Face morphology: Can it tell us something about body weight and fat?

Pascali, Maria Antonietta; Giorgi, Daniela; Bastiani, Luca; Henríquez, Pedro; Matuszewski, Bogdan J.; Morales, Maria‐Aurora; Colantonio, Sara

doi:10.1016/j.compbiomed.2016.06.006

Cited by 25 publications

(14 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Structural equation modeling (SEM) using Stata/SE 13.1, used to test the proposed model ( Fig. 1) [14,15]. The path analysis technique used measures to the extent that the model fit a data set and allowed testing of interrelationships between several variables simultaneously.…”

Section: Discussionmentioning

confidence: 99%

A new integrated approach for adolescent health and well-being: the AVATAR project

Mastorci

Bastiani

Trivellini

et al. 2020

Health Qual Life Outcomes

View full text Add to dashboard Cite

Background: Limited number of studies examined the relationship between factors (lifestyle, social, emotional, cognitive) affecting adolescents' health and well-being. The aims of this study were to identify the more important variables of the different components affecting adolescents' health [lifestyle habits (LH); emotional status (ES); social context (SC); and cognitive abilities (CA)], and explore the relationship between the aforementioned components. Methods: Data were collected between 2017 and 2018 from 756 eligible students, recruited from 5 Italian junior high school, by using KIDSCREEN-52 and cognitive processing using the Stroop Test. School engagement was estimated through questions concerning the scholastic achievement. Results: Of 756 adolescents, 395 were boys with a mean (SD) age of 12.19 (0.81) years. Compared to International T-value of reference group for KIDSCREEN-52, autonomy, bullying, psychological well-being and mood were lower than the reference groups, while self-perception score was higher. For LH, the most important predictor was autonomy (p < .0001). The most important aspects in the SC were the relationship with the parents (p < .0001), and the adolescent's relationships with peers (p < .0001). For ES, mood variables had the greatest contribution (p < .0001). The School performance related to Language & Literature (p < .0001) was the most important predictor in the CA latent variable. LH was positively associated with SC (p < .0001), ES (p < .0001), and CA (p < .0001). SC was positively associated with ES (p < .0001) and with CA (p < .0001). Conclusions: This study suggests the importance of an integrated approach to characterize adolescents' health and well-being. The approach suggested here may highlight additive synergistic effects of the various components in health and well-being assessment that may not be considered with a late approach and focused only on single factors.

show abstract

Section: Discussionmentioning

confidence: 99%

A new integrated approach for adolescent health and well-being: the AVATAR project

Mastorci

Bastiani

Trivellini

et al. 2020

Health Qual Life Outcomes

View full text Add to dashboard Cite

show abstract

“…Machine learning represents a powerful set of algorithms that can characterize, adapt, learn, predict and analyse data, amplifying our understanding of obesity and our capacity to predict with unprecedented precision. To this end, there have been increasing applications of machine learning in the obesity research field (1)(2)(3)(4)(5)(6)(7)(8)(9)(10). To demonstrate the effectiveness of machine learning for a broadly trained interdisciplinary readership, we provide here a general description of several of the most recognized methods along with a history of previous successful applications.…”

Section: Introductionmentioning

confidence: 99%

A review of machine learning in obesity

et al. 2018

View full text Add to dashboard Cite

Rich sources of obesity-related data arising from sensors, smartphone apps, electronic medical health records and insurance data can bring new insights for understanding, preventing and treating obesity. For such large datasets, machine learning provides sophisticated and elegant tools to describe, classify and predict obesity-related risks and outcomes. Here, we review machine learning methods that predict and/or classify such as linear and logistic regression, artificial neural networks, deep learning and decision tree analysis. We also review methods that describe and characterize data such as cluster analysis, principal component analysis, network science and topological data analysis. We introduce each method with a high-level overview followed by examples of successful applications. The algorithms were then applied to National Health and Nutrition Examination Survey to demonstrate methodology, utility and outcomes. The strengths and limitations of each method were also evaluated. This summary of machine learning algorithms provides a unique overview of the state of data analysis applied specifically to obesity.

show abstract

“…A method similar to Wen and Guo's was used by Wolffhechel and colleagues testing principal components resulting from face shape and color features to find the best BMI predictor model using 2D principal components of both shape and color [19]. Among more recent studies that have developed the use of facial imagery to estimate BMI, Pascali and colleagues examined 3D images of participants to estimate their BMI and found strong correlations between facial features and BMI [20]. However, the study had a small sample size (n = 30) and participants were required to travel to the researchers to be scanned by the 3D technology [20].…”

Section: Discussionmentioning

confidence: 99%

Detecting Body Mass Index from a Facial Photograph in Lifestyle Intervention

et al. 2018

View full text Add to dashboard Cite

This study aimed to identify whether a research participant’s body-mass index (BMI) can be correctly identified from their facial image (photograph) in order to improve data capturing in dissemination and implementation research. Facial BMI (fBMI) was measured using an algorithm formulated to identify points on each enrolled participant’s face from a photograph. Once facial landmarks were detected, distances and ratios between them were computed to characterize facial fatness. A regression function was then used to represent the relationship between facial measures and BMI values to then calculate fBMI from each photo image. Simultaneously, BMI was physically measured (mBMI) by trained researchers, calculated as weight in kilograms divided by height in meters squared (adult BMI). Correlation analysis of fBMI to mBMI (n = 1210) showed significant correlation between fBMI and BMIs in normal and overweight categories (p < 0.0001). Further analysis indicated fBMI to be less accurate in underweight and obese participants. Matched pair data for each individual indicated that fBMI identified participant BMI an average of 0.4212 less than mBMI (p < 0.0007). Contingency table analysis found 109 participants in the ‘obese’ category of mBMI were positioned into a lower category for fBMI. Facial imagery is a viable measure for dissemination of human research; however, further testing to sensitize fBMI measures for underweight and obese individuals are necessary.

show abstract

Face morphology: Can it tell us something about body weight and fat?

Cited by 25 publications

References 40 publications

A new integrated approach for adolescent health and well-being: the AVATAR project

A new integrated approach for adolescent health and well-being: the AVATAR project

A review of machine learning in obesity

Detecting Body Mass Index from a Facial Photograph in Lifestyle Intervention

Contact Info

Product

Resources

About