Dataset Information

The Key Factors in Physical Activity Type Detection Using Real-Life Data: A Systematic Review.

ABSTRACT: Background: Physical activity (PA) is paramount for human health and well-being. However, there is a lack of information regarding the types of PA and the way they can exert an influence on functional and mental health as well as quality of life. Studies have measured and classified PA type in controlled conditions, but only provided limited insight into the validity of classifiers under real-life conditions. The advantage of utilizing the type dimension and the significance of real-life study designs for PA monitoring brought us to conduct a systematic literature review on PA type detection (PATD) under real-life conditions focused on three main criteria: methods for detecting PA types, using accelerometer data collected by portable devices, and real-life settings. Method: The search of the databases, Web of Science, Scopus, PsycINFO, and PubMed, identified 1,170 publications. After screening of titles, abstracts and full texts using the above selection criteria, 21 publications were included in this review. Results: This review is organized according to the three key elements constituting the PATD process using real-life datasets, including data collection, preprocessing, and PATD methods. Recommendations regarding these key elements are proposed, particularly regarding two important PA classes, i.e., posture and motion activities. Existing studies generally reported high to near-perfect classification accuracies. However, the data collection protocols and performance reporting schemes used varied significantly between studies, hindering a transparent performance comparison across methods. Conclusion: Generally, considerably less studies focused on PA types, compared to other measures of PA assessment, such as PA intensity, and even less focused on real-life settings. To reliably differentiate the basic postures and motion activities in real life, two 3D accelerometers (thigh and hip) sampling at 20 Hz were found to provide the minimal sensor configuration. Decision trees are the most common classifier used in practical applications with real-life data. Despite the significant progress made over the past year in assessing PA in real-life settings, it remains difficult, if not impossible, to compare the performance of the various proposed methods. Thus, there is an urgent need for labeled, fully documented, and openly available reference datasets including a common evaluation framework.

SUBMITTER: Allahbakhshi H

PROVIDER: S-EPMC6379834 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The Key Factors in Physical Activity Type Detection Using Real-Life Data: A Systematic Review.

Allahbakhshi Hoda H Hinrichs Timo T Huang Haosheng H Weibel Robert R

Frontiers in physiology 20190212

<b>Background:</b> Physical activity (PA) is paramount for human health and well-being. However, there is a lack of information regarding the types of PA and the way they can exert an influence on functional and mental health as well as quality of life. Studies have measured and classified PA type in controlled conditions, but only provided limited insight into the validity of classifiers under real-life conditions. The advantage of utilizing the type dimension and the significance of real-life ...[more]

PMID: 30809152

Similar Datasets

Project description:Background and objectivesLittle is known about the consequences of asthma on daily life physical activity (DLPA). The aim of this study was to evaluate DLPA and determine its relationship to clinical and functional parameters in patients with asthma.MethodsThis was a single-center prospective study of DLPA conducted between May 2015 and June 2016 in northern France. Fifty-one adult patients with asthma and 36 healthy control subjects were enrolled. Four DLPA parameters were assessed for 5 consecutive days with a physical activity monitor: number of steps walked per day (SPD), total energy expenditure (EE, in kcal/day), EE spent in physical activity requiring ?3 metabolic equivalents (METs), and time (min) spent in activities requiring ?3 METs. Clinical characteristics, pulmonary function tests, 6-minute walk test, and four questionnaires (modified Medical Research Council [mMRC] for dyspnea, asthma control test [ACT], quality of life [AQLQ], and hospital anxiety and depression scale [HADS]), were evaluated. Comparisons of DLPA parameters between the two groups were performed using an analysis of covariance adjusted for age, sex, and body mass index (BMI). Relationships between DLPA parameters and patient characteristics were assessed in multivariable linear regression models.ResultsCompared with patients with mild/moderate asthma, those with severe asthma had lower mean (± standard deviation) forced expiratory volume in 1 s (FEV1) (66 ± 24 vs 94 ± 15% predicted, P < 0.001), ACT score (16.7 ± 4.5 vs 19.8 ± 4.2, P = 0.015), and AQLQ score (157 ± 40 vs 184 ± 33, P = 0.012). There were no significant differences between the two groups in SPD (6560 ± 3915 vs 8546 ± 3431; adjusted P = 0.95), EE in physical activity requiring ?3 METs (620 ± 360 vs 660 ± 140 kcal/day; P = 0.86), time spent in activities requiring EE ?3 (120 ± 54 vs 121 ± 32 min/day; P = 0.69), or total EE (2606 ± 570 vs 2666 ± 551 kcal/day; P = 0.80). These four DLPA measures showed strong inter-parameter correlations in patients with asthma (r = 0.37-0.95, all P < 0.01). All four parameters were lower in the patients with asthma group than in the control group: SPD, 7651 ± 3755 vs 11704 ± 4054 (adjusted P < 0.001); EE in activities requiring ?3 METs, 642 ± 360 vs 852 ± 374 kcal/day (adjusted P = 0.041); time spent in activities requiring ?3 EE, 120 ± 73 vs 189 ± 85 min (adjusted P = 0.005); and total EE, 2639 ± 555 vs 2746 ± 449 kcal/day (adjusted P = 0.007). In the patients with asthma group, the number of SPD correlated with age, FEV1, mMRC score, 6-minute walk test distance, and HADS scores, but not with BMI or ACT test score. Using multivariate analysis, the number of SPD was associated with only age, anxiety, and FEV1, whereas total EE was associated with mMRC score and BMI.ConclusionAge, anxiety, and FEV1 were significantly associated with the number of SPD in patients with asthma. Addressing anxiety should be further studied as way to attempt to increase physical activity in patients with asthma.

Project description:BackgroundIn recent years, researchers have begun applying a trajectory approach to identify homogeneous subgroups of physical activity (PA) in heterogeneous populations. This study systematically reviewed the articles identifying longitudinal PA trajectory classes and the related factors (e.g., determinants, predictors, and outcomes) in the general population during different life phases.MethodsThe included studies used finite mixture models for identifying trajectories of PA, exercise, or sport participation. Three electronic databases, PubMed (Medline), Web of Science, and CINAHL, were searched from the year 2000 to 13 February 2018. The study was conducted according to the PRISMA recommendations.ResultsTwenty-seven articles were included and organized into three age group: youngest (eleven articles), middle (eight articles), and oldest (eight articles). The youngest group consisted mainly of youth, the middle group of adults and the oldest group of late middle-aged and older adults. Most commonly, three or four trajectory classes were reported. Several trajectories describing a decline in PA were reported, especially in the youngest group, whereas trajectories of consistently increasing PA were observed in the middle and oldest group. While the proportion of persistently physically inactive individuals increased with age, the proportion was relatively high at all ages. Generally, male gender, being Caucasian, non-smoking, having low television viewing time, higher socioeconomic status, no chronic illnesses, and family support for PA were associated either with persistent or increasing PA.ConclusionsThe reviewed articles identified various PA subgroups, indicating that finite mixture modeling can yield new information on the complexity of PA behavior compared to studying population mean PA level only. The studies also provided novel information how different factors relate to changes in PA during life course. The recognition of the PA subgroups and their determinants is important for the more precise targeting of PA promotion and PA interventions.Trial registrationPROSPERO registration number: CRD42018088120 .

Project description:IntroductionOutcome assessments after surgery for degenerative lumbar disorders (DLDs) rely on subjective patient-reported outcomes (PROMs). New objective functional capacity tests, like the smartphone-based 6-min walking test (6WT), have been introduced but presumably also do not reflect the patient's real-life functional performance.Research questionPilot study to analyze changes in smartphone-based real-life activity data for physical performance outcome in patients undergoing surgery for DLD.Material and methodsProspective observational study of DLD patients. Objective functional capacity and subjective outcomes were measured using 6WT and PROMs. Real-life physical performance data were acquired retrospectively using Apple iPhone Health data and compared against objective capacity and subjective outcomes.ResultsEight patients (mean 46 years, 62% male) provided 286.858 smartphone mile counts. PROMs and physical capacity (6WT) significantly improved postoperatively. 6WT results increased from 352m pre-to 555/567m at 6/12 weeks postoperatively (p = 0.03). For physical performance a linear mixed effect models showed an increase in daily distance in the first 4 months after surgery (slope +0.178; p < 0.001). However, those increases reversed from 4 until 12 months postoperatively (negative slope estimate of -0.076; p < 0.001). Smartphone-derived physical performance measures showed a positive correlation with corresponding physical capacity in the 6WT (R = 0.57,p = 0.004) and negative correlations with PROMs (COMI: R = -0.62p = 0.001; ZCQ-Physical-Function: R = -0.68,p < 0.001; ZCQ-Symptom-Severity: R = -0.52,p = 0.009).Discussion and conclusionSmartphone-based real-life activity data allows for longitudinal physical performance assessment. Physical performance correlated with physical capacity and patient's subjective perception of disability. However, physical performance may be more resistant to postoperative longtime change which should consult a more cautious use as objective outcome measure.

Project description:BACKGROUND:Low levels of physical activity (PA) are a global concern and increasing PA engagement is becoming a priority in current public health policies. Despite the large number of studies and reviews available, the evidence regarding the behavioral determinants of PA is still inconclusive. Thus, the aim of this umbrella systematic literature review (SLR) was to summarize the evidence on the behavioral determinants of PA across the life course. METHODS:A systematic online search was conducted on MEDLINE, ISI Web of Science, Scopus, and SPORTDiscus databases. The search was limited to studies published in English from January, 2004 to April, 2016. SLRs and meta-analyses (MAs) of observational studies that investigated the behavioral determinants of PA were considered eligible. The extracted data were assessed based on the importance of the determinants, the strength of evidence, and the methodological quality. The full protocol is available from PROSPERO (PROSPERO 2014:CRD42015010616). RESULTS:Seventeen reviews on 35 behavioral determinants of PA were eligible for this umbrella SLR. Regardless of age, the most investigated determinants were those related with 'screen use' and 'smoking'. For youth, probable positive evidence emerged for 'previous PA' and 'independent mobility and active transport' among children and adolescents. For the adult population, 'transition to university' and 'pregnancy/having a child' showed probable negative associations. CONCLUSIONS:Although the majority of the evidence was limited and most of the determinants were not associated with PA, this umbrella SLR provided a comprehensive overview of the associations between behavioral determinants and PA. Youth should be physically active in the early years and increase active transportation to/from school, independent mobility, and 'free-range activities' without adult supervision, whilst adult PA behaviors are mostly influenced by the life events. Finally, more research is needed that incorporates prospective study designs, standardized definitions of PA, objective measurement methods of PA assessment, and the use of interactionist and mediational approaches for the evaluation of different behavioral determinants influencing PA behaviors.

Project description:BackgroundParticipation in regular physical activity is associated with a multitude of health benefits across the life course. However, many people fail to meet PA recommendations. Despite a plethora of studies, the evidence regarding the environmental (physical) determinants of physical activity remains inconclusive.ObjectiveTo identify the physical environmental determinants that influence PA across the life course.MethodsAn online systematic literature search was conducted using MEDLINE, ISI Web of Science, Scopus and SPORTDiscus. The search was limited to studies published in English (January 2004 to April 2016). Only systematic literature reviews (SLRs) and meta-analyses (MAs) of observational studies, that investigated the association between physical determinants and physical activity outcomes, were eligible for inclusion. The extracted data were assessed on the importance of determinants, strength of evidence and methodological quality.ResultsThe literature search identified 28 SLRs and 3 MAs on 67 physical environmental characteristics potentially related to physical activity that were eligible for inclusion. Among preschool children, a positive association was reported between availability of backyard space and outdoor toys/equipment in the home and overall physical activity. The availability of physical activity programs and equipment within schools, and neighbourhood features such as pedestrian and cyclist safety structure were positively associated with physical activity in children and adolescents. Negative street characteristics, for example, lack of sidewalks and streetlights, were negatively associated with physical activity in adults. Inconsistent associations were reported for the majority of reviewed determinants in adults.ConclusionThis umbrella SLR provided a comprehensive overview of the physical environment determinants of physical activity across the life course and has highlighted, particularly amongst youth, a number of key determinants that may be associated with overall physical activity. Given the limited evidence drawn mostly from cross-sectional studies, longitudinal studies are needed to further explore these associations.RegistrationPROSPERO CRD42015010616.

Dataset Information

The Key Factors in Physical Activity Type Detection Using Real-Life Data: A Systematic Review.

Publications

The Key Factors in Physical Activity Type Detection Using Real-Life Data: A Systematic Review.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets