Generating Synthetic Metabolic and Hormonal Data via Physiological In-Silico Modelling: Assessment of Reliability in Different Fitness Conditions

Synthetic data generation is helpful when real data are not easily available; this often happens in the medical field, as real data can be not only private but also expensive, such as those requiring blood sampling. In this work, we present a dataset generated by a previously developed and validated computational modelling approach consisting of 139 ordinary differential equations, adapted to account for individual variability in the metabolic and hormonal changes that occur in response to eating meals and performing physical exercise. The generated dataset consists of a total of 1080 virtual subjects, spanning different fitness classes (fair and excellent) and undergoing exercises differing in modality (arm and leg cycling, running, stepping and walking) and intensity levels (low and high). The response in terms of oxygen consumption, plasma concentrations of epinephrine, glucose, and insulin is considered to evaluate model performance in capturing different fitness conditions and exercise modalities. Oxygen consumption, expressed as a percentage of the individual maximum, shows saturation values consistent with the target values computed considering the modality and intensity of exercise, as well as the fitness class of the subject. Moreover, oxygen consumption in some cases exceeds 100%, thus suggesting a lack of coherence between the exercise and the subject's characteristics. Epinephrine responses show lower values for trained individuals than for untrained ones, according to the findings of the literature. Trends for glycemia and insulinemia show that, considering the same intensity and modality of exercise, non-trained individuals experience a more pronounced decrease compared to trained ones.