A machine learning approach relating 3D body scans to body composition in humans

GDM-BC: Non-invasive body composition dataset for intelligent prediction of Gestational Diabetes Mellitus

Gestational Diabetes Mellitus (GDM) refers to any degree of impaired glucose tolerance with onset or first recognition during pregnancy. As a high-prevalence disease, GDM damages the health of both pregnant women and fetuses in the short and long term. Accurate and cost-effective recognition of GDM is quite crucial to reduce the risk and economic pressure of this disease. However, existing datasets for the prediction of GDM primarily focus on clinical and biochemical parameters, including a mass of invasive indexes. These variables are hard to obtain and do not always perform well in the prediction of GDM. In this paper, we introduce a large-scale non-invasive body composition dataset, called GDM-BC, for intelligent risk prediction of GDM. Specifically, it contains a cohort of 39,438 pregnant women, of whom 7777 (19.7%) were subsequently diagnosed with GDM. Besides, our dataset includes a large number of body composition indexes that can be acquired non-invasively. In addition, we perform several traditional machine learning and deep learning methods on the GDM-BC dataset, among which the Residual Attention Fully Connected Network (RAFNet) performs the best, achieving an AUC (area under the ROC curve) of 0.920. The results show that our dataset is marvelous and creates a new perspective on the prediction of GDM. Our models may offer an opportunity to establish a cost-effective screening approach for identifying low-risk pregnant women based on body composition data. We believe that our proposed GDM-BC dataset will advance future research on risk prediction for GDM, as well as provide new insights for intelligent prediction of other high-incidence pregnancy-related diseases such as gestational hypertension.

D3BT: Dynamic 3D Body Transformer for Body Fat Percentage Assessment

3D body scan has been adopted for body composition assessment due to its ability to accurately capture body shape measurements. However, the complexity of mesh representation and the lack of fine-shape descriptors limit its applications in body fat percentage analysis. Most studies rely on algorithms applied to anthropometric values derived from 3D scans, such as multiple girth measurements, which fail to account for the body's detailed shape. To address these issues, we explore the feasibility of using point cloud representation. However, few existing point-based methods are aimed at the human body or regression tasks. In this study, we introduce a new model, D3BT, which utilizes a transformer-based network on the body point cloud to efficiently learn shape information for regional and global fat percentage regression tasks. The model dynamically divides the points into voxels for enhanced transformer training, providing higher density and better alignment across different subjects, which is more suitable for body shape learning. We evaluate various models for predicting body fat percentage from 3D body scans, using ground truth data from dual-energy X-ray absorptiometry (DXA) reports. Compared to traditional methods that depend on anthropometric measurements and other point-based approaches, the proposed model shows superior results. In extensive experiments, the model reduces the Root Mean Square Error (RMSE) by an average of 10.30% and achieves an average R-squared score of 0.86.

Essential dataset features in a successful obesity registry: a systematic review

BACKGROUND

The prevalence of obesity and the diversity of available treatments makes the development of a national obesity registry desirable. To do this, it is essential to design a minimal dataset to meet the needs of a registry. This review aims to identify the essential elements of a successful obesity registry.

METHODS

We conducted a systematic literature review adhering to the Preferred Reporting Items for Systematic Review and Meta-Analysis recommendations. Google Scholar, Scopus and PubMed databases and Google sites were searched to identify articles containing obesity or overweight registries or datasets of obesity. We included English articles up to January 2023.

RESULTS

A total of 82 articles were identified. Data collection of all registries was carried out via a web-based system. According to the included datasets, the important features were as follows: demographics, anthropometrics, medical history, lifestyle assessment, nutritional assessment, weight history, clinical information, medication history, family medical history, prenatal history, quality-of-life assessment and eating disorders.

CONCLUSIONS

In this study, the essential features in the obesity registry dataset were demographics, anthropometrics, medical history, lifestyle assessment, nutritional assessment, weight history and clinical analysis items.

Optimal Instruments for Measurement of Dietary Intake, Physical Activity, and Sleep Among Adults in Population-Based Studies: Report of a National Heart, Lung, and Blood Institute Workshop

The National Heart, Lung, and Blood Institute convened a virtual workshop in September 2022 to discuss "Optimal Instruments for Measurement of Diet, Physical Activity, and Sleep." This report summarizes the proceedings, identifying current research gaps and future directions for measuring different lifestyle behaviors in adult population-based studies. Key discussions centered on integrating report-based methods, like questionnaires, with device-based assessments, including wearables and physiological measures such as biomarkers and omics to enhance self-reported metrics and better understand the underlying biologic mechanisms of chronic diseases. Emphasis was placed on the need for data harmonization, including the adoption of standard terminology, reproducible metrics, and accessible raw data, to enhance the analysis through artificial intelligence and machine learning techniques. The workshop highlighted the importance of standardizing procedures for integrated behavioral phenotypes using time-series data. These efforts aim to refine data accuracy and comparability across studies and populations, thereby advancing our understanding of lifestyle behaviors and their impact on chronic disease outcomes over the life course.

Combination of Machine Learning Techniques to Predict Overweight/Obesity in Adults

(1) Background: Artificial intelligence using machine learning techniques may help us to predict and prevent obesity. The aim was to design an interpretable prediction algorithm for overweight/obesity risk based on a combination of different machine learning techniques. (2) Methods: 38 variables related to sociodemographic, lifestyle, and health aspects from 1179 residents in Madrid were collected and used to train predictive models. Accuracy, precision, and recall metrics were tested and compared between nine classical machine learning techniques and the predictive model based on a combination of those classical machine learning techniques. Statistical validation was performed. The shapely additive explanation technique was used to identify the variables with the greatest impact on weight gain. (3) Results: Cascade classifier model combining gradient boosting, random forest, and logistic regression models showed the best predictive results for overweight/obesity compared to all machine learning techniques tested, reaching an accuracy of 79%, precision of 84%, and recall of 89% for predictions for weight gain. Age, sex, academic level, profession, smoking habits, wine consumption, and Mediterranean diet adherence had the highest impact on predicting obesity. (4) Conclusions: A combination of machine learning techniques showed a significant improvement in accuracy to predict risk of overweight/obesity than machine learning techniques separately.

Revisiting the beyond BMI paradigm in excess weight diagnosis and management: A call to action

Adolphe Quételet, a 19th-century Belgian sociologist and statistician, pioneered the incorporation of statistics into social sciences. He initiated the development of anthropometry since he was interested in identifying the proportions of the 'ideal man'. He devised a ratio between weight and height, originally termed the Quételet Index, and today widely known and used as the body mass index or BMI. In 1835, he demonstrated that a normal curve accommodates the distribution of human traits articulating his reasoning on human variance around the average. Quételet's long-lasting legacy of the establishment of a simple measure to classify people's weight relative to an ideal for their height endures today with minor variations having dramatically influenced public health agendas. While being very useful, the limitations of the BMI are well known. Thus, revisiting the beyond BMI paradigm is a necessity in the era of precision medicine with morphofunctional assessment representing the way forward via incorporation of body composition and functionality appraisal. While healthcare systems were originally designed to address acute illnesses, today's demands require a radical rethinking together with an original reappraisal of our diagnosis and treatment approaches from a multidimensional perspective. Embracing new methodologies is the way forward to advance the field, gain a closer look at the underlying pathophysiology of excess weight, keep the spotlight on improving diagnostic performance and demonstrate its clinical validity. In order to provide every patient with the most accurate diagnosis together with the most appropriate management, a high degree of standardization and personalization is needed.

Mobile phone applications for 3-dimensional scanning and digital anthropometry: a precision comparison with traditional scanners

BACKGROUND

The precision of digital anthropometry through 3-dimensional (3D) scanning has been established for relatively large, expensive, non-portable systems. The comparative performance of modern mobile applications is unclear.

SUBJECTS/METHODS

Forty-six adults (age: 23.3 ± 5.3 y; BMI: 24.4 ± 4.1 kg/m2) were assessed in duplicate using: (1) a mobile phone application capturing two individual 2D images, (2) a mobile phone application capturing serial images collected during a subject's complete rotation, (3) a traditional scanner with a time of flight infrared sensor collecting visual data from a subject being rotated on a mechanical turntable, and (4) a commercial measuring booth with structured light technology using 20 infrared depth sensors positioned in the booth. The absolute and relative technical error of measurement (TEM) and intraclass correlation coefficient (ICC) for each method were established.

RESULTS

Averaged across circumferences, the absolute TEM, relative TEM, and ICC were (1) 0.9 cm, 1.5%, and 0.975; (2) 0.5 cm, 0.9%, and 0.986; (3) 0.8 cm, 1.5%, and 0.974; and (4) 0.6 cm, 1.1%, and 0.985. For total body volume, these values were (1) 2.2 L, 3.0%, and 0.978; (2) 0.8 L, 1.1%, and 0.997; (3) 0.7 L, 0.9%, and 0.998; and (4) 0.8 L, 1.1%, and 0.996, with segmental volumes demonstrating higher relative errors.

CONCLUSION

A 3D scanning mobile phone application involving full rotation of subjects in front of a smartphone camera exhibited similar reliability to larger, less portable, more expensive 3D scanners. In contrast, larger errors were observed for a mobile scanning application utilizing two 2D images, although the technical errors were acceptable for some applications.

Patient perceptions of three-dimensional (3D) surface imaging technology and traditional methods used to assess anthropometry

Background

Obesity and overweight are commonplace, yet attrition rates in weight management clinics are high. Traditional methods of body measurement may be a deterrent due to invasive and time-consuming measurements and negative experiences of how data are presented back to individuals. Emerging new technologies, such as three-dimensional (3D) surface imaging technology, might provide a suitable alternative. This study aimed to understand acceptability of traditional and 3D surface imaging-based body measures, and whether perceptions differ between population groups.

Methods

This study used a questionnaire to explore body image, body measurement and shape, followed by a qualitative semi-structured interview and first-hand experience of traditional and 3D surface imaging-based body measures.

Results

49 participants responded to the questionnaire and 26 participants attended for the body measurements and interview over a 2-month period. There were 3 main themes from the qualitative data 1) Use of technology, 2) Participant experience, expectations and perceptions and 3) Perceived benefits and uses.

Conclusion

From this study, 3D-surface imaging appeared to be acceptable to patients as a method for anthropometric measurements, which may reduce anxiety and improve attrition rates in some populations. Further work is required to understand the scalability, and the role and implications of these technologies in weight management practice. (University Research Ethics Committee reference number ER41719941).

Phenomic Imaging

Human phenomics is defined as the comprehensive collection of observable phenotypes and characteristics influenced by a complex interplay among factors at multiple scales. These factors include genes, epigenetics at the microscopic level, organs, microbiome at the mesoscopic level, and diet and environmental exposures at the macroscopic level. "Phenomic imaging" utilizes various imaging techniques to visualize and measure anatomical structures, biological functions, metabolic processes, and biochemical activities across different scales, both in vivo and ex vivo. Unlike conventional medical imaging focused on disease diagnosis, phenomic imaging captures both normal and abnormal traits, facilitating detailed correlations between macro- and micro-phenotypes. This approach plays a crucial role in deciphering phenomes. This review provides an overview of different phenomic imaging modalities and their applications in human phenomics. Additionally, it explores the associations between phenomic imaging and other omics disciplines, including genomics, transcriptomics, proteomics, immunomics, and metabolomics. By integrating phenomic imaging with other omics data, such as genomics and metabolomics, a comprehensive understanding of biological systems can be achieved. This integration paves the way for the development of new therapeutic approaches and diagnostic tools.

Associations between 3D surface scanner derived anthropometric measurements and body composition in a cross-sectional study

BACKGROUND

3D laser-based photonic scanners are increasingly used in health studies to estimate body composition. However, too little is known about whether various 3D body scan measures estimate body composition better than single standard anthropometric measures, and which body scans best estimate it. Furthermore, little is known about differences by sex and age.

METHODS

105 men and 96 women aged between 18 and 90 years were analysed. Bioelectrical Impedance Analysis was used to estimate whole relative fat mass (RFM), visceral adipose tissue (VAT) and skeletal muscle mass index (SMI). An Anthroscan VITUSbodyscan was used to obtain 3D body scans (e.g. volumes, circumferences, lengths). To reduce the number of possible predictors that could predict RFM, VAT and SMI backward elimination was performed. With these selected predictors linear regression on the respective body compositions was performed and the explained variations were compared with models using standard anthropometric measurements (Body Mass Index (BMI), waist circumference (WC) and waist-to-height-ratio (WHtR)).

RESULTS

Among the models based on standard anthropometric measures, WC performed better than BMI and WHtR in estimating body composition in men and women. The explained variations in models including body scan variables are consistently higher than those from standard anthropometrics models, with an increase in explained variations between 5% (RFM for men) and 10% (SMI for men). Furthermore, the explained variation of body composition was additionally increased when age and lifestyle variables were added. For each of the body composition variables, the number of predictors differed between men and women, but included mostly volumes and circumferences in the central waist/chest/hip area and the thighs.

CONCLUSIONS

3D scan models performed better than standard anthropometric measures models to predict body composition. Therefore, it is an advantage for larger health studies to look at body composition more holistically using 3D full body surface scans.

Translating digital anthropometry measurements obtained from different 3D body image scanners

BACKGROUND

Body image scanners are used in industry and research to reliably provide a wealth of anthropometric measurements within seconds. The demonstrated utility of the scanners drives the current proliferation of more commercially available devices that rely on their own reference body sites and proprietary algorithms to output anthropometric measurements. Since each scanner relies on its own algorithms, measurements obtained from different scanners cannot directly be combined or compared.

OBJECTIVES

To develop mathematical models that translate anthropometric measurements between the three popular commercially available scanners.

METHODS

A unique database that contained 3D scanner measurements in the same individuals from three different scanners (Styku, Human Solutions, and Fit3D) was used to develop linear regression models that translate anthropometric measurements between each scanner. A limits of agreement analysis was performed between Fit3D and Styku against Human Solutions measurements and the coefficient of determination, bias, and 95% confidence interval were calculated. The models were then applied to normalized scanner data from four different studies to compare the results of a k-means cluster analysis between studies. A scree plot was used to determine the optimal number of clusters derived from each study.

RESULTS

Correlations ranged between R2 = 0.63 (Styku and Human Solutions mid-thigh circumference) to R2 = 0.97 (Human Solutions and Fit3D neck circumference). In general, Fit3D had better agreement with Human Solutions compared to Styku. The widest disagreement was found in chest circumference (Fit3D (bias = 2.30, 95% CI = [-3.83, 8.43]) and Styku (bias = -5.60, 95% CI = [-10.98, -0.22]). The optimal number of body shape clusters in each of the four studies was consistently 5.

CONCLUSIONS

The newly developed models that translate measurements between the scanners Styku and Fit3D to predict Human Solutions measurements make it possible to standardize data between scanners allowing for data pooling and comparison.

Artificial intelligence and body composition

AIMS

Although obesity is associated with chronic disease, a large section of the population with high BMI does not have an increased risk of metabolic disease. Increased visceral adiposity and sarcopenia are also risk factors for metabolic disease in people with normal BMI. Artificial Intelligence (AI) techniques can help assess and analyze body composition parameters for predicting cardiometabolic health. The purpose of the study was to systematically explore literature involving AI techniques for body composition assessment and observe general trends.

METHODS

We searched the following databases: Embase, Web of Science, and PubMed. There was a total of 354 search results. After removing duplicates, irrelevant studies, and reviews(a total of 303), 51 studies were included in the systematic review.

RESULTS

AI techniques have been studied for body composition analysis in the context of diabetes mellitus, hypertension, cancer and many specialized diseases. Imaging techniques employed for AI methods include CT (Computerized Tomography), MRI (Magnetic Resonance Imaging), ultrasonography, plethysmography, and EKG(Electrocardiogram). Automatic segmentation of body composition by deep learning with convolutional networks has helped determine and quantify muscle mass. Limitations include heterogeneity of study populations, inherent bias in sampling, and lack of generalizability. Different bias mitigation strategies should be evaluated to address these problems and improve the applicability of AI to body composition analysis.

CONCLUSIONS

AI assisted measurement of body composition might assist in improved cardiovascular risk stratification when applied in the appropriate clinical context.

Machine learning-based obesity classification considering 3D body scanner measurements

Obesity can cause various diseases and is a serious health concern. BMI, which is currently the popular measure for judging obesity, does not accurately classify obesity; it reflects the height and weight but ignores the characteristics of an individual's body type. In order to overcome the limitations of classifying obesity using BMI, we considered 3-dimensional (3D) measurements of the human body. The scope of our study was limited to Korean subjects. In order to expand 3D body scan data clinically, 3D body scans, Dual-energy X-ray absorptiometry, and Bioelectrical Impedance Analysis data was collected pairwise for 160 Korean subjects. A machine learning-based obesity classification framework using 3D body scan data was designed, validated through Accuracy, Recall, Precision, and F1 score, and compared with BMI and BIA. In a test dataset of 40 people, BMI had the following values: Accuracy: 0.529, Recall: 0.472, Precision: 0.458, and F1 score: 0.462, while BIA had the following values: Accuracy: 0.752, Recall: 0.742, Precision: 0.751, and F1 score: 0.739. Our proposed model had the following values: Accuracy: 0.800, Recall: 0.767, Precision: 0.842, and F1 score: 0.792. Thus, our accuracy was higher than BMI as well as BIA. Our model can be used for obesity management through 3D body scans.

Military Body Composition Standards and Physical Performance: Historical Perspectives and Future Directions

ABSTRACT

Harty, PS, Friedl, KE, Nindl, BC, Harry, JR, Vellers, HL, and Tinsley, GM. Military body composition standards and physical performance: historical perspectives and future directions. J Strength Cond Res 36(12): 3551-3561, 2022-US military physique and body composition standards have been formally used for more than 100 years. These metrics promote appropriate physical fitness, trim appearance, and long-term health habits in soldiers, although many specific aspects of these standards have evolved as evidence-based changes have emerged. Body composition variables have been shown to be related to many physical performance outcomes including aerobic capacity, muscular endurance, strength and power production, and specialized occupational tasks involving heavy lifting and load carriage. Although all these attributes are relevant, individuals seeking to improve military performance should consider emphasizing strength, hypertrophy, and power production as primary training goals, as these traits appear vital to success in the new Army Combat Fitness Test introduced in 2020. This fundamental change in physical training may require an adjustment in body composition standards and methods of measurement as physique changes in modern male and female soldiers. Current research in the field of digital anthropometry (i.e., 3-D body scanning) has the potential to dramatically improve performance prediction algorithms and potentially could be used to inform training interventions. Similarly, height-adjusted body composition metrics such as fat-free mass index might serve to identify normal weight personnel with inadequate muscle mass, allowing for effective targeted nutritional and training interventions. This review provides an overview of the origin and evolution of current US military body composition standards in relation to military physical readiness, summarizes current evidence relating body composition parameters to aspects of physical performance, and discusses issues relevant to the emerging modern male and female warrior.

Machine Learning Enabled 3D Body Measurement Estimation Using Hybrid Feature Selection and Bayesian Search

The 3D body scan technology has recently innovated the way of measuring human bodies and generated a large volume of body measurements. However, one inherent issue that plagues the use of the resultant database is the missing data usually caused by using automatic data extractions from the 3D body scans. Tedious extra efforts have to be made to manually fill the missing data for various applications. To tackle this problem, this paper proposes a machine learning (ML)-based approach for 3D body measurement estimation while considering the measurement (feature) importance. The proposed approach selects the most critical features to reduce the algorithm input and to improve the ML method performance. In addition, a Bayesian search is further used in fine-tuning the hyperparameters to minimize the mean square error. Two distinct ML methods, i.e., Random Forest and XGBoost, are used and tested on a real-world dataset that contains 3D body scans of 212 participants in the Kansas-Missouri area of the United States. The results show the effectiveness of the proposed methods with roughly 3% of Mean Absolute Percentage Errors in estimating the missing data. The two ML methods with the proposed hybrid feature selection and the Baysian search are comprehensively compared. The comparative results suggest that the Random Forest method performs better than the XGBoost counterpart in filling missing 3D body measurements.

Modelling of human torso shape variation inferred by geometric morphometrics

Traditional body measurement techniques are commonly used to assess physical health; however, these approaches do not fully represent the complex shape of the human body. Three-dimensional (3D) imaging systems capture rich point cloud data that provides a representation of the surface of 3D objects and have been shown to be a potential anthropometric tool for use within health applications. Previous studies utilising 3D imaging have only assessed body shape based on combinations and relative proportions of traditional body measures, such as lengths, widths and girths. Geometric morphometrics (GM) is an established framework used for the statistical analysis of biological shape variation. These methods quantify biological shape variation after the effects of non-shape variation-location, rotation and scale-have been mathematically held constant, otherwise known as the Procrustes paradigm. The aim of this study was to determine whether shape measures, identified using geometric morphometrics, can provide additional information about the complexity of human morphology and underlying mass distribution compared to traditional body measures. Scale-invariant features of torso shape were extracted from 3D imaging data of 9,209 participants form the LIFE-Adult study. Partial least squares regression (PLSR) models were created to determine the extent to which variations in human torso shape are explained by existing techniques. The results of this investigation suggest that linear combinations of body measures can explain 49.92% and 47.46% of the total variation in male and female body shape features, respectively. However, there are also significant amounts of variation in human morphology which cannot be identified by current methods. These results indicate that Geometric morphometric methods can identify measures of human body shape which provide complementary information about the human body. The aim of future studies will be to investigate the utility of these measures in clinical epidemiology and the assessment of health risk.

A systematic literature review on obesity: Understanding the causes & consequences of obesity and reviewing various machine learning approaches used to predict obesity

Obesity is considered a principal public health concern and ranked as the fifth foremost reason for death globally. Overweight and obesity are one of the main lifestyle illnesses that leads to further health concerns and contributes to numerous chronic diseases, including cancers, diabetes, metabolic syndrome, and cardiovascular diseases. The World Health Organization also predicted that 30% of death in the world will be initiated with lifestyle diseases in 2030 and can be stopped through the suitable identification and addressing of associated risk factors and behavioral involvement policies. Thus, detecting and diagnosing obesity as early as possible is crucial. Therefore, the machine learning approach is a promising solution to early predictions of obesity and the risk of overweight because it can offer quick, immediate, and accurate identification of risk factors and condition likelihoods. The present study conducted a systematic literature review to examine obesity research and machine learning techniques for the prevention and treatment of obesity from 2010 to 2020. Accordingly, 93 papers are identified from the review articles as primary studies from an initial pool of over 700 papers addressing obesity. Consequently, this study initially recognized the significant potential factors that influence and cause adult obesity. Next, the main diseases and health consequences of obesity and overweight are investigated. Ultimately, this study recognized the machine learning methods that can be used for the prediction of obesity. Finally, this study seeks to support decision-makers looking to understand the impact of obesity on health in the general population and identify outcomes that can be used to guide health authorities and public health to further mitigate threats and effectively guide obese people globally.

Associations between relative body fat and areal body surface roughness characteristics in 3D photonic body scans-a proof of feasibility

INTRODUCTION

A reliable and accurate estimate of the percentage and distribution of adipose tissue in the human body is essential for evaluating the risk of developing chronic and noncommunicable diseases. A precise and differentiated method, which at the same time is fast, noninvasive, and straightforward to perform, would, therefore, be desirable. We sought a new approach to this research area by linking a person's relative body fat with their body surface's areal roughness characteristics.

MATERIALS AND METHODS

For this feasibility study, we compared areal surface roughness characteristics, assessed from 3D photonic full-body scans of 76 Swiss young men, and compared the results with body impedance-based estimates of relative body fat. We developed an innovative method for characterizing the areal surface roughness distribution of a person's entire body, in a similar approach as it is currently used in geoscience or material science applications. We then performed a statistical analysis using different linear and stepwise regression models.

RESULTS

In a stepwise regression analysis of areal surface roughness frequency tables, a combination of standard deviation, interquartile range, and mode showed the best association with relative body fat (R² = 0.55, p < 0.0001). The best results were achieved by calculating the arithmetic mean height, capable of explaining up to three-quarters of the variance in relative body fat (R² = 0.74, p < 0.001).

DISCUSSION AND CONCLUSION

This study shows that areal surface roughness characteristics assessed from 3D photonic whole-body scans associate well with relative body fat, therefore representing a viable new approach to improve current 3D scanner-based methods for determining body composition and obesity-associated health risks. Further investigations may validate our method with other data or provide a more detailed understanding of the relation between the body's areal surface characteristics and adipose tissue distribution by including larger and more diverse populations or focusing on particular body segments.

How shape-based anthropometry can complement traditional anthropometric techniques: a cross-sectional study

Manual anthropometrics are used extensively in medical practice and epidemiological studies to assess an individual's health. However, traditional techniques reduce the complicated shape of human bodies to a series of simple size measurements and derived health indices, such as the body mass index (BMI), the waist-hip-ratio (WHR) and waist-by-height0.5 ratio (WHT.5R). Three-dimensional (3D) imaging systems capture detailed and accurate measures of external human form and have the potential to surpass traditional measures in health applications. The aim of this study was to investigate how shape measurement can complement existing anthropometric techniques in the assessment of human form. Geometric morphometric methods and principal components analysis were used to extract independent, scale-invariant features of torso shape from 3D scans of 43 male participants. Linear regression analyses were conducted to determine whether novel shape measures can complement anthropometric indices when estimating waist skinfold thickness measures. Anthropometric indices currently used in practice explained up to 52.2% of variance in waist skinfold thickness, while a combined regression model using WHT.5R and shape measures explained 76.5% of variation. Measures of body shape provide additional information regarding external human form and can complement traditional measures currently used in anthropometric practice to estimate central adiposity.

Multiple measures derived from 3D photonic body scans improve predictions of fat and muscle mass in young Swiss men

INTRODUCTION

Digital tools like 3D laser-based photonic scanners, which can assess external anthropometric measurements for population based studies, and predict body composition, are gaining in importance. Here we focus on a) systematic deviation between manually determined and scanned standard measurements, b) differences regarding the strength of association between these standard measurements and body composition, and c) improving these predictions of body composition by considering additional scan measurements.

METHODS

We analysed 104 men aged 19-23. Bioelectrical Impedance Analysis was used to estimate whole body fat mass, visceral fat mass and skeletal muscle mass (SMM). For the 3D body scans, an Anthroscan VITUSbodyscan was used to automatically obtain 90 body shape measurements. Manual anthropometric measurements (height, weight, waist circumference) were also taken.

RESULTS

Scanned and manually measured height, waist circumference, waist-to-height-ratio, and BMI were strongly correlated (Spearman Rho>0.96), however we also found systematic differences. When these variables were used to predict body fat or muscle mass, explained variation and prediction standard errors were similar between scanned and manual measurements. The univariable predictions performed well for both visceral fat (r2 up to 0.92) and absolute fat mass (AFM, r2 up to 0.87) but not for SMM (r2 up to 0.54). Of the 90 body scanner measures used in the multivariable prediction models, belly circumference and middle hip circumference were the most important predictors of body fat content. Stepwise forward model selection using the AIC criterion showed that the best predictive power (r2 up to 0.99) was achieved with models including 49 scanner measurements.

CONCLUSION

The use of a 3D full body scanner produced results that strongly correlate to manually measured anthropometric measures. Predictions were improved substantially by including multiple measurements, which can only be obtained with a 3D body scanner, in the models.

Identification of Risk Factors Associated with Obesity and Overweight-A Machine Learning Overview

Social determining factors such as the adverse influence of globalization, supermarket growth, fast unplanned urbanization, sedentary lifestyle, economy, and social position slowly develop behavioral risk factors in humans. Behavioral risk factors such as unhealthy habits, improper diet, and physical inactivity lead to physiological risks, and "obesity/overweight" is one of the consequences. "Obesity and overweight" are one of the major lifestyle diseases that leads to other health conditions, such as cardiovascular diseases (CVDs), chronic obstructive pulmonary disease (COPD), cancer, diabetes type II, hypertension, and depression. It is not restricted within the age and socio-economic background of human beings. The "World Health Organization" (WHO) has anticipated that 30% of global death will be caused by lifestyle diseases by 2030 and it can be prevented with the appropriate identification of associated risk factors and behavioral intervention plans. Health behavior change should be given priority to avoid life-threatening damages. The primary purpose of this study is not to present a risk prediction model but to provide a review of various machine learning (ML) methods and their execution using available sample health data in a public repository related to lifestyle diseases, such as obesity, CVDs, and diabetes type II. In this study, we targeted people, both male and female, in the age group of >20 and <60, excluding pregnancy and genetic factors. This paper qualifies as a tutorial article on how to use different ML methods to identify potential risk factors of obesity/overweight. Although institutions such as "Center for Disease Control and Prevention (CDC)" and "National Institute for Clinical Excellence (NICE)" guidelines work to understand the cause and consequences of overweight/obesity, we aimed to utilize the potential of data science to assess the correlated risk factors of obesity/overweight after analyzing the existing datasets available in "Kaggle" and "University of California, Irvine (UCI) database", and to check how the potential risk factors are changing with the change in body-energy imbalance with data-visualization techniques and regression analysis. Analyzing existing obesity/overweight related data using machine learning algorithms did not produce any brand-new risk factors, but it helped us to understand: (a) how are identified risk factors related to weight change and how do we visualize it? (b) what will be the nature of the data (potential monitorable risk factors) to be collected over time to develop our intended eCoach system for the promotion of a healthy lifestyle targeting "obesity and overweight" as a study case in the future? (c) why have we used the existing "Kaggle" and "UCI" datasets for our preliminary study? (d) which classification and regression models are performing better with a corresponding limited volume of the dataset following performance metrics?

The aging human body shape

Body shape and composition are heterogeneous among humans with possible impact for health. Anthropometric methods and data are needed to better describe the diversity of the human body in human populations, its age dependence, and associations with health risk. We applied whole-body laser scanning to a cohort of 8499 women and men of age 40–80 years within the frame of the LIFE (Leipzig Research Center for Civilization Diseases) study aimed at discovering health risk in a middle European urban population. Body scanning delivers multidimensional anthropometric data, which were further processed by machine learning to stratify the participants into body types. We here applied this body typing concept to describe the diversity of body shapes in an aging population and its association with physical activity and selected health and lifestyle factors. We find that aging results in similar reshaping of female and male bodies despite the large diversity of body types observed in the study. Slim body shapes remain slim and partly tend to become even more lean and fragile, while obese body shapes remain obese. Female body shapes change more strongly than male ones. The incidence of the different body types changes with characteristic Life Course trajectories. Physical activity is inversely related to the body mass index and decreases with age, while self-reported incidence for myocardial infarction shows overall the inverse trend. We discuss health risks factors in the context of body shape and its relation to obesity. Body typing opens options for personalized anthropometry to better estimate health risk in epidemiological research and future clinical applications.