Laboratory diagnostic pathways using machine learning

Muhammad Arif; Muhammad Ahsan Aslam; Haseeb Ur Rehman; Mohsin Abbas; Sarrah Bukhari

Author(s)

Muhammad Arif Department of Computer Science, NFC_IET, Multan, Pakistan

Muhammad Ahsan Aslam Department of Computer Science, Southwest Jiaotong University,(SWJTU), Chengdu,China

Haseeb Ur Rehman Department of Computer Science, Bahauddin Zakariya University,Multan,Pakistan

Mohsin Abbas Department of Physiotherapy, KAIMS International Institute,Multan,Pakistan

Sarrah Bukhari Department of Computer Science, NFC_IET, Multan, Pakistan

Abstract

The healthcare is one of the serious problems for the society. It is necessary for patients and to detect disease quickly in order to start appropriate cares. The most difficult problem is to detect disease, some other fields such as computer science and statistics support for searches [1]. In a formal way to detect human disease i.e. through medical tests are too expensive that poor patients don't afford. It is need of need of society to propose the alternative path to detect human disease. Modern machine learning algorithms are used to uncover intriguing patterns and provide non-trivial predictions that are valuable in decision making. In this research blood donation and HEP-C advancement are predicted hybrid by using simple tests reports values that are simple, easy, non invasive and cheapest way especially for periodically repeated HEP_C diagnosing patients. The accuracies of 5 algorithms is compared to each other by using recall, precision,f1 score and specificity metrics [2]. In this study, five different methods for predicting HEP-C progression are examined. The logistic regression model was found to be the best classifier for HEP-C progression prediction in the comparison research.

Publication Details

Page(s) 78-85

DOI DOI not available

Published Journal: VFAST Transactions on Software Engineering, Volume: 10, Issue: 1, Year: 2022

Request the full text from PASTIC

Keywords

Machine learning, Blood donor, Blood donor, Prediction, Algorithms, hepatitis –c, XG Boost, healthcare disease