Revolutionizing Medical Diagnosis with Novel Teaching-Learning-Based Optimization

In medical diagnosis, the precise and prompt identification of diseases is crucial for effective treatment and optimal patient care. As medical data grows increasingly complex, there's an urgent need for efficient diagnostic tools. Researchers are turning to innovative optimization techniques to enhance the accuracy and speed of these diagnoses. This paper applied a novel Teaching-Learning-Based Optimization (TLBO) technique and its potential implications in medical diagnosis. Diagnoses require the interpretation of each data point and its categorization to a specific pathology. Tools such as computer-aided diagnostics and artificial neural networks exemplify the AI technologies that aim to refine diagnostic processes and minimize human error. These algorithms have the versatility to process a broad spectrum of medical data. Our investigation delves into the theory and potential of using artificial neural networks in medical diagnosis. Results indicate that while various methods are effective in predicting medical diagnostics, the TLBOMLP and ER-WCAMLP methods outperform with accuracy rates of AUC=0.971, compared to CART-MLP's AUC=0.961 and 0.962.