Corresponding electromyography data, reports, and reactions. Following that, four machine learning techniques were applied to the data sets: random forest, linear regression, support vector machine, and logistic regression. The random forest approach outperforms the other two in both data sets, according to comparisons of accuracy and recall rates amongst various algorithms. Additionally, comparisons between each algorithm's cases with and without deviation standardisation have been made, and the findings show that the deviation standardisation has a specific impact on the improvement of accuracy. It is also discovered that the random forest algorithm is capable of displaying the ranking of the features in terms of relevance. It has been demonstrated that the random forest method is utilised to diagnose facial paralysis and injury to the ear nerve. To create the best algorithm for computer-aided diagnosis systems, the proposed system uses two datasets consisting 575 facial motor nerve conduction study reports and 233 auditory brainstem reen.