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

Area of Science:

• Biochemistry
• Environmental Health
• Computational Biology

Background:

• Assessing human trace element status is crucial for addressing micromineral deficiencies.
• Direct measurement of trace element retention 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 retention.
• To utilize artificial neural networks for modeling complex biological systems.
• To enable calculation of body microelement levels from water and urine data.

Main Methods:

• Development of multiple artificial neural network (ANN) models.
• Utilizing drinking water trace element concentrations to represent intake.
• Using urine trace element concentrations to represent excretion.
• Leveraging ANNs to implicitly model unknown system dependencies and handle incomplete data.

Main Results:

• Successfully created ANN models to describe trace element retention in the human body.
• Demonstrated the capability to calculate internal microelement levels based on external data (water and urine).
• Validated the potential for these models in health applications.

Conclusions:

• Artificial neural networks are effective tools for modeling complex biological trace element dynamics.
• The developed models can predict body trace element status, aiding in deficiency correction.
• Findings support the use of these models in public health initiatives for safe drinking water recommendations.