Logical analysis of data using linear approximation and heuristic algorithms for gene expression-based diagnostics

¹ Reshetnev Siberian State University of Science and Technology, 31, Krasnoyarsky Rabochy av., Krasnoyarsk, 660037, Russian Federation
² Siberian Federal University, 79, Svobodny av., Krasnoyarsk, 660041, Russian Federation

^* Corresponding author: i-masich@yandex.ru

Abstract

This research aims to develop a methodology that combines logical analysis of data with a white box model to predict the progression of chronic diseases. Such diseases represent a serious health problem, and accurate prediction and management are essential to improve patients’ quality of life. Current machine learning methods such as deep learning often have high accuracy, but their solutions are ‘black boxes’, making them difficult to understand. The research combines the best aspects of both methods to create more accurate and interpretable models for predicting the progression of chronic diseases. The methodology developed is expected to contribute to informative decision-making in medical practice, enrich knowledge in medical research and improve the quality of care for patients with chronic diseases.