A Method for Assessing the Retention of Trace Elements in Human Body Using Neural Network Technology

Area of Science:

• Biochemistry and Environmental Health
• Computational Biology and Bioinformatics

Background:

• Assessing human trace element status is crucial for addressing micromineral deficiencies.
• Directly measuring trace element retention in the body is complex due to internal physiological mechanisms.
• Trace element balance depends on intake (e.g., drinking water) and excretion (e.g., urine).

Purpose of the Study:

• To develop predictive models for human trace element status formation.
• To overcome limitations of traditional mathematical models in complex biological systems.
• To utilize artificial neural networks for implicit modeling of trace element dynamics.

Main Methods:

• Development of multiple artificial neural network (ANN) models.
• Utilizing drinking water concentrations to represent trace element intake.
• Employing urine concentrations as a proxy for trace element excretion.
• Processing potentially inaccurate and incomplete biological data.

Main Results:

• Successfully created ANN models to describe trace element retention in the human body.
• Demonstrated the capability to calculate internal microelement levels using drinking water and urine data.
• Established a foundation for health interventions related to trace element balance.

Conclusions:

• Artificial neural networks offer a robust approach to modeling complex biological systems like trace element metabolism.
• The developed models can predict body microelement levels, aiding in health assessments.
• Findings support public health initiatives for ensuring safe drinking water and adequate trace element intake.