in the UK). To develop the UTI detection algorithm, we have used a Non-negative Matrix Factorisation (NMF) technique to extract latent factors from raw observation and use them for clustering and identifying the possible UTI cases. In addition, we have designed an algorithm for detecting changes in activity patterns to identify early symptoms of cognitive decline or health decline in order to provide personalised and preventative care services. For this purpose, we have used an Isolation Forest (iForest) technique to create a holistic view of the daily activity patterns. This paper describes the algorithms and discusses the evaluation of the work using a large set of real-world data collected from a trial with people with dementia and their caregivers.
| S-EPMC6333356 | biostudies-literature
Project description:Wearable devices offer the potential to track motor symptoms in neurological disorders. Kinematic data used together with machine learning algorithms can accurately identify people living with movement disorders and the severity of their motor symptoms. In this study we aimed to establish whether a combination of wearable sensor data and machine learning algorithms with automatic feature selection can estimate the clinical rating scale and whether it is possible to monitor the motor symptom progression longitudinally, for people with Parkinson's Disease. Seventy-four patients visited the lab seven times at 3-month intervals. Their walking (2-minutes) and postural sway (30-seconds,eyes-closed) were recorded using six Inertial Measurement Unit sensors. Simple linear regression and Random Forest algorithms were utilised together with different routines of automatic feature selection or factorisation, resulting in seven different machine learning algorithms to estimate the clinical rating scale (Movement Disorder Society- Unified Parkinson's Disease Rating Scale part III; MDS-UPDRS-III). Twenty-nine features were found to significantly progress with time at group level. The Random Forest model revealed the most accurate estimation of the MDS-UPDRS-III among the seven models. The model estimations detected a statistically significant progression of the motor symptoms within 15 months when compared to the first visit, whereas the MDS-UPDRS-III did not capture any change. Wearable sensors and machine learning can track the motor symptom progression in people with PD better than the conventionally used clinical rating scales. The methods described in this study can be utilised complimentary to the clinical rating scales to improve the diagnostic and prognostic accuracy.
| S-EPMC10560243 | biostudies-literature
Project description:Gene expression profiles were generated from 199 primary breast cancer patients. Samples 1-176 were used in another study, GEO Series GSE22820, and form the training data set in this study. Sample numbers 200-222 form a validation set. This data is used to model a machine learning classifier for Estrogen Receptor Status. RNA was isolated from 199 primary breast cancer patients. A machine learning classifier was built to predict ER status using only three gene features.
2013-01-01 | E-GEOD-29210 | biostudies-arrayexpress
Project description:Knee joint forces (KJF) are biomechanical measures used to infer the load on knee joint structures. The purpose of this study is to develop an artificial neural network (ANN) that estimates KJF during sport movements, based on data obtained by wearable sensors. Thirteen participants were equipped with two inertial measurement units (IMUs) located on the right leg. Participants performed a variety of movements, including linear motions, changes of direction, and jumps. Biomechanical modelling was carried out to determine KJF. An ANN was trained to model the association between the IMU signals and the KJF time series. The ANN-predicted KJF yielded correlation coefficients that ranged from 0.60 to 0.94 (vertical KJF), 0.64 to 0.90 (anterior-posterior KJF) and 0.25 to 0.60 (medial-lateral KJF). The vertical KJF for moderate running showed the highest correlation (0.94 ± 0.33). The summed vertical KJF and peak vertical KJF differed between calculated and predicted KJF across all movements by an average of 5.7% ± 5.9% and 17.0% ± 13.6%, respectively. The vertical and anterior-posterior KJF values showed good agreement between ANN-predicted outcomes and reference KJF across most movements. This study supports the use of wearable sensors in combination with ANN for estimating joint reactions in sports applications.
| S-EPMC6749227 | biostudies-literature