Novel Bioparameters derived from Bioimpedance Measurements for Accurate Prediction of Weight Status in Infant-Juvenile Individuals: A Regression Analysis

Abstract

Objective The search for other bioparameters to assess the weight status of individuals is important as it may provide more accurate information concerning nutritional status. The objective of this pilot study was to investigate the correlation between weight status and two novel bioparameters, specific resistance and capacitance, and their relationship with the phase angle and health status in an infant-juvenile cohort from the eastern Cuban region, using machine learning predictions. Methods A total of 283 female and male volunteers ranging in age from 2 to 18 years old were studied. Standard tetrapolar whole-body bioimpedance measurements were taken, and a bioimpedance analyzer was used to collect fundamental bioelectrical and other parameters of interest. The collected data were analyzed using machine learning techniques to develop predictive models for weight status assessment. Results The results showed that the identified bioparameters (specific resistance and capacitance) can effectively predict weight status. The developed machine learning models can accurately assess weight status and disease risks in this population. The phase angle was also found to be significantly correlated with weight status and health status in the infant-juvenile cohort. Conclusion This study highlights the potential of using bioimpedance measurements and bioparameters in assessing health and disease risks in an infant-juvenile cohort. The developed predictive models can accurately predict weight status and help identify individuals at risk for various health conditions. These findings offer a starting point for future research in this area, and further studies can build upon these results to develop more accurate and comprehensive predictive models. Trial registration Retrospectively registered.