Comparative analysis of machine learning models for breast cancer diagnosis using time series and neural networks

This thesis emphasizes the importance of early diagnosis in the face of global health issues such as breast cancer and highlights the potential of advanced technological methods for this purpose. Since breast cancer is one of the most common types of cancer among women worldwide, improvements in diagnostic processes can lead to life-saving outcomes. This study compares the effectiveness of current methods used in breast cancer diagnosis by utilizing two significant and powerful technological approaches: time series analysis and neural networks. By comparing the effectiveness of different models such as KAN, ARIMA, and LSTM, this thesis presents an in-depth analysis within the scope of scientific research. The performance comparison among these models can play a critical role in determining which method is more suitable for breast cancer diagnosis. Additionally, this study reveals the limitations of different algorithms in terms of their ability to handle complex data structures and model long-term dependencies. In conclusion, this thesis represents an important step in expanding the applications of machine learning and time series analysis in the field of healthcare. By improving diagnostic processes, increasing the possibilities for early intervention, and enhancing the quality of patient care, it has the potential to revolutionize healthcare services. In this respect, the thesis aims to make significant contributions to academic literature and medical practice.