Hybrid Models for Classifying Liver Cirrhosis with SVM and Xgboost Algorithms

Detecting and controlling cirrhosis that destroy liver tissue is major issue in liver part. More complex machine learning may better predict this complex disease. In this paper, a novel hybrid classification model combining SVM and XGBoost models is proposed to help improve the effectiveness of liver cirrhosis detection. This paper assesses multiple algorithms for liver disease classification using clinical and laboratory data as a large healthcare dataset. Using SVMs optimal hyperplanes for classification and XGBoost resilient gradient boosting framework to identify how your data is related itself A hybrid model. Model performance is improved during training where hyperparameters and feature selection are optimised. The hybrid model was compared with standalone SVM and XGBoost models based on accuracy, precision, recall and F1 score. In preliminary findings, the hybrid method classifies patients with liver cirrhosis more accurately and yields fewer false positives than individual algorithms. This suggests that clinical diagnostic tools could be improved using machine learning approaches. It means that hybrid models may help to improve medical diagnostic and decision-making for liver cirrhosis care.