Development and validation of a prediction model to detect the effects of aged garlic extract supplement with precision

Personalized medicine is gaining interest as patients require information on the of a certain drug, treatment or lifestyle recommendation. Cardiovascular disease is the leading cause of mortality worldwide and one of the most severe complications of this disease is coronary artery calcification (CAC). Numerous patients are interested in complementary medicine and dietary supplements, one of these being aged garlic extract (AGE). The aim of the present study was to validate a prediction model to explore whether an individual patient will have a positive effect of AGE on their CAC and blood pressure. The algorithm in the present study was constructed using a cross‑industry standard process for data mining. It comprised a logistic regression model and the selected method for validation was leave‑one‑out cross‑validation. The developed algorithm was used to predict whether a patient would benefit from AGE or not. The present study demonstrated that it is possible to develop predictive models classifying patients into who would have the optimal results from treatment with the AGE supplement or not. The constructed algorithm was able to predict with 64% precision which patient would have a significant reduction of CAC and with 66% precision which patient would have a significant blood‑pressure lowering effect, using the AGE supplement for 12 months. For a number of patients, it is essential to determine whether they will have an effect before changes are made to their daily lives. The developed algorithm in the present study demonstrates that it is feasible to develop models to answer this question.