The «ФП Тест» method is a machine learning model based on gradient boosting. To determine the stage of liver fibrosis, there is no need to purchase expensive equipment or conduct additional studies; the results of a routine clinical examination of the patient with determination of age, height, weight and body mass index, as well as levels of platelets, ALT, AST, GGT and total bilirubin are sufficient.
The method is an interpretable logical model (QCA). To determine the degree of liver steatosis, the results of a routine clinical examination of the patient with determination of gender, age, height, weight, hepatitis C virus genotype and results of ultrasound of the abdominal organs are sufficient.
A method for predicting the duration of inpatient treatment for patients with COVID-19 based on machine learning technologies. To predict the duration of inpatient treatment, the results of a routine clinical examination of the patient with an assessment of such indicators as age, height, weight, body mass index, number of days from the onset of the disease, body temperature, pulse rate, respiratory rate, diastolic and systolic blood pressure, as well as SpO₂ level are sufficient.
Development of a method for short-term forecasting of the epidemic situation in organized groups in order to increase the effectiveness of preventive measures and reduce morbidity. The project is being implemented in cooperation with the Federal State Budgetary Institution «Main Center for State Sanitary and Epidemiological Surveillance (Special Purpose)» of the Ministry of Defense of the Russian Federation and the Federal State Budgetary Institution «St. Petersburg Research Institute of Physical Culture».
Cluster analysis of biomedical data (anamnestic data, experimental-psychological and laboratory examinations, MRI and EEG) in order to study the heterogeneity of mild cognitive decline syndrome and verify early prognostic criteria for the development of dementia in the elderly.