Early Detection of Leukemia Using AI and Blood Test

Abstract

The research offers a hybrid method that uses low-cost blood testing, patient symptoms, and artificial intelligence to diagnose leukemia early. The Complete Blood Count (CBC) results, which include the white blood cell count, red blood cell count, platelet count, and hemoglobin levels, as well as symptoms like exhaustion, fever, infections, and bleeding, are gathered by the system. A machine learning model created in Python using tools like Scikit-learn and Pandas is used to preprocess and analyze the data. The approach divides leukemia risk into three categories: low, medium, and high. The system can suggest additional medical testing for confirmation based on the prognosis. The suggested technique is appropriate for early screening, particularly in rural and low-resource areas, because it is quick, inexpensive, and easy to use. For ease of use, it can be developed as a straightforward online or mobile application. The technology aids in early detection and lowers the likelihood of late-stage identification, but it cannot take the place of expert medical diagnosis. All things considered, this strategy raises awareness, facilitates prompt diagnosis, and enhances treatment results.