Conclusion:
In conclusion we can state that for the prediction of surgical
re-intervention within two years after EA, the LR gives a better
prediction compared to the ML model. However, machine learning
algorithms should always be considered as candidate prediction tool for
classification or regression problems because of the possible
advantages. So far there is no evidence for one single algorithm that
outperforms the other in general use. Further research is needed for the
evaluation of ML based predictive modelling.