1
|
Rehman AU, Mian SH, Usmani YS, Abidi MH, Mohammed MK. Modeling Consequences of COVID-19 and Assessing Its Epidemiological Parameters: A System Dynamics Approach. Healthcare (Basel) 2023; 11:healthcare11020260. [PMID: 36673628 PMCID: PMC9858678 DOI: 10.3390/healthcare11020260] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2022] [Revised: 01/08/2023] [Accepted: 01/10/2023] [Indexed: 01/19/2023] Open
Abstract
In 2020, coronavirus (COVID-19) was declared a global pandemic and it remains prevalent today. A necessity to model the transmission of the virus has emerged as a result of COVID-19's exceedingly contagious characteristics and its rapid propagation throughout the world. Assessing the incidence of infection could enable policymakers to identify measures to halt the pandemic and gauge the required capacity of healthcare centers. Therefore, modeling the susceptibility, exposure, infection, and recovery in relation to the COVID-19 pandemic is crucial for the adoption of interventions by regulatory authorities. Fundamental factors, such as the infection rate, mortality rate, and recovery rate, must be considered in order to accurately represent the behavior of the pandemic using mathematical models. The difficulty in creating a mathematical model is in identifying the real model variables. Parameters might vary significantly across models, which can result in variations in the simulation results because projections primarily rely on a particular dataset. The purpose of this work was to establish a susceptible-exposed-infected-recovered (SEIR) model describing the propagation of the COVID-19 outbreak throughout the Kingdom of Saudi Arabia (KSA). The goal of this study was to derive the essential COVID-19 epidemiological factors from actual data. System dynamics modeling and design of experiment approaches were used to determine the most appropriate combination of epidemiological parameters and the influence of COVID-19. This study investigates how epidemiological variables such as seasonal amplitude, social awareness impact, and waning time can be adapted to correctly estimate COVID-19 scenarios such as the number of infected persons on a daily basis in KSA. This model can also be utilized to ascertain how stress (or hospital capacity) affects the percentage of hospitalizations and the number of deaths. Additionally, the results of this study can be used to establish policies or strategies for monitoring or restricting COVID-19 in Saudi Arabia.
Collapse
Affiliation(s)
- Ateekh Ur Rehman
- Department of Industrial Engineering, College of Engineering, King Saud University, Riyadh 11421, Saudi Arabia
- Correspondence:
| | - Syed Hammad Mian
- Advanced Manufacturing Institute, King Saud University, Riyadh 11421, Saudi Arabia
| | - Yusuf Siraj Usmani
- Department of Industrial Engineering, College of Engineering, King Saud University, Riyadh 11421, Saudi Arabia
| | - Mustufa Haider Abidi
- Advanced Manufacturing Institute, King Saud University, Riyadh 11421, Saudi Arabia
| | - Muneer Khan Mohammed
- Advanced Manufacturing Institute, King Saud University, Riyadh 11421, Saudi Arabia
| |
Collapse
|
2
|
Bazilevych KO, Chumachenko DI, Hulianytskyi LF, Meniailov IS, Yakovlev SV. Intelligent Decision-Support System for Epidemiological Diagnostics. I. A Concept of Architecture Design. CYBERNETICS AND SYSTEMS ANALYSIS 2022; 58:343-353. [PMID: 36065231 PMCID: PMC9433526 DOI: 10.1007/s10559-022-00466-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/01/2021] [Indexed: 06/15/2023]
Abstract
The problems of decision support for epidemiological diagnostics are investigated. The basis for supporting decision-making is mathematical tools for analyzing morbidity data, as well as modeling of epidemic processes. The current state of research in this area is analyzed. The features of decision-making in epidemiology and public health are formalized. Principles for the development of an intelligent information system for decision-making support for epidemiological diagnostics are proposed. A systemic model of the system, a model of the interaction of elements of the epidemiological diagnostics system and the interaction of logical components of the information system has been developed. Taking into account the identified features of these processes, the concept of the architecture of such an intelligent information system is proposed.
Collapse
Affiliation(s)
- K. O. Bazilevych
- M. Ye. Zhukovsky National Aerospace University “Kharkiv Aviation Institute,”, Kharkiv, Ukraine
| | - D. I. Chumachenko
- M. Ye. Zhukovsky National Aerospace University “Kharkiv Aviation Institute,”, Kharkiv, Ukraine
| | - L. F. Hulianytskyi
- V. M. Glushkov Institute of Cybernetics, National Academy of Sciences of Ukraine, Kyiv, Ukraine
| | - I. S. Meniailov
- M. Ye. Zhukovsky National Aerospace University “Kharkiv Aviation Institute,”, Kharkiv, Ukraine
| | - S. V. Yakovlev
- M. Ye. Zhukovsky National Aerospace University “Kharkiv Aviation Institute,”, Kharkiv, Ukraine
| |
Collapse
|
3
|
Laddha S, Mnasri S, Alghamdi M, Kumar V, Kaur M, Alrashidi M, Almuhaimeed A, Alshehri A, Alrowaily MA, Alkhazi I. COVID-19 Diagnosis and Classification Using Radiological Imaging and Deep Learning Techniques: A Comparative Study. Diagnostics (Basel) 2022; 12:1880. [PMID: 36010231 PMCID: PMC9406661 DOI: 10.3390/diagnostics12081880] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/05/2022] [Revised: 07/23/2022] [Accepted: 07/25/2022] [Indexed: 11/16/2022] Open
Abstract
In December 2019, the novel coronavirus disease 2019 (COVID-19) appeared. Being highly contagious and with no effective treatment available, the only solution was to detect and isolate infected patients to further break the chain of infection. The shortage of test kits and other drawbacks of lab tests motivated researchers to build an automated diagnosis system using chest X-rays and CT scanning. The reviewed works in this study use AI coupled with the radiological image processing of raw chest X-rays and CT images to train various CNN models. They use transfer learning and numerous types of binary and multi-class classifications. The models are trained and validated on several datasets, the attributes of which are also discussed. The obtained results of various algorithms are later compared using performance metrics such as accuracy, F1 score, and AUC. Major challenges faced in this research domain are the limited availability of COVID image data and the high accuracy of the prediction of the severity of patients using deep learning compared to well-known methods of COVID-19 detection such as PCR tests. These automated detection systems using CXR technology are reliable enough to help radiologists in the initial screening and in the immediate diagnosis of infected individuals. They are preferred because of their low cost, availability, and fast results.
Collapse
Affiliation(s)
- Saloni Laddha
- Computer Science and Engineering Department, National Institute of Technology Hamirpur, Hamirpur 177005, Himachal Pradesh, India; (S.L.); (V.K.)
| | - Sami Mnasri
- Department of Computer Science, Applied College, University of Tabuk, Tabuk 47512, Saudi Arabia; (M.A.); (M.A.); (A.A.); (M.A.A.)
- Department of Computer Science, ISSAT of Gafsa, University of Gafsa, Gafsa 2112, Tunisia
| | - Mansoor Alghamdi
- Department of Computer Science, Applied College, University of Tabuk, Tabuk 47512, Saudi Arabia; (M.A.); (M.A.); (A.A.); (M.A.A.)
| | - Vijay Kumar
- Computer Science and Engineering Department, National Institute of Technology Hamirpur, Hamirpur 177005, Himachal Pradesh, India; (S.L.); (V.K.)
| | - Manjit Kaur
- School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju 61005, Korea;
| | - Malek Alrashidi
- Department of Computer Science, Applied College, University of Tabuk, Tabuk 47512, Saudi Arabia; (M.A.); (M.A.); (A.A.); (M.A.A.)
| | - Abdullah Almuhaimeed
- The National Centre for Genomics Technologies and Bioinformatics, King Abdulaziz City for Science and Technology, Riyadh 11442, Saudi Arabia
| | - Ali Alshehri
- Department of Computer Science, Applied College, University of Tabuk, Tabuk 47512, Saudi Arabia; (M.A.); (M.A.); (A.A.); (M.A.A.)
| | - Majed Abdullah Alrowaily
- Department of Computer Science, Applied College, University of Tabuk, Tabuk 47512, Saudi Arabia; (M.A.); (M.A.); (A.A.); (M.A.A.)
| | - Ibrahim Alkhazi
- College of Computers & Information Technology, University of Tabuk, Tabuk 47512, Saudi Arabia;
| |
Collapse
|
4
|
Muñoz-Organero M, Queipo-Álvarez P. Deep Spatiotemporal Model for COVID-19 Forecasting. SENSORS 2022; 22:s22093519. [PMID: 35591208 PMCID: PMC9101138 DOI: 10.3390/s22093519] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/07/2022] [Revised: 04/29/2022] [Accepted: 05/03/2022] [Indexed: 11/24/2022]
Abstract
COVID-19 has caused millions of infections and deaths over the last 2 years. Machine learning models have been proposed as an alternative to conventional epidemiologic models in an effort to optimize short- and medium-term forecasts that will help health authorities to optimize the use of policies and resources to tackle the spread of the SARS-CoV-2 virus. Although previous machine learning models based on time pattern analysis for COVID-19 sensed data have shown promising results, the spread of the virus has both spatial and temporal components. This manuscript proposes a new deep learning model that combines a time pattern extraction based on the use of a Long-Short Term Memory (LSTM) Recurrent Neural Network (RNN) over a preceding spatial analysis based on a Convolutional Neural Network (CNN) applied to a sequence of COVID-19 incidence images. The model has been validated with data from the 286 health primary care centers in the Comunidad de Madrid (Madrid region, Spain). The results show improved scores in terms of both root mean square error (RMSE) and explained variance (EV) when compared with previous models that have mainly focused on the temporal patterns and dependencies.
Collapse
|
5
|
RDPVR: Random Data Partitioning with Voting Rule for Machine Learning from Class-Imbalanced Datasets. ELECTRONICS 2022. [DOI: 10.3390/electronics11020228] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/22/2022]
Abstract
Since most classifiers are biased toward the dominant class, class imbalance is a challenging problem in machine learning. The most popular approaches to solving this problem include oversampling minority examples and undersampling majority examples. Oversampling may increase the probability of overfitting, whereas undersampling eliminates examples that may be crucial to the learning process. We present a linear time resampling method based on random data partitioning and a majority voting rule to address both concerns, where an imbalanced dataset is partitioned into a number of small subdatasets, each of which must be class balanced. After that, a specific classifier is trained for each subdataset, and the final classification result is established by applying the majority voting rule to the results of all of the trained models. We compared the performance of the proposed method to some of the most well-known oversampling and undersampling methods, employing a range of classifiers, on 33 benchmark machine learning class-imbalanced datasets. The classification results produced by the classifiers employed on the generated data by the proposed method were comparable to most of the resampling methods tested, with the exception of SMOTEFUNA, which is an oversampling method that increases the probability of overfitting. The proposed method produced results that were comparable to the Easy Ensemble (EE) undersampling method. As a result, for solving the challenge of machine learning from class-imbalanced datasets, we advocate using either EE or our method.
Collapse
|