| Popis: |
According to recent research conducted by the World Health Organisation (WHO), there has been a significant increase in the prevalence of liver and cardiac conditions. The rapid growth of India's population has made the identification and diagnosis of these illnesses more challenging. However, a solution is now available in the form of machine learning, a rapidly advancing technology that can help address practical issues and reach complex conclusions. Machine learning algorithms are widely employed in the healthcare industry to assist decision-makers in making well-informed choices. The primary objective of this study is to develop multiple models using various machine learning techniques on datasets related to heart and liver diseases. By comparing measures such as accuracy, recall, and others, it will be possible to determine which method is most effective in classifying specific disorders. The UCI Machine Learning Repository has provided two benchmark datasets—one for liver ailments and another for cardiac disorders. To construct these models, we utilized key machine learning techniques such as Decision Tree, Random Forest, Support Vector Machine (SVM), and linear models. These algorithms were employed to establish relationships among the variables in each dataset for both heart disease and liver disease. Subsequently, we classified the diseases based on their higher efficiency and accuracy rates. The results of our analysis revealed that the Logistic Regression method performed best in categorizing liver disease, while the Support Vector Machine (SVM) method excelled in categorizing heart disease. The selection of the best-performing algorithms was based on various parameters, including the time spent, accuracy, and others. Undoubtedly, this proposal will greatly assist medical practitioners by serving as a valuable decision-support system in clinical scenarios. By leveraging the power of machine learning, healthcare professionals can make more informed decisions regarding the identification and treatment of liver and cardiac conditions, ultimately improving patient care. |
