Validation of machine learning for Clinical Assessment of lumbar spine pathologies Using Graphic User Interface

The vertebral column degenerative disc clinical disease repressent an important part of the activity in neurospine surgery, in particular, the lumbar pathologies. Humans have certain limitations in terms of accuracy and effective time to perform the diagnostic prediction. the diagnosis by the radiologist is not always as accurate as the use of computer-aided technology (CAT). Nowadays, CAT becomes necessary to overcome these limitations in diagnosing diseases. It will help a neurosurgeon to make rapid and effective decisions. The purpose of our work is to introduce machine learning computer-aided technology methods to perform the diagnostic of pathology on the column vertebral based on the K-Nearest Neighbor classifier. Several patients with lumbar spine disease will be presented to evaluate and validate the performance of the proposed technique. It can help to diagnose a patient effectively based on the statistics performance metrics: Accuracy, precision score, sensitivity, F1-score, and specificity. The simulation results show that the proposed technique can correctly predict the pathologies with a significant higher recognition rate (100%), with the training accuracy and the test accuracy in the range of (82.6%~100.0%), (70.2%~95.2%), respectively. To conclude, the proposed model works better, indicating a pretty good prediction and a high recognition rate in detecting a new patient disease effectively. This will result in reducing the heavy physician workloads and diagnostic time. The proposed technique can be recommended to be integrated for clinical support decision systems and will serve as a primary screening and diagnosis guidline.