Personalized medicine: integrating phenotype and healthy habits for treatment individualization

In today's world, personalized medicine is transforming treatments by adapting them to individuals' characteristics, such as their phenotype and healthy habits. This project focuses on developing a mathematical model that combines phenotypic variables and healthy habits with high-impact diseases according to their mortality rate in Colombia, utilizing 2023 Death Statistics data from DANE. The model will be constructed through an extensive literature review to identify the predominant phenotypic characteristics and healthy habits associated with each disease. These will be compiled into a table, and association rules will be created using logical propositions. Subsequently, a table will be generated for each disease, randomly linking the criteria from the initial table with assigned weights. The diseases to be considered include ischemic heart disease, tuberculosis, respiratory infections (especially SARS-CoV-2), chronic kidney disease, and cerebrovascular diseases. The primary objective is to create a personalized medicine model tailored to each patient, integrating phenotypic data and healthy habits with the aforementioned diseases. This model aims to offer more effective and individualized treatments by creating patterns that relate phenotype, healthy habits, and diseases, enabling patient categorization and more precise care. It will serve as a clinical decision support system through predictive modeling. This approach is expected to lead to improved health outcomes and quality of life for patients by reducing medical diagnostic errors. According to the World Health Organization (WHO) in 2019, around 134 million people suffer from avoidable medical errors annually, resulting in 2.6 million deaths. With a validated model, a considerable reduction in these errors is projected, promoting precision healthcare. Overall, this project represents a promising step towards personalized medicine, leveraging advanced mathematical modeling and data analysis techniques to provide tailored treatments and improve patient outcomes.