Knowledge discovery applied in the prognosis and treatment of Acute Myeloid Leukemia

• Grant number: 21/13325-1
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Effective date (Start): March 01, 2022
• Effective date (End): February 28, 2023
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Tiago Agostinho de Almeida
• Grantee: Jade Manzur de Almeida
• Host Institution: Centro de Ciências em Gestão e Tecnologia (CCGT). Universidade Federal de São Carlos (UFSCAR). Campus de Sorocaba. Sorocaba , SP, Brazil

Abstract

Acute Myeloid Leukemia is a chronic and disabling disease. To assist with the right decisions about the treatment of patients, a prognosis is made concerning the risk of the disease, in three groups: favorable, intermediate, and unfavorable. This classification is commonly used as an aid in customizing therapeutic decisions. However, the current ranking is very conservative. Patients with favorable and unfavorable risk prognoses are usually correctly identified. However, most patients are classified as intermediate risk, and not offered subsidies to support the specialists' decisions. Given the severity of the disease and the urgency of starting treatment, a more assertive and less evasive classification is needed so that specialists are provided with information to support an accurate prognosis, which supports decisions on effective treatments. In this sense, this research project proposes using machine learning techniques to generate a new predictive model using clinical and genetic data to obtain more assertive risk predictions than existing models. (AU)