ARTIFICIAL INTELLIGENCE FOR THE DETECTION OF SICKLE CELL ANEMIA

ISBN-13: 9786209628870 / Angielski / Miękka / 2026 / 80 str.

Jorge Gómez Gómez; Velssy Hernández Riaño

Opis

This study presents a machine learning-based system for the early prediction of sickle cell anemia using structured clinical data from patient blood counts. The proposed approach seeks to address the limitations of conventional diagnostic methods, which are often costly, time-consuming, and require specialized laboratory infrastructure. The objective was to identify the best-performing model and develop an application that could be used by medical personnel in hard-to-reach areas as a support tool for the early diagnosis of this disease. Among the models evaluated, the Random Forest model achieved the best performance, with an accuracy of 98%, a sensitivity rate of 98%, and an F1 score of 98%. Its superior performance is attributed to its ability to capture non-linear interactions between hematological variables, which are crucial for clinical diagnosis. The system's predictions were validated by medical specialists, showing high agreement with traditional diagnoses. A key innovation of this study is the use of structured blood count data.