Jahanzaib Ali Khan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Jahanzaib Ali Khan has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Amanullah Yasin
Department of Computer Science, Bahria School of Engineering and Applied Science, Islamabad, Pakistan
1 shared publication Muhammad Arslan
Department of Creative Technology, Air University, Islamabad 44000, Pakistan
1 shared publication- Muhammad Nadeem
Department of Computer Science, Alhamd Islamic University, Islamabad 44000, Pakistan
1 shared publication - Syeda Wajiha Zahra
Department of Computing, Abasyn University, Islamabad 44000, Pakistan
1 shared publication Waqas Ahmad
Department of Computer Science, Alhamd Islamic University, Islamabad 44000, Pakistan
1 shared publication
Latest Publications
- Open Access
- 29 December 2023
- Published by Universal Wiser Publisher Pte. Ltd in Research Reports on Computer Science
- p. 128-157
Comparative Machine Learning Approaches to Analyzing the Illnesses of the Chronic Renal and Heart Diseases
The considerable increase in the risk of clinical events associated with chronic renal disease makes it a severe global public health issue. Chronic kidney disease (CKD) is a severe global public health issue, increasing the risk of clinical events and being associated with renal failure, cardiovascular disease, and early mortality. An accurate and timely diagnosis is essential. This research paper focuses on the global public health issue of chronic kidney disease (CKD) and its association with cardiovascular disease. It emphasizes the importance of accurate diagnosis and timely intervention for CKD, which poses significant risks to patients’ health. The study proposes a machine learning (ML) approach using deep neural networks and feature selection methods to diagnose CKD and heart attack disease. The ensemble learning algorithms used in this study are decision tree (DT), logistic regression (LR), Naive Bayes (NB), random forest (RF), support vector machine (SVM), and gradient boosted trees (GBT) classifier, as well as one deep learning technique called recurrent neural network (RNN). Feature selection techniques like correlation coefficient methods are used to identify critical characteristics. The evaluation of the proposed approach was conducted using accuracy, precision, recall, and F1 measure metrics. The study employed all features for grid search and testing in each approach.
- 29 December 2023
- Published by Universal Wiser Publisher Pte. Ltd in Research Reports on Computer Science
- p. 128-157
Open AccessComparative Machine Learning Approaches to Analyzing the Illnesses of the Chronic Renal and Heart Diseases
The considerable increase in the risk of clinical events associated with chronic renal disease makes it a severe global public health issue. Chronic kidney disease (CKD) is a severe global public health issue, increasing the risk of clinical events and being associated with renal failure, cardiovascular disease, and early mortality. An accurate and timely diagnosis is essential. This research paper focuses on the global public health issue of chronic kidney disease (CKD) and its association with cardiovascular disease. It emphasizes the importance of accurate diagnosis and timely intervention for CKD, which poses significant risks to patients’ health. The study proposes a machine learning (ML) approach using deep neural networks and feature selection methods to diagnose CKD and heart attack disease. The ensemble learning algorithms used in this study are decision tree (DT), logistic regression (LR), Naive Bayes (NB), random forest (RF), support vector machine (SVM), and gradient boosted trees (GBT) classifier, as well as one deep learning technique called recurrent neural network (RNN). Feature selection techniques like correlation coefficient methods are used to identify critical characteristics. The evaluation of the proposed approach was conducted using accuracy, precision, recall, and F1 measure metrics. The study employed all features for grid search and testing in each approach.