scholarly journals Correlates of Physical Activity Behavior in Adults: A Data Mining Approach

2020 ◽  
Author(s):  
Vahid Farrahi ◽  
Maisa Niemelä ◽  
Mikko Kärmeniemi ◽  
Soile Puhakka ◽  
Maarit Kangas ◽  
...  
Keyword(s):  
Physical Activity ◽  
Data Mining ◽  
Decision Tree ◽  
Sitting Time ◽  
Physically Active ◽  
Additional Hypothesis ◽  
Interaction Detection ◽  
Data Mining Approach ◽  
Modifiable Factors ◽  
Physically Inactive

Abstract Purpose A data mining approach was applied to establish a multilevel hierarchy explaining physical activity (PA) behavior, and to methodologically identify the correlates of PA behavior. Methods The 46-year follow-up data from the population-based Northern Finland Birth Cohort 1966 were used to create a hierarchy using Chi-square Automatic Interaction Detection (CHAID) decision tree technique for predicting PA behavior. The study’s subjects were classified as physically active or physically inactive based on their activity profiles derived from objective measurement of PA. The variables were a wide list of potentially modifiable factors including self-reported, clinical, and environmental measures. We then analyzed the association of the factors emerging from the model with three PA metrics including sedentary (SED), light PA (LPA), and moderate-to-vigorous PA (MVPA) minutes per day. Results Model fitting was performed using a total of 168 factors as input variables to classify the PA behavior of 2,701 physically active and 1,881 physically inactive subjects. The decision tree selected a total of 36 factors of different domains by which 54 subgroups of subjects were formed. Factors emerging from the model were associated with the PA metrics, including body fat percentage (SED: B=26.5, LPA: B=-16.1, and MVPA: B=-11.7), normalized heart rate recovery 60 seconds after exercise (SED: B=-16.1, LPA: B=9.9, and MVPA: B=9.6), average weekday total sitting time (SED: B=34.1, LPA: B=-25.3, and MVPA: B=-5.8), and extravagance score (SED: B=6.3 and LPA: B=-3.7). Conclusions Using data mining, a data-driven model was established from empirical data that can be potentially utilized to identify subgroups for multilevel intervention allocation. An extensive set of factors was methodologically discovered that can be a basis for additional hypothesis testing in PA correlates research.

scholarly journals Correlates of Physical Activity Behavior in Adults: A Data Mining Approach

2020 ◽  
Author(s):  
Vahid Farrahi ◽  
Maisa Niemelä ◽  
Mikko Kärmeniemi ◽  
Soile Puhakka ◽  
Maarit Kangas ◽  
...  
Keyword(s):  
Physical Activity ◽  
Data Mining ◽  
Decision Tree ◽  
Sitting Time ◽  
Accelerometer Data ◽  
Relative Importance ◽  
Interaction Detection ◽  
Data Mining Approach ◽  
Input Variables

Abstract Purpose: A data mining approach was applied to establish a multilevel hierarchy predicting physical activity (PA) behavior, and to methodologically identify the correlates of PA behavior. Methods: Cross-sectional data from the population-based Northern Finland Birth Cohort 1966 study, collected in the most recent follow-up at age 46, were used to create a hierarchy using the chi-square automatic interaction detection (CHAID) decision tree technique for predicting PA behavior. PA behavior is defined as active or inactive depending on participants’ activity profiles, which were previously created through a multidimensional (clustering) approach on continuous accelerometer-measured activity intensities in one week. The input variables (predictors) used for decision tree fitting consisted of individual, demographical, psychological, behavioral, environmental, and physical factors. Using generalized linear mixed models, we also analyzed how factors emerging from the model were associated with three PA metrics, including daily time (minutes per day) in sedentary (SED), light PA (LPA), and moderate-to-vigorous PA (MVPA), to assure the relative importance of methodologically identified factors. Results: Of the 4,582 participants with valid accelerometer data at the latest follow-up, 2,701 and 1,881 had active and inactive profiles, respectively. We used a total of 168 factors as input variables to classify these two PA behaviors. Out of these 168 factors, the decision tree selected 36 factors of different domains from which 54 subgroups of participants were formed. The emerging factors from the model explained minutes per day in SED, LPA, and/or MVPA, including body fat percentage (SED: B=26.5, LPA: B=-16.1, and MVPA: B=-11.7), normalized heart rate recovery 60 seconds after exercise (SED: B=-16.1, LPA: B=9.9, and MVPA: B=9.6), average weekday total sitting time (SED: B=34.1, LPA: B=-25.3, and MVPA: B=-5.8), and extravagance score (SED: B=6.3 and LPA: B=-3.7). Conclusions: Using data mining, we established a data-driven model composed of 36 different factors of relative importance from empirical data. This model may be used to identify subgroups for multilevel intervention allocation and design. Additionally, this study methodologically discovered an extensive set of factors that can be a basis for additional hypothesis testing in PA correlates research.

scholarly journals Correlates of Physical Activity Behavior in Adults: A Data Mining Approach

2020 ◽  
Author(s):  
Vahid Farrahi ◽  
Maisa Niemelä ◽  
Mikko Kärmeniemi ◽  
Soile Puhakka ◽  
Maarit Kangas ◽  
...  
Keyword(s):  
Physical Activity ◽  
Data Mining ◽  
Decision Tree ◽  
Sitting Time ◽  
Accelerometer Data ◽  
Relative Importance ◽  
Interaction Detection ◽  
Data Mining Approach ◽  
Input Variables

Abstract Purpose: A data mining approach was applied to establish a multilevel hierarchy predicting physical activity (PA) behavior, and to methodologically identify the correlates of PA behavior.Methods: Cross-sectional data from the population-based Northern Finland Birth Cohort 1966 study, collected in the most recent follow-up at age 46, were used to create a hierarchy using the chi-square automatic interaction detection (CHAID) decision tree technique for predicting PA behavior. PA behavior is defined as active or inactive based on machine-learned activity profiles, which were previously created through a multidimensional (clustering) approach on continuous accelerometer-measured activity intensities in one week. The input variables (predictors) used for decision tree fitting consisted of individual, demographical, psychological, behavioral, environmental, and physical factors. Using generalized linear mixed models, we also analyzed how factors emerging from the model were associated with three PA metrics, including daily time (minutes per day) in sedentary (SED), light PA (LPA), and moderate-to-vigorous PA (MVPA), to assure the relative importance of methodologically identified factors.Results: Of the 4,582 participants with valid accelerometer data at the latest follow-up, 2,701 and 1,881 had active and inactive profiles, respectively. We used a total of 168 factors as input variables to classify these two PA behaviors. Out of these 168 factors, the decision tree selected 36 factors of different domains from which 54 subgroups of participants were formed. The emerging factors from the model explained minutes per day in SED, LPA, and/or MVPA, including body fat percentage (SED: B=26.5, LPA: B=-16.1, and MVPA: B=-11.7), normalized heart rate recovery 60 seconds after exercise (SED: B=-16.1, LPA: B=9.9, and MVPA: B=9.6), average weekday total sitting time (SED: B=34.1, LPA: B=-25.3, and MVPA: B=-5.8), and extravagance score (SED: B=6.3 and LPA: B=-3.7).Conclusions: Using data mining, we established a data-driven model composed of 36 different factors of relative importance from empirical data. This model may be used to identify subgroups for multilevel intervention allocation and design. Additionally, this study methodologically discovered an extensive set of factors that can be a basis for additional hypothesis testing in PA correlates research.

scholarly journals Data mining untuk memprediksi prestasi siswa berdasarkan sosial ekonomi, motivasi, kedisiplinan dan prestasi masa lalu

2014 ◽  
Vol 4 (2) ◽  
Author(s):  
Heri Susanto ◽  
Sudiyatno Sudiyatno
Keyword(s):  
Data Mining ◽  
Decision Tree ◽  
Multiple Regression ◽  
Economic Status ◽  
Predictive Analysis ◽  
Research Approach ◽  
Significance Level ◽  
Achievement Prediction ◽  
Interaction Detection ◽  
Chi Squared

Penelitian ini bertujuan untuk membuat prediksi prestasi belajar siswa berdasarkan status sosial ekonomi orang tua, motivasi, kedisiplinan siswa dan prestasi masa lalu menggunakan metode data mining dengan algoritma J48. Sebagai perbandingan, data penelitian dianalisis juga dengan CHAID (Chi Squared Automatic Interaction Detection) dan regresi ganda. Pendekatan penelitian yang digunakan adalah kuantitatif. Subyek penelitian ini adalah siswa tingkat X SMK Negeri 4 Surakarta berjumlah 416 siswa. Teknik pengumpulan data yang digunakan adalah dokumentasi dan angket. Hasil penelitian menunjukkan bahwa analisis prediksi menggunakan decision tree algoritma J48 memiliki akurasi sebesar 95,7%, sedangkan analisis prediksi menggunakan CHAID memiliki tingat akurasi 82,1% dan analisis regresi ganda menghasilkan tingkat signifikansi sebesar 90,6%. Berdasarkan hasil tersebut bisa disimpulkan bahwa metode J48 lebih baik dibandingkan dengan metode CHAID dan regresi ganda. DATA MINING TO PREDICT STUDENT’S ACHIEVEMENT BASED ON SOCIO-ECONOMIC, MOTIVATION, DISCIPLINE AND ACHIEVEMENT OF THE PASTAbstractThis study aims to make student achievement prediction based on socio-economic status of parents, motivation, discipline students and past achievements using data mining methods with the J48 algorithm. For comparison, the data were analyzed also with CHAID (Chi Squared Automatic Interaction Detection) and multiple regression. The research approach is quantitative. The subjects of this study were student-first level at SMK Negeri 4 Surakarta totaled 416 students. Data collection techniques used are documentation and questionnaires. The results showed that the predictive analysis using J48 decision tree algorithm has an accuracy of 95.7%, while the predictive analysis using CHAID has the rank of an accuracy of 82.1% and a multiple regression analysis resulted in a significance level of 90.6%. Based on these results it can be concluded that the J48 method is better than the CHAID and multiple regression methods.

scholarly journals Physical activity, diet and quality of life during mandatory (COVID-19) quarantine following repatriation

2020 ◽  
Vol 8 ◽  
pp. 2050313X2097250
Author(s):  
Philippe Jean-Luc Gradidge ◽  
Herculina Salome Kruger
Keyword(s):  
Physical Activity ◽  
South African ◽  
Cardiovascular Health ◽  
Sitting Time ◽  
Physical And Mental Health ◽  
Physically Active ◽  
Self Monitoring ◽  
Prolonged Sitting ◽  
Online Tools

The coronavirus disease 2019 crisis in South Africa has been managed through an effective evidence-based approach. The aim of this case report was to determine the value of staying physically active during the coronavirus disease 2019 pandemic, using online resources to prevent the harmful effects of sedentary behaviour under confined living conditions. A repatriated South African citizen was placed into monitored 14-day quarantine confined to a room, self-monitoring dietary intake and physical and health measures, while engaged in online exercise videos and indoor walking. This study demonstrates that structured indoor activity improves physical and mental health outcomes, despite prolonged sitting time during the day. During the current pandemic and in the presence of limited freedom of movement, sustained physical activity is made feasible by accessing online tools and resources, essentially reducing vulnerability to existing cardiovascular health concerns. However, these findings are based on a single participant and therefore further study is required.

Readiness to change level of physical activity in leisure time among physically inactive Danish adults

2009 ◽  
Vol 37 (8) ◽  
pp. 785-792 ◽  
Author(s):  
Pia V. Pedersen ◽  
Mette Kjøller ◽  
Ola Ekholm ◽  
Morten Grønbæk ◽  
Tine Curtis
Keyword(s):  
Physical Activity ◽  
Social Factors ◽  
Leisure Time ◽  
Readiness To Change ◽  
Multiple Correspondence Analysis ◽  
Physically Active ◽  
Danish Health ◽  
The Family ◽  
Interview Survey ◽  
Physically Inactive

Aims: The study examined readiness to change the level of physical activity in leisure time among physically inactive adults, the sociodemographic, lifestyle-related and social factors associated with readiness to change, and finally the various kinds of help to become more physically active required by people who are ready to change and by those not ready to change. Materials and methods: Data were derived from the national representative Danish Health Interview Survey 2005 and included 9,160 physically inactive persons between 16 and 79 years of age. Data were analysed using multiple logistic regression and multiple correspondence analysis. Results: In all, 52 % of the physically inactive respondents stated they were ready to change their level of physical activity. Men had higher odds of being ready to change than women. Readiness to change decreased with age and increased with increasing levels of education. Those ready to change led an active and social lifestyle characterized by considerable health-oriented engagement, while the opposite characterised those not ready to change. Those ready to change wanted help to become more physically active in the form of e.g. opportunities for physical activity at work or help and support from the family. Those not ready to change wanted help from a general practitioner or did not want help at all. Conclusions: Those ready to change and those not ready to change were characterized by very different sociodemographic, lifestyle-related and social factors. This knowledge will benefit prevention initiatives and elucidates the necessity of targeting the initiatives.

Inmates’ physical activity as part of the health ecology

Open Medicine ◽  
2011 ◽  
Vol 6 (5) ◽  
pp. 679-684 ◽  
Author(s):  
Vidmantas Vaiciulis ◽  
Saulius Kavaliauskas ◽  
Ricardas Radisauskas
Keyword(s):  
Physical Activity ◽  
Social Skills ◽  
Secondary Education ◽  
Self Esteem ◽  
Psychological State ◽  
Cross Sectional ◽  
Physically Active ◽  
Study Results ◽  
Sports Activities ◽  
Physically Inactive

AbstractTo evaluate the possibilities of physical activity in developing inmates’ healthy lifestyle and social skills. The research, which was conducted in 2009 in Pravieniskes First and Second Correction Houses, was local and cross-sectional using a written questionnaire. The questionnaire consisted of four groups of questions/statements: I — demographic questions; II — questions/statements about inmates’ physical (sports) activities (was created for this study) and III — assessment of inmates’ social skills. And IV — assessment of inmates’ self esteem. Sufficiently physically active inmates (n=185) comprised 57.8 percent of the total number of respondents. Inmates’ physical activity statistically significantly (p<0.05) correlates with their younger age. Secondary education is prevailing in the group of physically active inmates, while primary — lower secondary education predominates in the group of physically inactive inmates (n=135). Only less than 6 percent of inmates have higher education. The average age of physically active inmates is statistically significantly lower than that of physically inactive inmates, 26 and 31.6 years respectively (p=0.01). The analysis of inmates’ contentment with their psychological state and satisfaction with health care services, food quality, and conditions for sports activities showed that physically active inmates are more critical about these factors than physically inactive inmates. Only the contentment with psychological state in physically active inmates is statistically significantly higher than in inactive inmates. Out of eleven social skills assessed in the study, only two skills (ability to initiate conversation with a stranger and sense of responsibility) are statistically significant (p<0.05). The probability that the convicts who have a strong sense of responsibility tend to be more physically active than the inmates who do not consider themselves responsible is 7.4 times higher. The study results showed that self-esteem in physically active inmates is statistically significantly higher that in physically inactive inmates (p=0.033). Low self-esteem was not determined in any inmates.

scholarly journals Suspicious E-mail Detection via Decision Tree: A Data Mining Approach

2007 ◽  
Vol 15 (2) ◽  
pp. 161 ◽  
Author(s):  
Appavu Balamurugan ◽  
Ramasamy Rajaram
Keyword(s):  
Data Mining ◽  
Decision Tree ◽  
Data Mining Approach ◽  
E Mail

scholarly journals Influence of Physically Active or Sedentary Lifestyle on Postural Control of Community-dwelling Old Adults

2021 ◽  
Vol 5 ◽  
pp. 4
Author(s):  
Uanderson Silva Pirôpo ◽  
Silvania Moraes Costa ◽  
Ícaro JS Ribeiro ◽  
Ivna Vidal Freire ◽  
Ludmila Schettino ◽  
...  
Keyword(s):  
Physical Activity ◽  
Postural Control ◽  
Sedentary Behavior ◽  
Postural Balance ◽  
Community Dwelling ◽  
Sitting Time ◽  
Mean Velocity ◽  
Physically Active ◽  
Old Adults ◽  
Significant Difference

Objectives: The maintenance of the postural balance is fundamental for the daily living activities, as well as for the practice of physical exercise. However, the aging process and sedentary behavior (i.e., large sitting time) lead to changes biological systems, impairing postural balance with consequent increased falls risk. On the other hand, physical activity practice is a protective factor against these trends. The aim of this study is to investigate the influence of physical activity profile and sedentary behavior on postural control in community-dwelling old adults.Methods: This is a cross-sectional study including 208 community-dwelling old adults, which were stratified as sufficiently or insufficiently physically active and with or without sedentary behavior. Then, they were grouped as follow: G1 (sufficiently physically active and without sedentary behavior), G2 (insufficiently physically active, but without sedentary behavior), G3 (sufficiently physically active, but with sedentary behavior), and G4 (insufficiently physically active and with sedentary behavior).Results: Stabilometric parameters (sway area, total length of center of pressure [CoP] trajectory, and the mean velocity of CP displacement) were obtained to evaluate the postural control. There was significant difference between G1 and G4 on mean velocity of CoP displacement (p < 0.05).Conclusions: The coexistence of sedentary behavior and insufficient physically active profile seem to impact negatively on postural control.

Physical activity and functional shortening of the muscles of the lower limbs in pupils aged between 14-16

Physiotherapy ◽  
2014 ◽  
Vol 22 (1) ◽  
Author(s):  
Katarzyna Kuraczowska ◽  
Katarzyna Ligarska
Keyword(s):  
Physical Activity ◽  
Young Women ◽  
Lower Limbs ◽  
Motor Ability ◽  
Sports Activity ◽  
Physically Active ◽  
Functional Movement ◽  
Sports Club ◽  
Muscle Shortening ◽  
Physically Inactive

AbstractAim of the study: The aim of this study was to evaluate how sports activity influences the extent and incidence of muscle shortening in lower limbs in physically active and inactive young women. Material and methods: A group of 30 pupils aged between 14-16 was tested. Fifteen pupils out of the group regularly played volleyball in TRS Siła Ustroń sports club, while the remaining fifteen were physically inactive. The Functional Movement Screen (FMS) system was used to assess the level of motor ability, and four functional tests were used to measure the length of lower limbs muscles based on the use of V-Rippstein plurimeter. In addition to tests the students also filled out a questionnaire. Results: The results of the analysis showed that among the physically inactive pupils the muscle shortening occurred more frequently in comparison to the students who played volleyball. Moreover, the results of the FMS indicated that the young women who took up sports had a higher level of motor ability than their peers. Conclusions: Regular physical activity improves and maintains normal length of muscles of lower limbs.

Predictivity of International Physical Activity Questionnaire Short Form for 5-Year Incident Disability Among Japanese Older Adults

2021 ◽  
pp. 1-5
Author(s):  
Satoshi Kurita ◽  
Takehiko Doi ◽  
Kota Tsutsumimoto ◽  
Sho Nakakubo ◽  
Hideaki Ishii ◽  
...  
Keyword(s):  
Physical Activity ◽  
Older Adults ◽  
International Physical Activity Questionnaire ◽  
Short Form ◽  
Physically Active ◽  
Intensity Physical Activity ◽  
Vigorous Intensity ◽  
Japanese Older Adults ◽  
Activity Questionnaire ◽  
Physically Inactive

Background: This study aimed to examine whether physical activity measured using the International Physical Activity Questionnaire Short Form (IPAQ-SF) can predict incident disability in Japanese older adults. Methods: Community-dwelling older adults participated in a prospective cohort survey. The time spent in moderate- to vigorous-intensity physical activity was assessed at the survey baseline using the IPAQ-SF. The participants were categorized into those who spent ≥150 minutes per week (physically active) or <150 minutes per week (physically inactive) in moderate- to vigorous-intensity physical activity. Incident disability was monitored through Long-Term Care Insurance certification during a follow-up lasting 5 years. Results: Among the 4387 analyzable participants (mean age = 75.8 y, 53.5% female), the IPAQ-SF grouped 1577 (35.9%) and 2810 (64.1%) participants as those who were physically active and inactive, respectively. A log-rank test showed a significantly higher incidence of disability among the inactive group of participants (P < .001). The Cox proportional hazards model showed that physically inactive participants had a higher risk of incident disability than the physically active ones did, even after adjusting for covariates (hazard ratio, 1.24; 95% CI, 1.07–1.45, P < .001). Conclusions: Older adults identified as physically inactive using the IPAQ-SF had a greater risk of developing disabilities than those identified as physically active. The IPAQ-SF seems to be appropriate to estimate the incidence risk of disability.

Sign in / Sign up

Export Citation Format

Share Document