Authors:
H. K. Sindhu, Manjula Sanjay Koti, S. Priyadarshini, R. Regin, A. Mohamed Suhail, Saly Jaber
Addresses:
Department of Computer Application, Dayananda Sagar Academy of Technology and Management, Bengaluru, Karnataka, India. Department of Computer Science and Engineering, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. Department of Computer Science and Engineering, Dhaanish Ahmed College of Engineering, Chennai, Tamil Nadu, India. Department of Analytical Chemistry, Saint Joseph University, Beirut, Lebanon.
Abstract:
Liver inflammation quantification is the field of liver disease diagnosis and assessment, such as hepatitis and cirrhosis. Invasive and non-invasive diagnoses will be among the routine diagnoses. This contribution proposes a paradigm for a computer system that applies machine learning to classify and predict liver inflammation grade from clinical data. Operations are conducted on the publicly available "Hepatitis Data Set" from the UCI Machine Learning Repository, using a set of demographic, clinical, and biochemical patient predictors. Python programming language and its entire set of tools, from data handling through Pandas, modelling through Scikit-learn, and visualizations through Matplotlib/Seaborn, are major tools utilized for this study. This article elucidates the construction of a Random Forest classifier, a brutal ensemble, for patient outcome prediction. By performing meticulous preprocessing, model training, and model testing, we aim to demonstrate machine learning's ability to provide an immediate, accurate, and painless diagnosis. Conclusions are drawn from data-based methods that have the potential to optimise clinical decision-making, patient outcomes, and the effectiveness of treatment for liver disease.
Keywords: Machine Learning; Hepatitis Data Set; Random Forest; Data Analysis; Hepatitis and Cirrhosis; Liver Inflammation; Diagnosis and Assessment; Model Training; Biochemical Patient Predictors.
Received: 31/08/2024, Revised: 18/12/2024, Accepted: 08/02/2025, Published: 05/06/2025
DOI: 10.64091/ATIHL.2025.000168
AVE Trends in Intelligent Health Letters, 2025 Vol. 2 No. 2 , Pages: 85-93