Optimized machine learning based comparative analysis of predictive models for classification of kidney tumors
Vatsala Anand1, Ajay Khajuria2, Rupendra Kumar Pachauri3,4
1Department of Computer Science and Engineering, Akal University, Talwandi Sabo, Bathinda, Punjab, India.
Abstract:
The kidney is an important organ that helps clean the blood by removing waste, extra fluids, and harmful substances. It also keeps the balance of minerals in the body and helps control blood pressure. But if the kidney gets sick, like from a tumor, it can cause big health problems. Finding kidney issues early and knowing what kind of problem it has is very important for good treatment and better results for patients. In this study, different machine learning models were used to detect and classify kidney tumors. These models included Decision Tree, XGBoost Classifier, K-Nearest Neighbors (KNN), Random Forest, and Support Vector Machine (SVM). The dataset splitting is done in two ways 80:20 and 75:25 and the models worked best with the 80:20 split. Among them, the top three models-SVM, KNN, and XGBoost-were tested with different batch sizes, which are 16 and 32. SVM performed best when the batch size was 32. These models were also trained using two types of optimizers, called Adam and SGD. SVM did better when using the Adam method. SVM had the highest accuracy of 98. 5%, then came KNN with 90.4%. This method will help healthcare professionals in the early diagnosis of disease.
Insights
Machine learning models accurately detect and classify kidney tumors. Support Vector Machine (SVM) achieved 98.5% accuracy, aiding early disease diagnosis.
Area of Science:
- Nephrology
- Medical Imaging
- Artificial Intelligence
Background:
- Kidney tumors pose significant health risks.
- Early detection and classification are crucial for effective treatment and patient outcomes.
- Machine learning offers potential for improving diagnostic accuracy.
Purpose of the Study:
- To evaluate the efficacy of various machine learning models in detecting and classifying kidney tumors.
- To identify the optimal model and hyperparameters for kidney tumor classification.
Main Methods:
- Utilized Decision Tree, XGBoost Classifier, K-Nearest Neighbors (KNN), Random Forest, and Support Vector Machine (SVM) models.
- Dataset splitting ratios of 80:20 and 75:25 were employed, with 80:20 yielding superior performance.
- Optimized models using batch sizes of 16 and 32, and Adam and SGD optimizers.
Main Results:
- The 80:20 data split improved model performance.
- Support Vector Machine (SVM) demonstrated the highest accuracy at 98.5% with a batch size of 32 and Adam optimizer.
- K-Nearest Neighbors (KNN) achieved 90.4% accuracy.
Conclusions:
- Machine learning models, particularly SVM, show high potential for accurate kidney tumor detection and classification.
- This approach can assist healthcare professionals in early disease diagnosis.
- Further research can refine these models for clinical application.
More Related Videos
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
