OBM Integrative and Complementary Medicine is an international peer-reviewed Open Access journal published quarterly online by LIDSEN Publishing Inc. It covers all evidence-based scientific studies on integrative, alternative and complementary approaches to improving health and wellness.

Topics contain but are not limited to:

  • Acupuncture
  • Acupressure
  • Acupotomy
  • Bioelectromagnetics applications
  • Pharmacological and biological treatments including their efficacy and safety
  • Diet, nutrition and lifestyle changes
  • Herbal medicine
  • Homeopathy
  • Manual healing methods (e.g., massage, physical therapy)
  • Kinesiology
  • Mind/body interventions
  • Preventive medicine
  • Research in integrative medicine
  • Education in integrative medicine
  • Related policies

It publishes a variety of article types: Original Research, Review, Communication, Opinion, Comment, Conference Report, Technical Note, Book Review, etc.

There is no restriction on paper length, provided that the text is concise and comprehensive. Authors should present their results in as much detail as possible, as reviewers are encouraged to emphasize scientific rigor and reproducibility.

Indexing: DOAJ-Directory of Open Access Journals.

Indexing: 
.

Publication Speed (median values for papers published in 2023): Submission to First Decision: 5.9 weeks; Submission to Acceptance: 14.7 weeks; Acceptance to Publication: 8 days (1-2 days of FREE language polishing included)

Open Access Editorial

Artificial Intelligence Applications in Digital Anthropometry 1

Diego A. Bonilla 1,2,3,4,*

  1. Research Division, Dynamical Business & Science Society – DBSS International SAS, Bogotá 110311, Colombia

  2. Research Group in Biochemistry and Molecular Biology, Faculty of Sciences and Education, Universidad Distrital Francisco José de Caldas, Bogotá 110311, Colombia

  3. Research Group in Physical Activity, Sports and Health Sciences—GICAFS, Universidad de Córdoba, Montería 230002, Colombia

  4. Sport Genomics Research Group, Department of Genetics, Physical Anthropology and Animal Physiology, Faculty of Science and Technology, University of the Basque Country (UPV/EHU), 48940 Leioa, Spain

Correspondence: Diego A. Bonilla

Special Issue: Nutrition and Exercise for Weight Loss

Received: December 21, 2022 | Accepted: December 21, 2022 | Published: December 26, 2022

OBM Integrative and Complementary Medicine 2022, Volume 7, Issue 4, doi:10.21926/obm.icm.2204056

Recommended citation: Bonilla DA. Artificial Intelligence Applications in Digital Anthropometry 1. OBM Integrative and Complementary Medicine 2022; 7(4): 056; doi:10.21926/obm.icm.2204056.

© 2022 by the authors. This is an open access article distributed under the conditions of the Creative Commons by Attribution License, which permits unrestricted use, distribution, and reproduction in any medium or format, provided the original work is correctly cited.

Abstract

Anthropometric measurements are frequently used to assess changes in body composition in different populations. Despite being a cheap, in-field, and relatively valid technique, the COVID-19 pandemic has impulse research on digital anthropometry across the globe. Machine learning, as the convergence of artificial intelligence and data mining, has the potential to improve data collection and analysis in the applications of kinanthropometry. Far from replacing conventional methods, digital anthropometry is a powerful opportunity to increase accuracy, validity, practicality, and the use of self-monitoring procedures under professional supervision. However, further research and scientific literacy among practitioners are warranted.

Graphical abstract

Click to view original image

Keywords

Artificial intelligence; machine learning; estimation techniques

Artificial intelligence (AI) represents the intelligence performed by machines that mimic the cognitive functions of human beings [1]. On the other hand, data mining (DM) is the semi-automatic or automatic analysis by which patterns and information are extracted, analyzed, and visualized from large data sets [2]. In turn, machine learning (ML) is at the convergence between AI and MD, which allows automata to learn from data, adapt and improve by performing different tasks such as predictions, classifications, and regressions [2]. The learning process is the key difference when comparing ML and DM.

Among several methods, kinanthropometry offers to exercise and health practitioners a standardized procedure for acquiring anatomical surface measurements that might be used to track changes in body composition. This represents a cheap, in-field, and relatively valid technique commonly used in several instances across the lifespan. However, the main drawbacks encompass i) the high inter-technician variability if the International Standards for Anthropometric Assessment established by the International Society for the Advancement of Kinanthropometry (ISAK) are ignored; and ii) the time-consuming procedure necessary to take all measurements by duplicate or triplicate when assessing the ISAK restricted (21 variables) and full (43 variables) profiles.

ML has the potential to improve data collection and analysis in kinanthropometry. This should call the attention of practitioners, considering that anthropometric data can be used to create morphological profiles or body composition estimation models beyond conventional statistical analyses. For example, unsupervised ML methods allow the inherent structure of unlabeled data to be discovered. Since the clustering method is applied to find homogeneous subgroups of observations, the algorithms have been used to profile phenotypes in sports science [3,4,5]. It is worth mentioning that the selection of the most appropriate clustering algorithm will depend on the distribution of the data and the phenotype/biological phenomenon to be analyzed (field knowledge) [6].

On the other hand, considering the predictive power of supervised ML methods, methodologies have been developed to estimate basic measures and girths by processing subpixels (silhouettes) [7,8], searching for convex hull defects (convex Hull) [9] or by using support vector machines or convolutional neural networks with collected data [10]. In this sense, estimating adiposity through digital anthropometry seems promising with valid and reliable results [11], although more research is needed.

As a result of the significant disruption that was caused by the COVID-19 pandemic, digital anthropometry has become an active line of research. The community of practitioners and kinanthropometry researchers is invited to undertake a scientific literacy process in this field to acquire the necessary programming and data science skills to enable correct analysis with ML algorithms (or at least understand the essentials). It is highly likely, in the future, practitioners will use hybrid procedures (human-machine-based methods) to collect anthropometric data. Skinfolds are those measures that might be maintained in future kinanthropometry protocols unless portable ultrasound devices (e.g., BodyMetrix™ BX2000) reduce their price to increase accessibility which may replace the manual procedures due to high reliability, validity, and agreement against dual-energy X-ray absorptiometry (DXA) [12]. After a possible transition into digital anthropometry, basic measures (stature, sitting height, and arm span), girths, breadths, and lengths can be evaluated with high accuracy and reliability using AI methods. Finally, unsupervised ML algorithms would benefit sports practitioners when the aim is to obtain anthropometric profiles, as has been demonstrated by our research group [3,4,5].

The lack of knowledge and standardization makes digital anthropometry a promising area for research and innovation. Our Research Division at the Dynamical Business and Science Society—DBSS International SAS will continue working on the ANTHROCYBER initiative as a multi-centric research project to design and validate digital anthropometry methodologies in various countries of Euro-America. Those interested in collaborating with this initiative may contact the author for details.

Acknowledgments

The author would like to thank all fellows of the ‘Red Iberoamericana de Investigadores en Antropometría Aplicada—RIBA2’, keynote speakers, and attendees at the ‘I Congreso Iberoamericano de Antropometría Aplicada’ where this topic was fully covered.

Author Contributions

The author did all the research work of this study.

Competing Interests

D.A.B. is a certified Level Three Anthropometrist (Instructor) by the International Society for the Advancement of Kinanthropometry (ISAK), has conducted academic-sponsored research on anthropometry and has received honoraria for selling anthropometric equipment and speaking about anthropometry at international conferences/private courses. Additionally, he is an active member of the ‘Red Iberoamericana de Investigadores en Antropometría Aplicada—RIBA2’.

References

  1. Russell S, Norvig P. Artificial Intelligence: A Modern Approach. Prentice Hall Press: 2009
  2. Sarker IH. Machine learning: Algorithms, real-world applications and research directions. SN Comput Sci. 2021; 2: 160. [CrossRef]
  3. Bonilla DA, Peralta JO, Bonilla JA, Urrutia-Mosquera W, Vargas-Molina S, Cannataro R, et al. Morphology, body composition and maturity status of young Colombian athletes from the Urabá subregion: A k-Medoids and hierarchical clustering analysis. Proceedings of the Journal of Human Sport and Exercise - 2020 - Summer Conferences of Sports Science; 2020. [CrossRef]
  4. Bonilla DA, Peralta-Alzate JO, Bonilla-Henao JA, Urrutia-Mosquera W, Cannataro R, Kočí J, et al. Unsupervised machine learning analysis of the anthropometric characteristics and maturity status of young Colombian athletes. J Phys Educ Sport. 2022; 22: 256-265,
  5. Gasperín-Rodríguez EI, Gómez-Figueroa JA, Gómez-Miranda LM, Ríos-Gallardo PT, Palmeros-Exsome C, Hernández-Lepe MA, et al. Body composition profiles of applicants to a physical education and sports major in Southeastern Mexico. Int J Environ Res Public Health. 2022; 19: 15685. [CrossRef]
  6. Mohedano-Munoz MA, Alique-García S, Rubio-Sánchez M, Raya L, Sánchez A. Interactive visual clustering and classification based on dimensionality reduction mappings: A case study for analyzing patients with dermatologic conditions. Expert Syst Appl. 2021; 171: 114605. [CrossRef]
  7. Ji Z, Qi X, Wang Y, Xu G, Du P, Wu X, et al. Human body shape reconstruction from binary silhouette images. Comput Aided Geom Des. 2019; 71: 231-243. [CrossRef]
  8. Sobhiyeh S, Dunkel A, Dechenaud M, Mehrnezhad A, Kennedy S, Shepherd J, et al. Digital anthropometric volumes: Toward the development and validation of a universal software. Med Phys. 2021; 48: 3654-3664. [CrossRef]
  9. Rativa D, Fernandes BJ, Roque A. Height and weight estimation from anthropometric measurements using machine learning regressions. IEEE J Transl Eng Health Med. 2018; 6: 1-9. [CrossRef]
  10. Nguyen TL, Nguyen TH, Zhukov A. Studies of anthropometrical features using machine learning approach. CEUR Workshop Proceedings, Supplementary Proceedings of the 4th International Conference on Analysis of Images, Social Networks and Texts; 2015 September 09-11; Yekaterinburg, Russia.
  11. Majmudar MD, Chandra S, Yakkala K, Kennedy S, Agrawal A, Sippel M, et al. Smartphone camera based assessment of adiposity: A validation study. NPJ Digit Med. 2022; 5: 79. [CrossRef]
  12. Kang S, Park JH, Seo MW, Jung HC, Kim YI, Lee JM. Validity of the portable ultrasound BodyMetrix™ BX-2000 for measuring body fat percentage. Sustainability. 2020; 12: 8786. [CrossRef]
Newsletter
Download PDF Download Citation
0 0

TOP