Analysis of Medical Laboratory Data and Biomarker Prediction Using Machine Learning

Abstract

Medical laboratory data offer critical insights into patient health, enabling early detection of diseases and monitoring of treatment efficacy. This study investigates the application of machine learning (ML) algorithms specifically Random Forest (RF), Support Vector Machine (SVM), and Multi-Layer Perceptron (MLP) neural networks in analyzing a dataset comprising routine biological parameters. The dataset includes complete blood count (CBC), platelets, erythrocyte sedimentation rate (ESR), C-reactive protein (CRP), electrolytes, and renal function indicators. The primary objective is to classify patients based on anomaly risk and predict potential biomarkers indicative of underlying health conditions. The findings demonstrate that ML models can effectively process complex medical data, offering valuable tools for enhancing diagnostic accuracy and patient care.