A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
A Comparative Analysis of Machine Learning Algorithms for Enhancing Liver Disease Diagnosis
Liver disease, a significant health disease often arises from factors such as infections, genetics, and lifestyle choices. It is ranked as the eleventh leading cause of death worldwide, accounting for 4% of global deaths. The use of artificial intelligence (AI) can greatly aid in the early detection of this disease, as it has achieved groundbreaking advancements in enhancing the medical diagnostic processes through its ability to analyze complex medical data. This paper introduces a comparative analysis of 16 machine learning models to improve the accuracy of liver disease classification from clinical datasets, a task conventionally performed by medical professionals. Utilizing a range of algorithms, from logistic regression to advanced deep neural networks, the study examines models' accuracy, precision, recall, and F1-scores, providing a comprehensive evaluation of each models' capabilities. The proposed comparative analysis revealed varying degrees of effectiveness in classifying liver disease; the Random Forest Classifier with PCA & Feature Selection, alongside the Artificial Neural Network (ANN), demonstrated perfect performance, achieving perfect scores of 100% across all metrics: accuracy, precision, recall, and F1-score. This indicates their excellent ability to classify liver disease accurately without any misclassifications. This study highlights the significant impact that the different AI models have on diagnostic accuracy.
A Comparative Analysis of Machine Learning Algorithms for Enhancing Liver Disease Diagnosis
Liver disease, a significant health disease often arises from factors such as infections, genetics, and lifestyle choices. It is ranked as the eleventh leading cause of death worldwide, accounting for 4% of global deaths. The use of artificial intelligence (AI) can greatly aid in the early detection of this disease, as it has achieved groundbreaking advancements in enhancing the medical diagnostic processes through its ability to analyze complex medical data. This paper introduces a comparative analysis of 16 machine learning models to improve the accuracy of liver disease classification from clinical datasets, a task conventionally performed by medical professionals. Utilizing a range of algorithms, from logistic regression to advanced deep neural networks, the study examines models' accuracy, precision, recall, and F1-scores, providing a comprehensive evaluation of each models' capabilities. The proposed comparative analysis revealed varying degrees of effectiveness in classifying liver disease; the Random Forest Classifier with PCA & Feature Selection, alongside the Artificial Neural Network (ANN), demonstrated perfect performance, achieving perfect scores of 100% across all metrics: accuracy, precision, recall, and F1-score. This indicates their excellent ability to classify liver disease accurately without any misclassifications. This study highlights the significant impact that the different AI models have on diagnostic accuracy.
A Comparative Analysis of Machine Learning Algorithms for Enhancing Liver Disease Diagnosis
Alobaid, Ahmad (author) / Bonny, Talal (author)
2024-06-03
2090036 byte
Conference paper
Electronic Resource
English
Enhancing Machine Learning Algorithms to Assess Rock Burst Phenomena
| Online Contents | 2021
| Springer Verlag | 2023
Is China’s Urbanization Inclusive?—Comparative Research Based on Machine Learning Algorithms
| DOAJ | 2023