Fig. 2

Supervised machine learning (ML) process. The first step is when biomarkers are taken from a cohort, then the data is pre-processed, outliers are removed, data is imputed and normalized, then the data is divided between testing and training data sets; the first is used to train the algorithms, and the second test it and validate it, if the model is selected as the best performing algorithm. Finally, the model can be used to diagnose a new patient