Artificial intelligence technologies in biomedical research on human adaptation and maladaptation to environmental factors

The number of environmental factors simultaneously affecting the human body is extremely large. Tracking these factors in time has become possible thanks to the development of artificial intelligence technologies, including machine learning algorithms, deep learning algorithms, and generative artificial intelligence. The integration of this new generation of technological solutions into biomedical sciences enables the identification of hidden interdependencies among studied elements and processes that were previously overlooked. In the context of research on the mechanisms of human adaptation and maladaptation, special attention should be given to exogenous hypoxia as one of the most significant environmental factors studied within ecology, physiology, and clinical medicine. The topic of individual markers of human resistance to hypoxia remains open and is regularly addressed in physiological and pathophysiological works. In recent works, methods of machine and deep learning have already found wide application, including the analysis of multimodal physiological data. For example, a machine learning model has been developed to predict the development of acute mountain sickness with a sensitivity of 0.998 and a specificity of 0.978. The model was trained using physiological indicators of test subjects and real-time climate data. Thus, the application of artificial intelligence tools for scientific research planning, data processing, and the creation of predictive models significantly expands the current understanding of physiological mechanisms of human adaptation to hypoxia and enables the analysis of other environmental factors to be carried out at a new technological level.