Explainable Symptom-Based Artificial A template for thinking for Leukaemia Detection

  • Shreedhar Maruti Kumbhar Department of Master of Computer Applications Raja Rajeswari College of Engineering, Bangalore
  • Manoj S Department of Master of Computer Applications Raja Rajeswari College of Engineering, Bangalore
Keywords: Explainable AI, Leukemia, Machine Learning, Symptom-Based Detection.

Abstract

Leukaemianevertheless has an untimely end, but it can be extremely costly to cure. Nonetheless, early detection of leukaemia may save lives as well as funds for those affected, particularly children, for whom leukaemia is a common disease type. In this study, we present a directed An AI algorithm that successfully forecasts the possibility of the initial stages leukaemia based solely on side effects. Furthermore, include selection is carried outbased on facts set to demonstrate the power of individual elements and work on the exhibition of characterisation models. We use two AI calculations, the nave bayes classifier and the support vector network.Cross-validation is a strategy for testing ML models that involves training numerous ML models on subsets of the available input data and then evaluating them on the complementary subset. To detect overfitting, use cross-validation. The SVM algorithm based on performance achieved the highest accuracy, precision, recall, and F-measure.

Published
2023-07-01
Statistics
Abstract views: 123 times
PDF downloads: 76 times
Section
Articles