The paper is devoted to the application of machine learning methods to the prediction of the development of gestational diabetes mellitus in early pregnancy. Based on two publicly available databases, study assesses influence of such features as body mass index, thickness of triceps skin folds, ultrasound measurements of maternal visceral fat, first measured fasting glucose, and others a predictors of gestational diabetes mellitus. The supervised machine learning methods based on decision trees, support vector machines, logistic regression, k-nearest neighbors classifier, ensemble learning, Naive Bayes classifier, and neural networks were implemented to determine the best classification models for computerized gestational diabetes mellitus disease prediction. The accuracy of the different classifiers was determined and compared.  Support vector machine classifier demonstrated the highest accuracy (83.0% of total correctly prognosed cases, 87.9% for healthy class, and 78.1% for gestational diabetes mellitus) in predicting the development of gestational diabetes based on features from Pima Indians Diabetes Database. Extreme gradient boosting classifier performed the best, comparing to other supervised machine learning methods, for Visceral Adipose Tissue Measurements during Pregnancy Database. It showed 87.9% of total correctly prognosed cases, 82.2% for healthy class, and 93.6% for gestational diabetes mellitus).

The method of electrical analogies for the analysis of bioelectric dynamic processes in cardiomyocytes is used in the study. This method allows for replacing investigation of phenomena in nonelectrical systems by research of analogous phenomena in electrical circuits. The investigation of time processes in cardiac cells is based on the solution of the system of ordinary differential equations for an electrical circuit. Electrophysiological properties of cardiomyocytes such as refractory period, maximum capture rate and electrical restitution are studied. Mathematical modeling. Computational simulation of the action potential and currents for + , + , 2+ ions in cardiomyocytes is performed by using the parallel conductance model. This model is based on the assumption of the presence of independent ion channels for + , + , 2+ ions, as well as leakage through the membrane of cardiac cell. Each branch of the electrical circuit reflects the contribution of one type of ions to total membrane current. Results.The obtained electrical restitution curves for ventricular and atrial cardiomyocytes are presented in the paper. The proposed model makes it possible to identify the areas with the maximum slope on the restitution curves, which are crucial in the development of cardiac arrhythmias. Dependences of calcium current on stimulation frequency for atrial and ventricular cardiomyocytes are obtained. Analysis of the kinetics of calcium ions under various protocols of external influences can be useful for predicting the contractile force of cardiomyocytes. Conclusion.The results of calculations can be used to interpret the experimental results obtained in investigations of cardiomyocytes using the "laboratory on a chip" technology, as well as in the design of new experiments with cardiomyocytes for drug screening, cell therapy and personalized studies of heart diseases.