Display omitted
•Hybrid machine learning algorithms-based estimation method for body fat percentage.•Estimation of BFP with minimum feature selection with feature selection algorithm.•No need for ...equation, body fat percentage estimation.•The measurement cost has been reduced with the feature selection algorithm.•BPF measurement with a high accuracy rate with only one anthropometric measurement.
Before obesity treatment, body fat percentage (BFP) should be determined. BFP cannot be measured by weighing. The devices developed to produce solutions to this problem are called “Body Analysis Devices”. These devices are very costly. Therefore, more practical and cost-effective solutions are needed. This study aims to determine BFP using hybrid machine learning methods with high accuracy rate and minimum parameter. This study uses real data sets, which are 13 anthropometric measurements of individuals. Different feature groups were created with feature selection algorithm. In the next step, 4 different hybrid models were created by using MLFFNN, SVMs, and DT regression models. According to the results, BFP of individuals can be estimated with a correlation value of R=0.79 with one anthropometric measurement. The results show that the developed system can be used to estimate BFP in practice. Besides, the system can calculate BFP with just one anthropometric measurement without device requirement.
Introduction: The present is aimed to determine the effects of three different doses of Liraglutide (Saxenda) that are 0.6mg, 1.2mg and 1.8mg with and without exercises on obese population after 6 ...months of intervention. Methodology: A three arm randomized controlled trial was performed at Isra Univeristy Hospital, Hyderabad. A total of n=60 obese participants including both male and female were recruited and divided into two groups n=20 participants in each group. Each group was than further divided into two subgroups n=10 participants in each subgroup. Results: The analyses of the findings had revealed that n=22 participants included in the study were male whereas n=38 were female. The mean Body Mass Index (BMI) of the participants in group A at baseline was 29.95±1.35kg/m2, 30.21±1.56 kg/m2 and 29.54±2.33 kg/m2 in subgroup (i), (ii) and (iii) respectively whereas in group B the values of BMI at baseline were 30.25±1.56 kg/m2, 29.87±2.56 kg/m2 and 30.11±2.33 kg/m2 in subgroup (i), (ii) and (iii) respectively. In group C the values were 30.01±2.14 kg/m2, 28.59±2.22 kg/m2 and 30.58±1.98 kg/m2 in subgroup (i), (ii) and (iii) respectively. Conclusion: The findings revealed substantial differences in BMI and body fat percentage within each group from baseline through three and six months of intervention. Higher Liraglutide (Saxenda) dosages (1.8mg) resulted with greater decreases in BMI and body fat percentage than lower doses (0.6mg and 1.2mg). Keywords: obesity, body mass index, body fat percentage
Fat mass changes during menopause: a metaanalysis Ambikairajah, Ananthan; Walsh, Erin; Tabatabaei-Jafari, Hossein ...
American journal of obstetrics and gynecology,
November 2019, 2019-11-00, 20191101, Volume:
221, Issue:
5
Journal Article
Peer reviewed
Data: Fat mass has been shown to increase in aging women; however, the extent to which menopausal status mediates these changes remains unclear. The purpose of this review was to determine (1) how ...fat mass differs in quantity and distribution between premenopausal and postmenopausal women, (2) whether and how age and/or menopausal status moderates any observed differences, and (3) which type of fat mass measure is best suited to the detection of differences in fat mass between groups.
This review with metaanalyses is reported according to Metaanalysis of Observational Studies in Epidemiology guidelines.
Studies (published up to May 2018) were identified via PubMed to provide fat mass measures in premenopausal and postmenopausal women. We included 201 cross-sectional studies in the metaanalysis, which provided a combined sample size of 1,049,919 individuals and consisted of 478,734 premenopausal women and 571,185 postmenopausal women. Eleven longitudinal studies were included in the metaanalyses, which provided a combined sample size of 2472 women who were premenopausal at baseline and postmenopausal at follow up.
The main findings of this review were that fat mass significantly increased between premenopausal and postmenopausal women across most measures, which included body mass index (1.14 kg/m2; 95% confidence interval, 0.95–1.32 kg/m2), bodyweight (1 kg; 95% confidence interval, 0.44–1.57 kg), body fat percentage (2.88%; 95% confidence interval, 2.13–3.63%), waist circumference (4.63 cm; 95% confidence interval, 3.90–5.35 cm), hip circumference (2.01 cm; 95% confidence interval, 1.36–2.65 cm), waist-hip ratio (0.04; 95% confidence interval, 0.03–0.05), visceral fat (26.90 cm2; 95% confidence interval, 13.12–40.68), and trunk fat percentage (5.49%; 95% confidence interval, 3.91–7.06 cm2). The exception was total leg fat percentage, which significantly decreased (–3.19%; 95% confidence interval, –5.98 to –0.41%). No interactive effects were observed between menopausal status and age across all fat mass measures.
The change in fat mass quantity between premenopausal and postmenopausal women was attributable predominantly to increasing age; menopause had no significant additional influence. However, the decrease in total leg fat percentage and increase in measures of central fat are indicative of a possible change in fat mass distribution after menopause. These changes are likely to, at least in part, be due to hormonal shifts that occur during midlife when women have a higher androgen (ie, testosterone) to estradiol ratio after menopause, which has been linked to enhanced central adiposity deposition. Evidently, these findings suggest attention should be paid to the accumulation of central fat after menopause, whereas increases in total fat mass should be monitored consistently across the lifespan.
•Machine learning-based prediction model for body fat percentage (BFP).•Artificial intelligence-based BFP prediction model for men and women.•BFP prediction model with photoplethysmography ...signal.•Low-cost BFP prediction model.•High accuracy BFP prediction model.
Calculation of body fat percentage (BFP) is a frequently encountered problem in the literature. BFP is one of the most significant parameters which should be processed in body weight control programs. Anthropometric measurements and statistical methods are being used generally in the literature for BFP estimation. Artificial intelligence and gender-based models with a photoplethysmography signal (PPG) were proposed for BFP estimation in this study.
In the study, the PPG signal is divided into lower frequency bands, and 25 features are taken out from each frequency band. Artificial intelligence algorithms were created by reducing the extracted features with the help of a feature selection algorithm.
According to the results obtained, models with performance values of RMSE=0.35, R=1 for men, RMSE=0.87, R=1 for women were created.
In the best performing models, the PPG signal's high-frequency components are used for men, whereas the low-frequency band of the PPG signal is used for women. As a result, the proposed model in this study is considered to be used for BFP measurement.
•Artificial intelligence-based prediction model for body fat percentage (BFP).•Artificial intelligence-based BFP prediction model for men and women.•BFP prediction model with electrocardiography ...signal.•Low cost BFP prediction model with practical use.•BFP prediction model with high accuracy.
Body fat percentage (BFP) is a frequently used parameter in the assessment of body composition. The body is made up of fat, muscle and lean body tissues. Excess fat tissue in the body causes obesity. Obesity is a treatable disease that decreases the quality of life. Obesity can trigger ailments such as psychological disorders, cardiovascular diseases and respiratory and digestive problems. Dual energy X-ray absorptiometry gold standard method is laborious, costly and time consuming. For this reason, more practical methods are needed. The aim of this study is to develop BFP prediction models with gender-based electrocardiography (ECG) signal and machine learning methods.
In the study, 25 features were extracted from seven different QRS bands and filtered and unfiltered ECG signals. In addition, age, height and weight were used as features. Spearman feature selection algorithm was used to increase the performance.
The BFP prediction models developed have performance values of R=0.94 for men and R=0.93 for women and R=0.91 for all individuals. Feature selection algorithm helped increase performance.
According to the results, it is thought that ECG based BFP prediction models can be used in practice.
Resumen Introducción: estudiar el porcentaje de grasa corporal (%GC) en niños y adolescentes es muy relevante, puesto que un elevado nivel de grasa corporal en la infancia y la adolescencia ...representa sobrepeso y obesidad. Objetivo: identificar los indicadores antropométricos que se relacionan con el %GC y validar ecuaciones de regresión para predecir el %GC de niños y adolescentes a partir del uso de la absorciometría de rayos X de doble energía (DXA) como método de referencia. Métodos: se diseñó un estudio descriptivo (transversal) en 1126 escolares (588 hombres y 538 mujeres) de la región del Maule (Chile). El rango de edad oscila desde los 6,0 hasta los 17,9 años. Se evaluaron el peso, la estatura, dos pliegues cutáneos (tricipital y subescapular) y la circunferencia de la cintura (CC). Se calcularon el índice de masa corporal (IMC), el índice ponderal (IP) y el índice cintura-estatura (ICE). Se evaluó el porcentaje de grasa corporal (%GC) por medio del escaneo DXA. Resultados: las relaciones entre Σ (Tricipital + Subescapular), IP e ICE con el %GC (DXA) fueron de R2 = 52-54 % en hombres y R2 = 41-49 % en mujeres. Las ecuaciones generadas para los hombres fueron: %GC = 9,775 + (0,415 * (Tr + SE) + (35,084 * ICE) - (0,828 * edad), R2 = 70 %, y %GC = 20,720 + (0,492 * (Tr + SE) + (0,354 * IP) - (0,923 * edad), R2 = 68 %; y para mujeres: %GC = 8,608 + (0,291 * (Tr + SE) + (38,893 * ICE) - (0,176 * edad), R2 = 60 %, y %GC = 16,087 + (0,306 * (Tr + SE) + (0,818 * IP) - (0,300 * edad), R2 = 59 %. Conclusión: este estudio demostró que la sumatoria de los pliegues cutáneos tricipital y subescapular, el IP y el ICE son adecuados predictores del %GC. Estos indicadores permitieron desarrollar dos ecuaciones de regresión aceptables en términos de precisión y exactitud para predecir el %GC en niños y adolescentes de ambos sexos.
The caloric restrictions are necessary during the bodybuilder athlete preparation, especially when approaching the pre-contest phase. Although the refeed strategies for bodybuilders are current ...recent in the scientific literature, drastically reducing calories in the pre-competition phase linearly without periodization may does not guarantee a greater reduction in body fat and still being able harm the athlete's physical on-stage readiness.
Two cross-sectional studies (n = 42) and three case studies (n = 3) recent involved bodybuilder athletes aged between 21 and 32 years old who had 14–32 weeks, time involved the preparation phase and the pre-contest phase, to prepare himself and did not contain any refeeding strategy in their dietary protocol prescribed at work. These articles followed participants diets regarding the number of calories and macronutrients, where data collected were separated by the author himself and recorded in Excel spreadsheets for be mathematically calculated and subjectively evaluated.
Of the five studies that were read and organized it's noted apparently that a greater caloric deficit does not influence a greater substantial loss of fat percentage or body weight neither looks to show any numerical visual relationship with maintenance of fat-free mass.
Observationally, a severe caloric deficit without refeed strategies applied in pre-contest phase may not guarantee a greater the weight loss neither a greater reduction in the body fat percentage.