Original Article(s)

• Prediction of Sex and Body Mass Index Based on Anthropometric Features and Balance Parameters Using Machine Learning Machine Learning-Based Prediction of Sex and BMI

  Ahmet Turan Urhan , Mustafa Furkan Ozturk , Ahmet Depreli , Omer Faruk Nasip , Tugba Ataseven

  XML | views: 85 | pages:

  Abstract

  Background: This study aims to evaluate the predictability of individuals’ Body Mass Index (BMI) and sex by integrating anthropometric data and balance parameters into machine learning algorithms. The primary goal is to propose a faster, more reliable, and data-driven model compared to traditional statistical approaches. Additionally, the effects of BMI, height, and weight variables on balance performance were analyzed.

  Materials and Methods: This study included 210 healthy adults (105 males, 105 females) aged 18–25 years. Height and weight were measured following standard anthropometric protocols, and balance performance was evaluated via the single-leg stance test on both sides. Anthropometric parameters (height, weight, dominant side) and balance durations were analyzed using machine learning algorithms (Decision Tree, Random Forest, Support Vector Machine). Model accuracy, precision, recall, and F1-score were calculated through 10-fold cross-validation. Statistical analyses were performed with IBM SPSS Statistics 25.

  Results: Machine learning algorithms achieved high accuracy rates in predicting both BMI and sex. The Random Forest model demonstrated the best overall performance, reaching an accuracy of 84% for sex prediction and 98% for BMI prediction. Furthermore, our results revealed that BMI and body weight negatively affected balance performance, whereas height was not identified as a significant determinant.

  Conclusion: The integration of anthropometric and balance parameters with machine learning algorithms provides an effective and non-invasive approach for predicting BMI and sex. This hybrid biomechanical–computational model may serve as a promising tool in personalized health assessments, balance analysis, and early risk detection studies.

• A comparative study of phase angle and its determinants in NAFLD patients and healthy individuals Phase angle and Non-alcoholic fatty liver disease

  Hamid Adeli Fard , Maryam Khosravi , Ali Bahari , Mahboobeh Ghasemzadeh Rahbardar , Habibollah Esmaily , Reza Rezvani , Farahnaz Akrami Moghadam , Mahsa Amarlou , Gordon A. Ferns , Maryam Saberi Karimian , Majid Ghayour-Mobarhan

  XML | views: 27 | pages:

  Abstract

  Background: The phase angle (PA) serves as an important indicator of cell membrane health and integrity, with higher values reflecting enhanced cell function. While malnutrition and the prognosis of chronic diseases have been extensively assessed, exploring the relationship between PA and Non-Alcoholic Fatty Liver Disease (NAFLD) has the potential to influence future disease management approaches.

  Aims: This study aimed to compare PA values across different NAFLD grades and investigate the correlation between anthropometric indices and phase angle measurements.

  Methods: A cross-sectional investigation was carried out on 191 people with NAFLD and 180 healthy controls. Anthropometric measurements were taken in the baseline using the Bio-Impedance Analyzer (In Body 770, In Body, South Korea), and hepatic steatosis was examined using FibroScan and ultrasound. The data was analyzed using SPSS version 16.

  Results: There was a significant unadjusted difference in trunk PA and whole-body PA between case and control groups (p< 0.001 and p< 0.05, respectively). After adjustment for confounders, the difference between different grades of fatty liver determined by ultrasound showed a significant difference (p< 0.001). Arm circumference emerged as the most positively correlated index influencing PA in both groups (p< 0.001), while the ratio of extracellular water to total body water exhibited the most negative correlation with PA (p< 0.001).

  Conclusions: The study found a substantial difference in PA levels between NAFLD patients and healthy individuals. Further research is needed to determine the potential of PA as a sensitive and specific predictor of NAFLD.