Building a Diagnostic Standard for Alzheimer’s Disease Based on Decision Trees and Analyzing Key Factors with Random Forests

Abstract

Research Background and Significance: Alzheimer's disease (AD) is a widespread neurodegenerative disorder that poses a significant threat to the health of millions of older adults worldwide. Despite the availability of various methods to assess the severity of dementia, the need for a high-precision diagnostic model remains crucial to enhancing patient outcomes. Accurate diagnosis is essential not only for the well-being of individuals but also for the effective management and treatment of the disease. This study aims to address this critical need by developing a more precise diagnostic framework for AD, utilizing advanced machine learning techniques in combination with comprehensive clinical data. Study Contributions: In this research, a decision tree model was constructed based on the principle of information gain, using a meticulously pre-processed sample of 2,149 patients from a public dataset. The model achieved a diagnostic accuracy of 93.47%, markedly outperforming traditional diagnostic methods. Additionally, a random forest model was employed to identify key risk factors influencing AD, such as age and lifestyle habits. These findings not only equip clinicians with more accurate diagnostic tools but also provide a robust scientific foundation for developing AD prevention and treatment strategies. The study also acknowledges its limitations and suggests directions for future research to further improve the diagnosis and understanding of Alzheimer's disease.