Related Experiment Video
Updated: Jun 2, 2026
05:35
A Point-of-Care Method with Integrated Decision Support Tool to Estimate Anemia at Population Level
Published on: January 19, 2024
Artificial intelligence models for predicting iron deficiency anemia and iron serum level based on accessible
Iman Azarkhish1, Mohammad Reza Raoufy, Shahriar Gharibzadeh
1Amirkabir University of Technology, Tehran, Iran.
Journal of Medical Systems
|April 20, 2011
Summary
This study introduces an artificial neural network (ANN) to diagnose iron deficiency anemia (IDA) using accessible lab data. The ANN model proved superior to other methods for diagnosing IDA and predicting serum iron levels.
Area of Science:
- Biochemistry
- Medical Diagnostics
- Artificial Intelligence in Medicine
Background:
- Iron deficiency anemia (IDA) is a prevalent global nutritional deficiency.
- Current serum iron measurement methods are costly, time-consuming, and not widely available.
Purpose of the Study:
- To develop and evaluate computational models for diagnosing IDA and predicting serum iron levels.
- To utilize readily available laboratory parameters for anemia assessment.
Main Methods:
- Development of an artificial neural network (ANN) and an adaptive neuro-fuzzy inference system (ANFIS).
- Input data included accessible laboratory values: MCV, MCH, MCHC, and Hb/RBC ratio.
- Comparison of ANN and ANFIS performance against logistic regression models.
Main Results:
- The artificial neural network (ANN) demonstrated superior performance in diagnosing IDA compared to ANFIS and logistic regression.
- The ANN model showed high accuracy and acceptable precision in predicting serum iron levels.
Conclusions:
- ANN models offer a promising, accurate, and accessible approach for diagnosing IDA.
- The developed ANN can serve as a reliable tool for predicting serum iron levels using routine lab data.