Experimental study and comparison of medical methodology and machine learning models to enhance algorithms for morphological classification of clinical and hematologic syndromes

Abstract

The dynamic evolution of modern medicine highlights the increasing significance of automating diagnostic procedures. This progression is not solely a matter of convenience but a vital step towards fully leveraging technological advancements, with the goal of elevating both research and clinical outcomes to unprecedented levels. Among the notable advancements in this arena, the emergence of diagnostic systems founded on morphological classification algorithms holds particular prominence. This study compares the performance of different methods, including both traditional medical approaches and modern machine learning techniques. Clinical and hematologic syndromes refer to a broad range of medical conditions characterized by specific sets of signs, symptoms, and laboratory findings. Experimental study and comparison of medical methodology and machine learning models allowed to determine the most effective approaches to morphological classification of clinical-hematologic syndromes, which may lead to improved diagnosis and treatment of patients.

Ähnliche Arbeiten