Artificial Intelligence in the Evaluation of Body Composition

2020 ◽  
Vol 24 (01) ◽  
pp. 030-037
Author(s):  
Benjamin Wang ◽  
Martin Torriani

AbstractBody composition entails the measurement of muscle and fat mass in the body and has been shown to impact clinical outcomes in various aspects of human health. As a result, the need is growing for reliable and efficient noninvasive tools to measure body composition. Traditional methods of estimating body composition, anthropomorphic measurements, dual-energy X-ray absorptiometry, and bioelectrical impedance, are limited in their application. Cross-sectional imaging remains the reference standard for body composition analysis and is accomplished through segmentation of computed tomography and magnetic resonance imaging studies. However, manual segmentation of images by an expert reader is labor intensive and time consuming, limiting its implementation in large-scale studies and in routine clinical practice. In this review, novel methods to automate the process of body composition measurement are discussed including the application of artificial intelligence and deep learning to tissue segmentation.

2014 ◽  
Vol 44 (2) ◽  
pp. 279-286 ◽  
Author(s):  
Francisco Teixeira Andrade ◽  
Márvio Lobão Teixeira de Abreu ◽  
João Batista Lopes ◽  
Agustinho Valente de Figueiredo ◽  
Maria de Nazaré Bona Alencar Araripe ◽  
...  

Body composition analysis is relevant to characterize the nutritional requirements and finishing phase of fish. The aim of this study was to investigate the relationship between ichthyometric (weight, total and standard length, density and yields), bromatological (fat, protein, ash and water content) and bioelectrical-impedance-analysis (BIA) (resistance, reactance, phase angle and composition indexes) variables in the hybrid tambatinga (Colossoma macropomum × Piaractus brachypomus). In a non-fertilized vivarium, 520 juveniles were housed and fed commercial rations. Then, 136 days after hatching (DAH), 15 fish with an average weight of 37.69 g and average total length of 12.96 cm were randomly chosen, anesthetized (eugenol) and subjected to the first of fourteen fortnightly assessments (BIA and biometry). After euthanasia, the following parts were weighed: whole carcass with the head, fillet, and skin (WC); fillet with skin (FS); and the remainder of the carcass with the head (CH). Together, FS and CH were ground and homogenized for the bromatological analyses. Estimates of the body composition and yields of tambatinga, with models including ichthyometric and BIA variables, showed correlation coefficients ranging from 0.81 (for the FS yield) to 1,00 (for the total ash). Similarly, models that included only BIA variables had correlation coefficients ranging from 0.81 (FS and CH yields) to 0.98 (for the total ash). Therefore, in tambatinga, the BIA technique allows the estimation of the yield of the fillet with skin and the body composition (water content, fat, ash, and protein). The best models combine ichthyometric and BIA variables.


2020 ◽  
Author(s):  
Hamidreza Pouragha ◽  
Hosein Kazemi ◽  
Gholamreza Pouryaghoub ◽  
Ramin Mehrdad

Abstract Background: Why is bodyweight not a predictor of lung function, however, height, sex, race, and age are predictors of lung capacity and function. In this study, we want to investigate the association between body composition and pulmonary function. And as much as possible, answer the question of why bodyweight is not predictive of lung function.Method: This cross-sectional study was performed among 2967 employees of Tehran University of Medical Sciences (TUMS) who participated in the TUMS Employees Cohort (TEC) study. The body composition of the participants was measured using the Bioelectrical Impedance Analysis (BIA) method. Anthropometric variables were also measured as a confounder. The pulmonary function of participants was assessed by a forced spirometry test.Results: The correlation of BIA values including fat-free mass and total body water with a pulmonary function such as FEV1, FVC, and FEF25-75 is higher than most anthropometric values such as weight, wrist circumference, and the waist to hip ratio. Also, in regression analysis, age and sex had an association with pulmonary function, but the weight did not show a significant relationship. On the other hand, fat-free mass and visceral fat were significantly associated with pulmonary function. One is direct and the other is inverse.Conclusion: The hypothesis that the results of this study created in the minds of the authors were that; The direct association of fat-free mass with pulmonary function may be ineffective by the inverse association of visceral fat with pulmonary function, leading to a lack of association between weight and pulmonary function.


2021 ◽  
pp. 345-352

Background. Body weight or BMI do not provide any information about the content of muscle tissue, water content, body fat and its distribution in the body. Thyroid dysfunction is associated with a change in body weight, but also its composition regardless of physical activity. Objective. The aim of the study was to compare the body composition of female patients diagnosed with Hashimoto's disease (HD) and the body composition of healthy women who have never been treated before due to thyroid diseases. Materials and methods. The study involved 47 women diagnosed with Hashimoto disease (HD) and 65 women declaring good health. Body mass and height and body composition analysis using bioelectrical impedance analysis were performed using the TANITA multi-frequency segmental body composition analyzer. Variables having a distribution similar to the normal distribution were analyzed by the analysis of variance (ANOVA), otherwise the Kruskal-Wallis test was used. Results. Women with Hashimoto disease were characterized by significantly higher values of body weight, and thus BMI index, than healthy women (respectively 73.64 kg vs. 64.36 kg, p <0.0001; 27.65 kg/m2 vs. 23.95 kg/m2, p <0.001).The problem of excess body fat in the body statistically significantly more often affected women with Hashimoto disease than healthy women (44.7% vs. 13.8%, p <0.001). Conclusions. The results regarding the weight and composition of the patients treated for thyroid disease indicate the need for further in-depth analyses. Even small abnormalities of the thyroid function in the range of reference values may result in the development of many adverse changes in the body.


Author(s):  
Mututho L. N. ◽  
Kiboi W. K. ◽  
Waihenya R. N.

Background: Research has shown that body composition is directly related to health. Altered body composition, can greatly increase the risks of conditions such as cardiovascular disease and diabetes. Bioelectrical Impedance Analysis fosters early detection of an improper balance in the body composition, which allows for earlier intervention and prevention.Methods: This was a cross sectional analysis of body composition for adults who volunteered to be screened during a Nutrition week in Kiambu County, Kenya. A total of 301 adults were included in the assessment. Body Mass Index (BMI) and Body composition (body fat %, bone mass, muscle mass, visceral fat and water %) were measured using bioelectrical impedance analysis.Results: The age of the participants ranged from 18-99 years (mean 42.19±16.57 years). Most of the participants were males (53.5%). More than half (53.2%) of the participants had a poor BMI, 37.2% had high total body fat percentage, 12.6% had excess levels of visceral fat and 26.6% had poor water hydration status. Age (OR=0.095; p value <0.001; CI 0.033-0272) and visceral fat (r=0.74; p value <0.001) were significantly associated with the BMI. Females had a significantly higher BMI (P <0.001). Visceral fat was also positively correlated with age: r=0.74; P value <0.001.Conclusions: Sex, age and BMI were important determinants of body composition. Increased physical activity, appropriate dietary practices are crucial in maintaining a healthy BMI and body composition. For timely intervention regular nutrition screening should be promoted among different populations.


Author(s):  
Leena Raje ◽  
Pallavi Mhaskar

Background: Diabetes mellitus being a metabolic disorder lot of alteration takes place in body composition parameters such increase in fat mass, decrease in muscle mass, increase visceral fat. With advancing age, the predominant feature develops which is more prevalent in diabetes. These changes in body composition should be monitored. The changes if monitored at an early age, can be well managed and proper interventions can be developed.  The study was conducted to observe the changes taking place in the body composition parameters in individuals with type II diabetes with varied duration of the disease.Methods: This cross- sectional study was done in 228 type II diabetic subjects from the clinics of the Mumbai and Pune. The baseline data was collected from the all the subjects coming to the clinic through the general questionnaire, Anthropometric measurements and Body composition analysis was done by the BIA principle-based Analyser.  Then these subjects were distributed according to the duration of the disease and then analysed.  The data was analysed using SPSS version 22 and mean values p values were obtained.Results: The results showed that there is statistically significant increase in fat mass, visceral fat and decrease in muscle mass.Conclusions: There is change in body composition parameters like decrease in muscle mass, increase in fat and visceral fat along with the increase in the duration of the disease.


2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Michelle Bai ◽  
Daniella Susic ◽  
Anthony J. O’Sullivan ◽  
Amanda Henry

Introduction. Bioelectrical impedance analysis (BIA) is a rapid and noninvasive method of body composition analysis; however, reproducibility between BIA instruments in pregnancy is uncertain. Adverse maternal body composition has been linked to pregnancy complications including gestational diabetes mellitus (GDM). This study aimed to evaluate the reproducibility of three BIA instruments in pregnancy and analyse the relationship between the body composition and the GDM risk. Methods. A prospective cohort (n = 117) of women with singleton pregnancies participating in the Microbiome Understanding in Maternity Study (MUMS) at St. George Hospital, Sydney, Australia. Anthropometric measurements and BIA body composition were measured at ≤13 weeks (T1), 20–24 weeks (T2), and 32–36 weeks (T3) of gestation. Body fat percentage (BFP), total body water (TBW), and impedance were estimated by three BIA instruments: Bodystat 1500, RJL Quantum III, and Tanita BC-587. GDM status was recorded after 75 g oral glucose tolerance test was performed at 28 weeks or earlier. Agreement between BIA instruments was assessed using Bland–Altman analysis. Logistic regression modelling explored associations of BFP with GDM. Results. Method comparison reproducibility between Bodystat and RJL was stronger than between Bodystat and Tanita for both BFP and TBW% at all three time points. RJL overestimated BFP on average by 3.3% (p<0.001), with limits of agreement within ±5% for all trimesters. Average BFP was not significantly different between Tanita and Bodystat although limits of agreement exceeded ±5%. GDM diagnosis was independently associated with increased BFP in T1 (adjusted OR 1.117 per 1% increase; 95% CI 1.020–1.224; p=0.017) and in T2 (adjusted OR 1.113 per 1% increase; 95% CI 1.010–1.226; p=0.031) and with Asian ethnicity in all models (OR 7.4–8.1). Conclusion. Reproducibility amongst instruments was moderate; therefore, interchangeability between instruments, particularly for research purposes, cannot be assumed. In this cohort, GDM risk was modestly associated with increasing BFP and strongly associated with Asian ethnicity.


DICP ◽  
1989 ◽  
Vol 23 (7-8) ◽  
pp. 548-555 ◽  
Author(s):  
Barbara J. Zarowitz ◽  
Alison M. Pilla

Bioelectrical impedance (BI) relies on the conduction of a low-voltage alternating current through the body. Lean tissue and fluids containing electrolytes conduct the current and cell membranes serve as capacitors and account for capacitive resistance. Fat and bone are poor conductors. Measurement of the voltage drop of the applied current yields resistance (R) and reactance (Xc). R and Xc are used with height, weight, age, and gender in a number of multiple regression relationships to predict body composition compartments such as fat-free mass, lean body mass, extracellular mass, and body cell mass. The technique has been compared with and validated against traditional measures of body composition analysis. In clinical practice, BI has been used to monitor fluid status in burn and dialysis patients, assess changes of body cell mass with nutritional repletion, and predict pharmacokinetic parameters and dose of theophylline and aminoglycoside antibiotics. BI is a noninvasive, safe, rapid, and reproducible technique with exciting potential in clinical practice.


2021 ◽  
Vol 19 (1) ◽  
Author(s):  
Luigi Barrea ◽  
Marianna Donnarumma ◽  
Sara Cacciapuoti ◽  
Giovanna Muscogiuri ◽  
Ludovica De Gregorio ◽  
...  

Abstract Background Acne is a chronic, inflammatory and debilitating skin disorder. Dietary factors and nutritional status are among the exacerbating factors of acne. Phase angle (PhA), a direct measure of Bioelectrical Impedance Analysis (BIA), represents an indicator of the chronic inflammatory state. The Mediterranean diet (MD) is a healthy dietary pattern that can exert anti-inflammatory effects in several inflammatory diseases. We aimed to investigate the difference in PhA and adherence to the MD and their associations with the severity of acne in a sample of naïve treatment patients with acne compared to control group. Materials In this cross-sectional, case–control, observational study, we enrolled 51 patients with acne and 51 control individuals. Body composition was evaluated by a BIA phase-sensitive system (50 kHz BIA 101 RJL, Akern Bioresearch, Florence, Italy, Akern). For adherence to the MD, we have used the PREvención con DIeta MEDiterránea (PREDIMED) questionnaire. The clinical severity of acne was assessed by using the global acne grading system (GAGS), a quantitative scoring system to assess acne severity. Results Patients with acne had a worse body composition, in particular smaller PhA (p = 0.003), and a lower adherence to the MD (p < 0.001) than the control group, in spite of no differences in gender, age and BMI between the two groups. Stratifying patients with acne according to GAGS categories, both PhA (p = 0.006) and PREDIMED score (p = 0.007) decreased significantly in severe acne than mild/moderate acne. The GAGS score was negative correlations with PhA (r = − 0.478, p < 0.001) and PREDIMED score (r = − 0.504, p < 0.001). The results of the multivariate analysis showed PhA and PREDIMED score were the major determinants of GAGS score (p < 0.001). The receiver operator characteristic (ROC) analysis reporting a value of PhA of ≤ 6.1° and a PREDIMED score of ≤ 9 identified patients with acne with the highest clinical severity of the disease. Conclusions Novel correlations were reported between PhA and the degree of adherence to the MD with acne severity. Of interest, PhA and PREDIMED scores might represent possible markers of the severity of acne in a clinical setting. This study highlights how a cooperation between dermatologist and nutritionists might provide a combination key in the complex management of acne patients.


2018 ◽  
Author(s):  
Carla M Prado ◽  
Camila LP Oliveira ◽  
M Cristina Gonzalez ◽  
Steven B Heymsfield

Body composition assessment is an important tool in both clinical and research settings able to characterize the nutritional status of individuals in various physiologic and pathologic conditions. Health care professionals can use the information acquired by body composition analysis for the prevention and treatment of diseases, ultimately improving health status. Here we describe commonly used techniques to assess body composition in healthy individuals, including dual-energy x-ray absorptiometry, bioelectrical impedance analysis, air displacement plethysmography, and ultrasonography. Understanding the key underlying concept(s) of each assessment method, as well as its advantages and limitations, facilitates selection of the method of choice and the method of the compartment of interest. This review contains 5 figures, 3 tables and 52 references Key words: air displacement plethysmography, bioelectrical impedance analysis, body composition, disease, dual-energy x-ray absorptiometry, health, muscle mass, nutritional status, obesity, sarcopenia, ultrasound fat mass


Sign in / Sign up

Export Citation Format

Share Document