A Machine Learning Framework for COVID-19 Prognosis Based on CT Imaging

View Sample PDF

Author(s): Usharani Bhimavarapu (Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, India)
Copyright: 2026
Pages: 26
Source title: Intersecting AI and Medicine for Improved Care and Administrative Efficiency
Source Author(s)/Editor(s): Omar Ali (Abdullah Al Salem University, Kuwait), Abbas Amini (Abdullah Al Salem University, Kuwait)and Ahmad Al-Ahmad (Gulf University for Science and Technology, Kuwait)
DOI: 10.4018/979-8-3373-1772-4.ch010

Keywords: Medical Diagnosis and Practice / Medical Information Science Reference / Medical Technologies / Medicine & Healthcare

Purchase

View A Machine Learning Framework for COVID-19 Prognosis Based on CT Imaging on the publisher's website for pricing and purchasing information.

Abstract

This study is based on the application of predictive analytics to inform clinical decision-making for COVID-19 suspected patients based on CT scan images and reports collected from March 1, 2023, to April 22, 2023. Standardization and preprocessing was applied to expert radiologist reports, while CT images were filtered and normalized to improve the quality of data. Particle Swarm Optimization (PSO) was employed for effective feature selection to identify the most relevant attributes associated with COVID-19-related lung changes. A Gated Recurrent Unit (GRU) neural network model was then developed to capture temporal relationships between patient data and predict clinical outcomes accurately. Integration of these approaches presented a robust prediction tool that allows for early diagnosis and treatment planning. This approach indicates potential for high-level machine learning applied to medical imaging data in the enhancement of pandemic healthcare delivery.

The IRMA Community

Research IRM

A Machine Learning Framework for COVID-19 Prognosis Based on CT Imaging

Purchase

Abstract

Related Content

IRMA Sponsors