An ensemble classifier method based on teaching-learning-based optimization for breast cancer diagnosis

IntroductionEpidemiological studies show that breast cancer is the most common cancer in women in the world. Breast cancer treatment can be very effective, especially when the disease is detected in the early stages. The goal can be achieved by using large-scale breast cancer data with the machine learning modelsMethodsThis paper proposes a new intelligent approach using an optimized ensemble classifier for breast cancer diagnosis. The classification is done by proposing a new intelligent Group Method of Data Handling (GMDH) neural network-based ensemble classifier. This method improves the performance of the machine learning technique by using a Teaching-Learning-Based Optimization (TLBO) algorithm to optimize the hyperparameters of the classifier. Meanwhile, we use TLBO as an evolutionary method to address the problem of appropriate feature selection in breast cancer data. ResultsThe simulation results show that the proposed method has a better accuracy between 7 and 26% compared to the best results of the existing equivalent algorithms. ConclusionAccording to the obtained results, we suggest the proposed algorithm as an intelligent medical assistant system for breast cancer diagnosis.

Automated summary

This paper proposes a new intelligent approach using an optimized ensemble classifier for breast cancer diagnosis. The method improves the performance of machine learning technique by optimizing the hyperparameters of the classifier through a Teaching-Learning-Based Optimization (TLBO) algorithm. The simulation results show that the proposed method has a better accuracy compared to existing equivalent algorithms, making it a potential intelligent medical assistant system for breast cancer diagnosis.