 This paper proposes a novel approach for improving the accuracy and speed of two important medical tasks, classification and image detection. The authors first applied advanced parallel k-means pre-processing to identify patterns and structures in the data, which improved the performance of both logistic regression and YOLO-V4. They then leveraged the acceleration capabilities of a neural engine processor to further increase the speed and efficiency of their approach. Finally, they tested their methodology on several large medical data sets and found that it was able to accurately classify large amounts of medical data and detect medical images. Their results demonstrate that the combination of advanced parallel k-means pre-processing and the neural engine processor resulted in a significant improvement in the performance of logistic regression and YOLO-V4, making them more reliable for use in medical applications. This article was authored by Fawad H. Awad, Murtada M. Hamad and Leigh Thalzabedi.