Predicting the Mortality of Patients with Leukemia Using Artificial Intelligence

Several factors must be considered when predicting mortality in patients with hematological malignancies. These factors and characteristics complicate the ability of doctors’ and nurses to predict the prognosis of these diseases. This study aimed to develop a mortality prediction model for leukemia patients using artificial intelligence and a nearest-neighbor genetic algorithm. This retrospective study used the medical records of ۲۳۵ patients with leukemia at the Ahvaz Oncology Center from ۲۰۱۶ to ۲۰۱۹. To provide a mortality prediction model, a genetic algorithm and nearest neighbor were used. A genetic approach was employed to identify the determinants of mortality, and the nearest-neighbor technique was utilized to enhance model accuracy. Ultimately, the diagnostic power of the mortality prediction model was assessed using accuracy, sensitivity, and specificity criteria. The laboratory values and variables incorporated into the genetic algorithm revealed that mechanical ventilation, hemodialysis, neutropenia, and bone marrow transplantation significantly influenced the mortality rate of patients with leukemia. The diagnostic accuracy of the genetic algorithm introduced in this study was ۷۷.۴%, with a sensitivity of ۷۸.۲% and specificity of ۸۲%. The results showed the artificial intelligence algorithm in predicting mortality in leukemia patients.

کلیدواژه ها:

Artificial intelligence ، Leukemia ، Genetic Algorithm ، k-nearest neighbor algorithm ، Oncology ، Intensive Care Unit