Predictive Modelling of Anaemia Using Clinical And Laboratory Data

Anaemia is a widespread medical condition which is characterized by a deficiency of red blood cells or hemoglobin that leads to various health issues. Early diagnosis and the efficient monitoring of anaemia are essential for treatment and prevention of health risks from anaemia. Generally, diagnosis of anaemia involves collection of clinical data from patient and laboratory tests, which are expensive and time-consuming process. With the advancements of machine learning techniques, there are different ways to automate the diagnosis process, which enables faster and accurate anaemia detection based on hematological data. This paper proposes a machine learning system for anaemia detection using Logistic Regression. The objective of this work is creating a web-based platform which predicts anaemia in individuals based on key medical data like gender, hemoglobin levels, MCV (Mean Corpuscular Volume), MCH (Mean Corpuscular hemoglobin), MCHC (Mean Corpuscular Hemoglobin Concentration), aiding for healthcare professionals with better accurate diagnostics. It also addresses the need for accessible and cost-effective tools for settings of resource limited. Even the system offers an automated, faster and non-invasive diagnostic approach.