Year: 2024
Type: article
Abstract: This study tackles the critical challenge of detecting Acute Liver Failure (ALF) using machine learning algorithms. The main goal is to assess the effectiveness of several algorithms, including Convolutional Neural Network (CNN), Support Vector Machine (SVM), Decision Tree, K-Nearest Neighbors (KNN), Gaussian Naive Bayes (GNB), and Gradient Boosting, in accurately classifying cases of ALF. For this purpose, a comprehensive dataset with 8,785 records and 30 features from Kaggle is utilized, involving thorough preprocessing steps like feature selection, data cleaning, and normalization. The research emphasizes achieving high precision in ALF detection. Results show that CNN outperforms other algorithms, achieving a precision score of 1.00 for identifying ALF cases, demonstrating its high reliability. This study highlights the importance of algorithm selection in complex medical diagnoses, showcasing the potential of deep learning methods in healthcare and paving the way for more accurate and timely ALF detection to improve patient outcomes.
Authors: Sarah Anjani, Maria Yohana Jawa Betan
Institutions: Universitas Gadjah Mada, Universitas Respati Yogyakarta
Language: English
Subfield: Health Information Management
Field: Health Professions
Domain: Health Sciences
Open Access status: hybrid
OpenAlex ID: W4411447751