Artificial Intelligence applied to the prediction of Myeloid Leukemia: A Systematic Review of Literature (#2139)

Authors

Mendoza-Montoya, Javier

Yapuchura-Ocaris, Enrique

Abstract

The purpose of this research is to analyze the impact and effectiveness of artificial intelligence (AI) models in diagnosing and predicting leukemia, with a particular focus on acute myeloid leukemia (AML). The goal is to identify the most accurate and robust models, as well as their limitations and medical applications. To this end, a systematic literature review (RSL) was carried out using the PRISMA methodology; the search was carried out in the Scopus database, identifying a total of 429 articles related to leukemia, and multiple cases of AML were analyzed that were evaluated with various AI approaches, including deep learning and machine learning. The models were evaluated based on their accuracy and the quality of the data used, with an emphasis on techniques such as convolutional neural networks (CNN), XGBoost, and hybrid models. The results show that the weighted convolutional neural network (WVCNN) model achieved 99.9% accuracy by analyzing genomic data. Techniques such as XGBoost and ResNet-50 demonstrated high effectiveness in different fields, achieving accuracy rates of 89% and 86%, respectively, depending on the type of data analyzed, whether tabular or medical images. In conclusion, AI advances have revolutionized AML prediction by combining hybrid approaches to overcome current limitations. Finally, it is suggested that future research should focus on the integration of multiple techniques, as well as the development of more interpretable models.