Development and evaluation of models for differential diagnosis of clinical and hematologic syndromes based on ensemble machine learning methods

The purpose of this study is to develop and apply the technology of differential diagnosis of clinical and hematologic syndromes for electronic passport. This approach is based on algorithms of ensemble methods of machine learning, which allow to increase the efficiency of technological processes of remote monitoring of hemoglobin synthesis disorder as a result of iron deficiency, developing against the background of various pathological (physiological) conditions and manifested by signs of anemia and sideropenia. The paper presents the rationale for the choice of methods for diagnosing clinical and hematologic syndromes based on ensemble methods of machine learning, integrating Bagging and adaptive Boosting of diagnostic criteria. The principal difference between the idea of this study and previous ones is that the focus of this project is to increase the accuracy of data classification using such ensemble learning algorithms as Bagging and adaptive Boosting.