# Comparison of machine learning models for hemoglobin prediction in patients undergoing maintenance hemodialysis

## TL;DR

This study compares machine learning models to predict hemoglobin levels in hemodialysis patients, finding that a neural network model performs best.

## Contribution

The study introduces a comparison of eight ML models for hemoglobin prediction in hemodialysis patients using real-world clinical data.

## Key findings

- The Multilayer Perceptron model achieved the highest performance with an R² of 0.672.
- The most recent hemoglobin value was identified as the strongest predictor of future levels.
- ML models using patient data can help identify anemia risk early in hemodialysis patients.

## Abstract

To estimate the next hemoglobin (Hb) levels in maintenance hemodialysis (MHD) patients, predictive models were developed using various Machine Learning (ML) algorithms.

A total of 8,159 records from 2,104 MHD patients across 24 blood purification centers in Shenzhen were included. Eight ML algorithms were employed to develop prediction models: Linear Regression (LR), Least Absolute Shrinkage and Selection Operator (Lasso), Bayesian Ridge, Gradient Boosting (XGBoost), Random Forest (RF), Support Vector Machine (SVM), Multilayer Perceptron (MLP), and Long Short-Term Memory (LSTM). Subsequently, the performance of models was evaluated and compared.

Among all the models, the MLP performed the best performance, with an R
2 of 0.672, a mean absolute error (MAE) of 9.360 g/L, and a root mean square error (RMSE) of 12.438 g/L. The analysis indicated that the most recent Hb value (Hb(t-1)) was the strongest predictor.

ML models based on demographic characteristics, dialysis records, and historical Hb data can effectively predict future Hb levels in MHD patients, which is helpful for early identification of anemia risk and timely clinical intervention.