• Somya Shukla
• Jitendra Tyagi

A clinical phenomenon known as acute-on-chronic liver failure (ACLF) affects people with chronic liver disease. It is characterized by rapid liver cirrhosis and is linked to a high short-term mortality rate. It is characterized by severe organ failure, systemic inflammation, and a bad prognosis. It is possible to classify and predict the course of patients with ACLF using specific prognostic ratings for liver and organ failures. Thus, this research aims to compare the efficacy of numerous “Machine Learning algorithms” to lower the expensive diagnostic cost of chronic liver disease. Several algorithms, including Gradient Boosting and Adaboost, were utilized in this work. The effectiveness of each classification approach was measured using metrics like accuracy, precision, recall, & f1-score in Gradient Boosting. Accuracy is 79.70%, 79%, 78%, and 75%, Adaboost, and Adaboost with Randomized Search CV, respectively. The testing results showed that the highest accuracy was achieved via Gradient Boosting. Our current research also primarily focuses on using clinical data to predict liver disease, and we investigate various data representations during our analysis. And the more accurate model is Ada Boost with RSCV for training in this study

Acute Liver Failure, Disease Prediction, Machine Learning, Gradient Boosting Classifier, Adaboost Classifier.

"An Efficient Machine Learning-Based Model for Predicting Acute Liver Failure", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 11, page no.b1-b11, November-2022, Available :http://www.jetir.org/papers/JETIR2211116.pdf

"An Efficient Machine Learning-Based Model for Predicting Acute Liver Failure", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 11, page no. ppb1-b11, November-2022, Available at : http://www.jetir.org/papers/JETIR2211116.pdf