1
|
Tariq MU, Ismail SB. Deep learning in public health: Comparative predictive models for COVID-19 case forecasting. PLoS One 2024; 19:e0294289. [PMID: 38483948 PMCID: PMC10939212 DOI: 10.1371/journal.pone.0294289] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/22/2023] [Accepted: 10/28/2023] [Indexed: 03/17/2024] Open
Abstract
The COVID-19 pandemic has had a significant impact on both the United Arab Emirates (UAE) and Malaysia, emphasizing the importance of developing accurate and reliable forecasting mechanisms to guide public health responses and policies. In this study, we compared several cutting-edge deep learning models, including Long Short-Term Memory (LSTM), bidirectional LSTM, Convolutional Neural Networks (CNN), hybrid CNN-LSTM, Multilayer Perceptron's, and Recurrent Neural Networks (RNN), to project COVID-19 cases in the aforementioned regions. These models were calibrated and evaluated using a comprehensive dataset that includes confirmed case counts, demographic data, and relevant socioeconomic factors. To enhance the performance of these models, Bayesian optimization techniques were employed. Subsequently, the models were re-evaluated to compare their effectiveness. Analytic approaches, both predictive and retrospective in nature, were used to interpret the data. Our primary objective was to determine the most effective model for predicting COVID-19 cases in the United Arab Emirates (UAE) and Malaysia. The findings indicate that the selected deep learning algorithms were proficient in forecasting COVID-19 cases, although their efficacy varied across different models. After a thorough evaluation, the model architectures most suitable for the specific conditions in the UAE and Malaysia were identified. Our study contributes significantly to the ongoing efforts to combat the COVID-19 pandemic, providing crucial insights into the application of sophisticated deep learning algorithms for the precise and timely forecasting of COVID-19 cases. These insights hold substantial value for shaping public health strategies, enabling authorities to develop targeted and evidence-based interventions to manage the virus spread and its impact on the populations of the UAE and Malaysia. The study confirms the usefulness of deep learning methodologies in efficiently processing complex datasets and generating reliable projections, a skill of great importance in healthcare and professional settings.
Collapse
Affiliation(s)
- Muhammad Usman Tariq
- Abu Dhabi University, Abu Dhabi, United Arab Emirates
- Universiti Tun Hussein Onn Malaysia (UTHM), Parit Raja, Malaysia
| | | |
Collapse
|
2
|
Li H, Cheng ZJ, Fu X, Liu M, Liu P, Cao W, Liang Z, Wang F, Sun B. Decoding acute myocarditis in patients with COVID-19: Early detection through machine learning and hematological indices. iScience 2024; 27:108524. [PMID: 38303719 PMCID: PMC10831249 DOI: 10.1016/j.isci.2023.108524] [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: 05/31/2023] [Revised: 11/14/2023] [Accepted: 11/20/2023] [Indexed: 02/03/2024] Open
Abstract
During the persistent COVID-19 pandemic, the swift progression of acute myocarditis has emerged as a profound concern due to its augmented mortality, underscoring the urgency of prompt diagnosis. This study analyzed blood samples from 5,230 COVID-19 individuals, identifying key blood and myocardial markers that illuminate the relationship between COVID-19 severity and myocarditis. A predictive model, applying Bayesian and random forest methodologies, was constructed for myocarditis' early identification, unveiling a balanced gender distribution in myocarditis cases contrary to a male predominance in COVID-19 occurrences. Particularly, older men exhibited heightened vulnerability to severe COVID-19 strains. The analysis revealed myocarditis was notably prevalent in younger demographics, and two subvariants COVID-19 progression paths were identified, characterized by symptom intensity and specific blood indicators. The enhanced myocardial marker model displayed remarkable diagnostic accuracy, advocating its valuable application in future myocarditis detection and treatment strategies amidst the COVID-19 crisis.
Collapse
Affiliation(s)
- Haiyang Li
- Department of Clinical Laboratory, National Clinical Research Center of Respiratory Disease, Guangzhou Institute of Respiratory Health, First Affiliated Hospital of Guangzhou Medical University, Guangzhou Medical University, Guangzhou 510120, China
- MRC Biostatistics Unit, University of Cambridge, Cambridge CB2 0SR, UK
| | - Zhangkai J. Cheng
- Department of Clinical Laboratory, National Clinical Research Center of Respiratory Disease, Guangzhou Institute of Respiratory Health, First Affiliated Hospital of Guangzhou Medical University, Guangzhou Medical University, Guangzhou 510120, China
| | - Xing Fu
- Group of Theoretical Biology, School of Life Sciences, Sun Yat-sen University, Guangzhou 510275, China
| | - Mingtao Liu
- Department of Clinical Laboratory, National Clinical Research Center of Respiratory Disease, Guangzhou Institute of Respiratory Health, First Affiliated Hospital of Guangzhou Medical University, Guangzhou Medical University, Guangzhou 510120, China
| | - Peng Liu
- Department of Clinical Pharmacy, Dazhou Central Hospital, Dazhou 635000, China
| | - Wenhan Cao
- Department of Clinical Laboratory, National Clinical Research Center of Respiratory Disease, Guangzhou Institute of Respiratory Health, First Affiliated Hospital of Guangzhou Medical University, Guangzhou Medical University, Guangzhou 510120, China
| | - Zhiman Liang
- Department of Clinical Laboratory, National Clinical Research Center of Respiratory Disease, Guangzhou Institute of Respiratory Health, First Affiliated Hospital of Guangzhou Medical University, Guangzhou Medical University, Guangzhou 510120, China
| | - Fei Wang
- Department of Clinical Pharmacy, Dazhou Central Hospital, Dazhou 635000, China
| | - Baoqing Sun
- Department of Clinical Laboratory, National Clinical Research Center of Respiratory Disease, Guangzhou Institute of Respiratory Health, First Affiliated Hospital of Guangzhou Medical University, Guangzhou Medical University, Guangzhou 510120, China
| |
Collapse
|
3
|
Kang JY, Bae YS, Chie EK, Lee SB. Predicting Deterioration from Wearable Sensor Data in People with Mild COVID-19. SENSORS (BASEL, SWITZERLAND) 2023; 23:9597. [PMID: 38067970 PMCID: PMC10708735 DOI: 10.3390/s23239597] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/07/2023] [Revised: 11/29/2023] [Accepted: 11/30/2023] [Indexed: 12/18/2023]
Abstract
Coronavirus has caused many casualties and is still spreading. Some people experience rapid deterioration that is mild at first. The aim of this study is to develop a deterioration prediction model for mild COVID-19 patients during the isolation period. We collected vital signs from wearable devices and clinical questionnaires. The derivation cohort consisted of people diagnosed with COVID-19 between September and December 2021, and the external validation cohort collected between March and June 2022. To develop the model, a total of 50 participants wore the device for an average of 77 h. To evaluate the model, a total of 181 infected participants wore the device for an average of 65 h. We designed machine learning-based models that predict deterioration in patients with mild COVID-19. The prediction model, 10 min in advance, showed an area under the receiver characteristic curve (AUC) of 0.99, and the prediction model, 8 h in advance, showed an AUC of 0.84. We found that certain variables that are important to model vary depending on the point in time to predict. Efficient deterioration monitoring in many patients is possible by utilizing data collected from wearable sensors and symptom self-reports.
Collapse
Affiliation(s)
- Jin-Yeong Kang
- Department of Medical Informatics, Keimyung University, Daegu 42601, Republic of Korea;
- Department of Statistics and Data Science, Yonsei University, Seoul 03722, Republic of Korea
| | - Ye Seul Bae
- Department of Family Medicine, Kangbuk Samsung Hospital, Sungkyunkwan University School of Medicine, Seoul 03181, Republic of Korea;
- Department of Future Healthcare Planning, Kangbuk Samsung Hospital, Sungkyunkwan University School of Medicine, Seoul 03181, Republic of Korea
| | - Eui Kyu Chie
- Department of Radiation Oncology, Seoul National University College of Medicine, Seoul 03080, Republic of Korea;
| | - Seung-Bo Lee
- Department of Medical Informatics, Keimyung University, Daegu 42601, Republic of Korea;
| |
Collapse
|
4
|
Lashen H, St John TL, Almallah YZ, Sasidhar M, Shamout FE. Machine Learning Models Versus the National Early Warning Score System for Predicting Deterioration: Retrospective Cohort Study in the United Arab Emirates. JMIR AI 2023; 2:e45257. [PMID: 38875543 PMCID: PMC11041421 DOI: 10.2196/45257] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/02/2023] [Revised: 06/19/2023] [Accepted: 08/01/2023] [Indexed: 06/16/2024]
Abstract
BACKGROUND Early warning score systems are widely used for identifying patients who are at the highest risk of deterioration to assist clinical decision-making. This could facilitate early intervention and consequently improve patient outcomes; for example, the National Early Warning Score (NEWS) system, which is recommended by the Royal College of Physicians in the United Kingdom, uses predefined alerting thresholds to assign scores to patients based on their vital signs. However, there is limited evidence of the reliability of such scores across patient cohorts in the United Arab Emirates. OBJECTIVE Our aim in this study was to propose a data-driven model that accurately predicts in-hospital deterioration in an inpatient cohort in the United Arab Emirates. METHODS We conducted a retrospective cohort study using a real-world data set that consisted of 16,901 unique patients associated with 26,073 inpatient emergency encounters and 951,591 observation sets collected between April 2015 and August 2021 at a large multispecialty hospital in Abu Dhabi, United Arab Emirates. The observation sets included routine measurements of heart rate, respiratory rate, systolic blood pressure, level of consciousness, temperature, and oxygen saturation, as well as whether the patient was receiving supplementary oxygen. We divided the data set of 16,901 unique patients into training, validation, and test sets consisting of 11,830 (70%; 18,319/26,073, 70.26% emergency encounters), 3397 (20.1%; 5206/26,073, 19.97% emergency encounters), and 1674 (9.9%; 2548/26,073, 9.77% emergency encounters) patients, respectively. We defined an adverse event as the occurrence of admission to the intensive care unit, mortality, or both if the patient was admitted to the intensive care unit first. On the basis of 7 routine vital signs measurements, we assessed the performance of the NEWS system in detecting deterioration within 24 hours using the area under the receiver operating characteristic curve (AUROC). We also developed and evaluated several machine learning models, including logistic regression, a gradient-boosting model, and a feed-forward neural network. RESULTS In a holdout test set of 2548 encounters with 95,755 observation sets, the NEWS system achieved an overall AUROC value of 0.682 (95% CI 0.673-0.690). In comparison, the best-performing machine learning models, which were the gradient-boosting model and the neural network, achieved AUROC values of 0.778 (95% CI 0.770-0.785) and 0.756 (95% CI 0.749-0.764), respectively. Our interpretability results highlight the importance of temperature and respiratory rate in predicting patient deterioration. CONCLUSIONS Although traditional early warning score systems are the dominant form of deterioration prediction models in clinical practice today, we strongly recommend the development and use of cohort-specific machine learning models as an alternative. This is especially important in external patient cohorts that were unseen during model development.
Collapse
Affiliation(s)
- Hazem Lashen
- Engineering Division, New York University Abu Dhabi, Abu Dhabi, United Arab Emirates
| | | | | | - Madhu Sasidhar
- Cleveland Clinic Tradition Hospital, Port St. Lucie, FL, United States
| | - Farah E Shamout
- Engineering Division, New York University Abu Dhabi, Abu Dhabi, United Arab Emirates
| |
Collapse
|
5
|
Verma P, Gupta A, Kumar M, Gill SS. FCMCPS-COVID: AI propelled fog-cloud inspired scalable medical cyber-physical system, specific to coronavirus disease. INTERNET OF THINGS (AMSTERDAM, NETHERLANDS) 2023; 23:100828. [PMID: 37274449 PMCID: PMC10214767 DOI: 10.1016/j.iot.2023.100828] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 04/13/2023] [Revised: 05/11/2023] [Accepted: 05/20/2023] [Indexed: 06/06/2023]
Abstract
Medical cyber-physical systems (MCPS) firmly integrate a network of medical objects. These systems are highly efficacious and have been progressively used in the Healthcare 4.0 to achieve continuous high-quality services. Healthcare 4.0 encompasses numerous emerging technologies and their applications have been realized in the monitoring of a variety of virus outbreaks. As a growing healthcare trend, coronavirus disease (COVID-19) can be cured and its spread can be prevented using MCPS. This virus spreads from human to human and can have devastating consequences. Moreover, with the alarmingly rising death rate and new cases across the world, there is an urgent need for continuous identification and screening of infected patients to mitigate their spread. Motivated by the facts, we propose a framework for early detection, prevention, and control of the COVID-19 outbreak by using novel Industry 5.0 technologies. The proposed framework uses a dimensionality reduction technique in the fog layer, allowing high-quality data to be used for classification purposes. The fog layer also uses the ensemble learning-based data classification technique for the detection of COVID-19 patients based on the symptomatic dataset. In addition, in the cloud layer, social network analysis (SNA) has been performed to control the spread of COVID-19. The experimental results reveal that compared with state-of-the-art methods, the proposed framework achieves better results in terms of accuracy (82.28 %), specificity (91.42 %), sensitivity (90 %) and stability with effective response time. Furthermore, the utilization of CVI-based alert generation at the fog layer improves the novelty aspects of the proposed system.
Collapse
Affiliation(s)
- Prabal Verma
- Department of Information Technology, National Institute of Technology, Srinagar, India
| | - Aditya Gupta
- Department of Computer Science and Engineering, Manipal University Jaipur, Jaipur, India
| | - Mohit Kumar
- Department of Information Technology, National Institute of Technology, Jalandhar, India
| | - Sukhpal Singh Gill
- School of Electronic Engineering and Computer Science, Queen Mary University Of London, UK
| |
Collapse
|
6
|
Casano N, Santini SJ, Vittorini P, Sinatti G, Carducci P, Mastroianni CM, Ciardi MR, Pasculli P, Petrucci E, Marinangeli F, Balsano C. Application of machine learning approach in emergency department to support clinical decision making for SARS-CoV-2 infected patients. J Integr Bioinform 2023; 20:jib-2022-0047. [PMID: 36877860 PMCID: PMC10561065 DOI: 10.1515/jib-2022-0047] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/20/2022] [Revised: 01/20/2023] [Accepted: 02/08/2023] [Indexed: 03/08/2023] Open
Abstract
To support physicians in clinical decision process on patients affected by Coronavirus Disease 2019 (COVID-19) in areas with a low vaccination rate, we devised and evaluated the performances of several machine learning (ML) classifiers fed with readily available clinical and laboratory data. Our observational retrospective study collected data from a cohort of 779 COVID-19 patients presenting to three hospitals of the Lazio-Abruzzo area (Italy). Based on a different selection of clinical and respiratory (ROX index and PaO2/FiO2 ratio) variables, we devised an AI-driven tool to predict safe discharge from ED, disease severity and mortality during hospitalization. To predict safe discharge our best classifier is an RF integrated with ROX index that reached AUC of 0.96. To predict disease severity the best classifier was an RF integrated with ROX index that reached an AUC of 0.91. For mortality prediction the best classifier was an RF integrated with ROX index, that reached an AUC of 0.91. The results obtained thanks to our algorithms are consistent with the scientific literature an accomplish significant performances to forecast safe discharge from ED and severe clinical course of COVID-19.
Collapse
Affiliation(s)
- Nicolò Casano
- School of Emergency Medicine, Interdisciplinary BioMedical group on Artificial Intelligence, IBMAI, Department MeSVA, University of L’Aquila, L’Aquila, Italy
| | - Silvano Junior Santini
- School of Emergency Medicine, Interdisciplinary BioMedical group on Artificial Intelligence, IBMAI, Department MeSVA, University of L’Aquila, L’Aquila, Italy
- Francesco Balsano Foundation, Via Giovanni Battista Martini 6, 00198, Rome, Italy
| | - Pierpaolo Vittorini
- School of Emergency Medicine, Interdisciplinary BioMedical group on Artificial Intelligence, IBMAI, Department MeSVA, University of L’Aquila, L’Aquila, Italy
| | - Gaia Sinatti
- School of Emergency Medicine, Interdisciplinary BioMedical group on Artificial Intelligence, IBMAI, Department MeSVA, University of L’Aquila, L’Aquila, Italy
- Francesco Balsano Foundation, Via Giovanni Battista Martini 6, 00198, Rome, Italy
| | - Paolo Carducci
- School of Emergency Medicine, Interdisciplinary BioMedical group on Artificial Intelligence, IBMAI, Department MeSVA, University of L’Aquila, L’Aquila, Italy
| | - Claudio Maria Mastroianni
- Department of Public Health and Infectious Diseases, “Sapienza” University of Rome, Policlinico Umberto I Hospital, Rome, Italy
| | - Maria Rosa Ciardi
- Department of Public Health and Infectious Diseases, “Sapienza” University of Rome, Policlinico Umberto I Hospital, Rome, Italy
| | - Patrizia Pasculli
- Department of Public Health and Infectious Diseases, “Sapienza” University of Rome, Policlinico Umberto I Hospital, Rome, Italy
| | - Emiliano Petrucci
- Department of Anesthesiology, Intensive Care and Pain Treatment, University of L’Aquila, L’Aquila, Italy
| | - Franco Marinangeli
- Department of Anesthesiology, Intensive Care and Pain Treatment, University of L’Aquila, L’Aquila, Italy
| | - Clara Balsano
- School of Emergency Medicine, Interdisciplinary BioMedical group on Artificial Intelligence, IBMAI, Department MeSVA, University of L’Aquila, L’Aquila, Italy
- Francesco Balsano Foundation, Via Giovanni Battista Martini 6, 00198, Rome, Italy
| |
Collapse
|
7
|
Portuondo-Jiménez J, Barrio I, España PP, García J, Villanueva A, Gascón M, Rodríguez L, Larrea N, García-Gutierrez S, Quintana JM. Clinical prediction rules for adverse evolution in patients with COVID-19 by the Omicron variant. Int J Med Inform 2023; 173:105039. [PMID: 36921481 PMCID: PMC9988314 DOI: 10.1016/j.ijmedinf.2023.105039] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2022] [Revised: 02/03/2023] [Accepted: 03/01/2023] [Indexed: 03/08/2023]
Abstract
OBJECTIVE We identify factors related to SARS-CoV-2 infection linked to hospitalization, ICU admission, and mortality and develop clinical prediction rules. METHODS Retrospective cohort study of 380,081 patients with SARS-CoV-2 infection from March 1, 2020 to January 9, 2022, including a subsample of 46,402 patients who attended Emergency Departments (EDs) having data on vital signs. For derivation and external validation of the prediction rule, two different periods were considered: before and after emergence of the Omicron variant, respectively. Data collected included sociodemographic data, COVID-19 vaccination status, baseline comorbidities and treatments, other background data and vital signs at triage at EDs. The predictive models for the EDs and the whole samples were developed using multivariate logistic regression models using Lasso penalization. RESULTS In the multivariable models, common predictive factors of death among EDs patients were greater age; being male; having no vaccination, dementia; heart failure; liver and kidney disease; hemiplegia or paraplegia; coagulopathy; interstitial pulmonary disease; malignant tumors; use chronic systemic use of steroids, higher temperature, low O2 saturation and altered blood pressure-heart rate. The predictors of an adverse evolution were the same, with the exception of liver disease and the inclusion of cystic fibrosis. Similar predictors were found to be related to hospital admission, including liver disease, arterial hypertension, and basal prescription of immunosuppressants. Similarly, models for the whole sample, without vital signs, are presented. CONCLUSIONS We propose risk scales, based on basic information, easily-calculable, high-predictive that also function with the current Omicron variant and may help manage such patients in primary, emergency, and hospital care.
Collapse
Affiliation(s)
- Janire Portuondo-Jiménez
- Osakidetza Basque Health Service, Sub-Directorate for Primary Care Coordination, Vitoria-Gasteiz, Spain; Biocruces Bizkaia Health Research Institute, Barakaldo, Spain; Network for Research on Chronicity, Primary Care, and Health Promotion (RICAPPS), Spain
| | - Irantzu Barrio
- University of the Basque Country UPV/EHU, Department of Mathematics, Leioa, Spain; Basque Center for Applied Mathematics, BCAM, Spain.
| | - Pedro P España
- Biocruces Bizkaia Health Research Institute, Barakaldo, Spain; Osakidetza Basque Health Service, Galdakao-Usansolo University Hospital, Respiratory Unit, Galdakao, Spain
| | - Julia García
- Basque Government Department of Health, Office of Healthcare Planning, Organization and Evaluation, Basque Country, Spain
| | - Ane Villanueva
- Network for Research on Chronicity, Primary Care, and Health Promotion (RICAPPS), Spain; Osakidetza Basque Health Service, Galdakao-Usansolo University Hospital, Research Unit, Galdakao, Spain; Health Service Research Network on Chronic Diseases (REDISSEC), Bilbao, Spain; Kronikgune Institute for Health Services Research, Barakaldo, Spain
| | - María Gascón
- Network for Research on Chronicity, Primary Care, and Health Promotion (RICAPPS), Spain; Osakidetza Basque Health Service, Galdakao-Usansolo University Hospital, Research Unit, Galdakao, Spain; Health Service Research Network on Chronic Diseases (REDISSEC), Bilbao, Spain; Kronikgune Institute for Health Services Research, Barakaldo, Spain
| | | | - Nere Larrea
- Network for Research on Chronicity, Primary Care, and Health Promotion (RICAPPS), Spain; Osakidetza Basque Health Service, Galdakao-Usansolo University Hospital, Research Unit, Galdakao, Spain; Health Service Research Network on Chronic Diseases (REDISSEC), Bilbao, Spain; Kronikgune Institute for Health Services Research, Barakaldo, Spain
| | - Susana García-Gutierrez
- Network for Research on Chronicity, Primary Care, and Health Promotion (RICAPPS), Spain; Osakidetza Basque Health Service, Galdakao-Usansolo University Hospital, Research Unit, Galdakao, Spain; Health Service Research Network on Chronic Diseases (REDISSEC), Bilbao, Spain; Kronikgune Institute for Health Services Research, Barakaldo, Spain
| | - José M Quintana
- Network for Research on Chronicity, Primary Care, and Health Promotion (RICAPPS), Spain; Osakidetza Basque Health Service, Galdakao-Usansolo University Hospital, Research Unit, Galdakao, Spain; Health Service Research Network on Chronic Diseases (REDISSEC), Bilbao, Spain; Kronikgune Institute for Health Services Research, Barakaldo, Spain
| | | |
Collapse
|
8
|
Barough SS, Safavi-Naini SAA, Siavoshi F, Tamimi A, Ilkhani S, Akbari S, Ezzati S, Hatamabadi H, Pourhoseingholi MA. Generalizable machine learning approach for COVID-19 mortality risk prediction using on-admission clinical and laboratory features. Sci Rep 2023; 13:2399. [PMID: 36765157 PMCID: PMC9911952 DOI: 10.1038/s41598-023-28943-z] [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: 10/11/2022] [Accepted: 01/27/2023] [Indexed: 02/12/2023] Open
Abstract
We aimed to propose a mortality risk prediction model using on-admission clinical and laboratory predictors. We used a dataset of confirmed COVID-19 patients admitted to three general hospitals in Tehran. Clinical and laboratory values were gathered on admission. Six different machine learning models and two feature selection methods were used to assess the risk of in-hospital mortality. The proposed model was selected using the area under the receiver operator curve (AUC). Furthermore, a dataset from an additional hospital was used for external validation. 5320 hospitalized COVID-19 patients were enrolled in the study, with a mortality rate of 17.24% (N = 917). Among 82 features, ten laboratories and 27 clinical features were selected by LASSO. All methods showed acceptable performance (AUC > 80%), except for K-nearest neighbor. Our proposed deep neural network on features selected by LASSO showed AUC scores of 83.4% and 82.8% in internal and external validation, respectively. Furthermore, our imputer worked efficiently when two out of ten laboratory parameters were missing (AUC = 81.8%). We worked intimately with healthcare professionals to provide a tool that can solve real-world needs. Our model confirmed the potential of machine learning methods for use in clinical practice as a decision-support system.
Collapse
Affiliation(s)
- Siavash Shirzadeh Barough
- Basic and Molecular Epidemiology of Gastrointestinal Disorders Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Seyed Amir Ahmad Safavi-Naini
- Basic and Molecular Epidemiology of Gastrointestinal Disorders Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Fatemeh Siavoshi
- Basic and Molecular Epidemiology of Gastrointestinal Disorders Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Atena Tamimi
- Basic and Molecular Epidemiology of Gastrointestinal Disorders Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Saba Ilkhani
- Department of Surgery, Center for Surgery and Public Health, Brigham and Women's Hospital, Harvard Medical School and Harvard T.H Chan School of Public Health, Boston, MA, USA
| | - Setareh Akbari
- Basic and Molecular Epidemiology of Gastrointestinal Disorders Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Sadaf Ezzati
- Basic and Molecular Epidemiology of Gastrointestinal Disorders Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Hamidreza Hatamabadi
- Department of Emergency Medicine, School of Medicine, Safety Promotion and Injury Prevention Research Center, Imam Hossein Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Mohamad Amin Pourhoseingholi
- Basic and Molecular Epidemiology of Gastrointestinal Disorders Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
| |
Collapse
|
9
|
Ibrahim Z, Tulay P, Abdullahi J. Multi-region machine learning-based novel ensemble approaches for predicting COVID-19 pandemic in Africa. ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH INTERNATIONAL 2023; 30:3621-3643. [PMID: 35948797 PMCID: PMC9365685 DOI: 10.1007/s11356-022-22373-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 05/09/2022] [Accepted: 07/30/2022] [Indexed: 06/15/2023]
Abstract
Coronavirus disease 2019 (COVID-19) has produced a global pandemic, which has devastating effects on health, economy and social interactions. Despite the less contraction and spread of COVID-19 in Africa compared to some other continents in the world, Africa remains amongst the most vulnerable regions due to less technology and unequipped or poor health system. Recent happenings showed that COVID-19 may stay for years owing to the discoveries of new variants (such as Omicron) and new wave of infections in several countries. Therefore, accurate prediction of new cases is vital to make informed decisions and in evaluating the measures that should be implemented. Studies on COVID-19 prediction are limited in Africa despite the risks and dangers that the virus possessed. Hence, this study was performed to predict daily COVID-19 cases in 10 African countries spread across the north, south, east, west and central Africa considering countries with few and large number of daily COVID-19 cases. Machine learning (ML) models due to their nonlinearity and accurate prediction capabilities were employed for this purpose, including artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), support vector machine (SVM) and conventional multiple linear regression (MLR) models. As any other natural process, the COVID-19 pandemic may contain both linear and nonlinear aspects. In such circumstances, neither nonlinear (ML) nor linear (MLR) models could be sufficient; hence, combining both ML and MLR models may produce better accuracy. Consequently, to improve the prediction efficiency of the ML models, novel ensemble approaches including ANN-E and SVM-E were employed. The advantage of using ensemble approaches is that they provide collective benefits of all the standalone models, thereby reducing their weaknesses and enhancing their prediction capabilities. The obtained results showed that ANFIS led to better prediction performance with MAD = 0.0106, MSE = 0.0003, RMSE = 0.0185 and R2 = 0.9059 in the validation step. The results of the proposed ensemble approaches demonstrated very high improvements in predicting the COVID-19 pandemic in Africa with MAD = 0.0073, MSE = 0.0002, RMSE = 0.0155 and R2 = 0.9616. The ANN-E improved the standalone models performance in the validation step up to 10%, 14%, 42%, 6%, 83%, 11%, 7%, 5%, 7% and 31% for Morocco, Sudan, Namibia, South Africa, Uganda, Rwanda, Nigeria, Senegal, Gabon and Cameroon, respectively. This study results offer a solid foundation in the application of ensemble approaches for predicting COVID-19 pandemic across all regions and countries in the world.
Collapse
Affiliation(s)
- Zurki Ibrahim
- Department of Medical Genetics, Near East University, Mersin 10, Lefkosa, Turkey
| | - Pinar Tulay
- Department of Medical Genetics, Near East University, Mersin 10, Lefkosa, Turkey
| | - Jazuli Abdullahi
- Department of Civil Engineering, Faculty of Engineering, Baze University, Abuja, Nigeria.
| |
Collapse
|
10
|
Doheny EP, Flood M, Ryan S, McCarthy C, O'Carroll O, O'Seaghdha C, Mallon PW, Feeney ER, Keatings VM, Wilson M, Kennedy N, Gannon A, Edwards C, Lowery MM. Prediction of low pulse oxygen saturation in COVID-19 using remote monitoring post hospital discharge. Int J Med Inform 2023; 169:104911. [PMID: 36347139 PMCID: PMC9625852 DOI: 10.1016/j.ijmedinf.2022.104911] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2022] [Revised: 10/21/2022] [Accepted: 10/27/2022] [Indexed: 11/05/2022]
Abstract
BACKGROUND Monitoring systems have been developed during the COVID-19 pandemic enabling clinicians to remotely monitor physiological measures including pulse oxygen saturation (SpO2), heart rate (HR), and breathlessness in patients after discharge from hospital. These data may be leveraged to understand how symptoms vary over time in COVID-19 patients. There is also potential to use remote monitoring systems to predict clinical deterioration allowing early identification of patients in need of intervention. METHODS A remote monitoring system was used to monitor 209 patients diagnosed with COVID-19 in the period following hospital discharge. This system consisted of a patient-facing app paired with a Bluetooth-enabled pulse oximeter (measuring SpO2 and HR) linked to a secure portal where data were available for clinical review. Breathlessness score was entered manually to the app. Clinical teams were alerted automatically when SpO2 < 94 %. In this study, data recorded during the initial ten days of monitoring were retrospectively examined, and a random forest model was developed to predict SpO2 < 94 % on a given day using SpO2 and HR data from the two previous days and day of discharge. RESULTS Over the 10-day monitoring period, mean SpO2 and HR increased significantly, while breathlessness decreased. The coefficient of variation in SpO2, HR and breathlessness also decreased over the monitoring period. The model predicted SpO2 alerts (SpO2 < 94 %) with a mean cross-validated. sensitivity of 66 ± 18.57 %, specificity of 88.31 ± 10.97 % and area under the receiver operating characteristic of 0.80 ± 0.11. Patient age and sex were not significantly associated with the occurrence of asymptomatic SpO2 alerts. CONCLUSION Results indicate that SpO2 alerts (SpO2 < 94 %) on a given day can be predicted using SpO2 and heart rate data captured on the two preceding days via remote monitoring. The methods presented may help early identification of patients with COVID-19 at risk of clinical deterioration using remote monitoring.
Collapse
Affiliation(s)
- Emer P. Doheny
- School of Electrical and Electronic Engineering, University College Dublin, Dublin, Ireland,Insight Centre for Data Analytics, University College Dublin, Dublin, Ireland,Corresponding author
| | - Matthew Flood
- School of Electrical and Electronic Engineering, University College Dublin, Dublin, Ireland
| | - Silke Ryan
- School of Medicine, University College Dublin, Dublin, Ireland,St. Vincent’s University Hospital, Dublin, Ireland
| | - Cormac McCarthy
- School of Medicine, University College Dublin, Dublin, Ireland,St. Vincent’s University Hospital, Dublin, Ireland
| | | | | | | | - Eoin R. Feeney
- School of Medicine, University College Dublin, Dublin, Ireland
| | | | | | | | - Avril Gannon
- Midland Regional Hospital at Tullamore, Tullamore, Ireland
| | | | - Madeleine M. Lowery
- School of Electrical and Electronic Engineering, University College Dublin, Dublin, Ireland,Insight Centre for Data Analytics, University College Dublin, Dublin, Ireland
| |
Collapse
|
11
|
Developing and validating a machine learning prognostic model for alerting to imminent deterioration of hospitalized patients with COVID-19. Sci Rep 2022; 12:19220. [PMID: 36357439 PMCID: PMC9648491 DOI: 10.1038/s41598-022-23553-7] [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: 05/26/2022] [Accepted: 11/02/2022] [Indexed: 11/12/2022] Open
Abstract
Our study was aimed at developing and validating a new approach, embodied in a machine learning-based model, for sequentially monitoring hospitalized COVID-19 patients and directing professional attention to patients whose deterioration is imminent. Model development employed real-world patient data (598 prediction events for 210 patients), internal validation (315 prediction events for 97 patients), and external validation (1373 prediction events for 307 patients). Results show significant divergence in longitudinal values of eight routinely collected blood parameters appearing several days before deterioration. Our model uses these signals to predict the personal likelihood of transition from non-severe to severe status within well-specified short time windows. Internal validation of the model's prediction accuracy showed ROC AUC of 0.8 and 0.79 for prediction scopes of 48 or 96 h, respectively; external validation showed ROC AUC of 0.7 and 0.73 for the same prediction scopes. Results indicate the feasibility of predicting the forthcoming deterioration of non-severe COVID-19 patients by eight routinely collected blood parameters, including neutrophil, lymphocyte, monocyte, and platelets counts, neutrophil-to-lymphocyte ratio, CRP, LDH, and D-dimer. A prospective clinical study and an impact assessment will allow implementation of this model in the clinic to improve care, streamline resources and ease hospital burden by timely focusing the medical attention on potentially deteriorating patients.
Collapse
|
12
|
Severe COVID-19 is characterised by inflammation and immature myeloid cells early in disease progression. Heliyon 2022; 8:e09230. [PMID: 35386227 PMCID: PMC8973020 DOI: 10.1016/j.heliyon.2022.e09230] [Citation(s) in RCA: 14] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2020] [Revised: 04/20/2021] [Accepted: 03/28/2022] [Indexed: 12/21/2022] Open
Abstract
SARS-CoV-2 infection causes a wide spectrum of disease severity. Identifying the immunological characteristics of severe disease and the risk factors for their development are important in the management of COVID-19. This study aimed to identify and rank clinical and immunological features associated with progression to severe COVID-19 in order to investigate an immunological signature of severe disease. One hundred and eight patients with positive SARS-CoV-2 PCR were recruited. Routine clinical and laboratory markers were measured, as well as myeloid and lymphoid whole-blood immunophenotyping and measurement of the pro-inflammatory cytokines IL-6 and soluble CD25. All analysis was carried out in a routine hospital diagnostic laboratory. Univariate analysis demonstrated that severe disease was most strongly associated with elevated CRP and IL-6, loss of DLA-DR expression on monocytes and CD10 expression on neutrophils. Unbiased machine learning demonstrated that these four features were strongly associated with severe disease, with an average prediction score for severe disease of 0.925. These results demonstrate that these four markers could be used to identify patients developing severe COVID-19 and allow timely delivery of therapeutics. Severe COVID-19 is characterised by a combination of emergency myelopoiesis and inflammation. These changes can be rapidly identified in a diagnostic laboratory, facilitating intervention. This disease signature was derived from a cohort of patients with a wide range of ages, frailty and COVID-19 severity.
Collapse
|
13
|
Rauseo M, Perrini M, Gallo C, Mirabella L, Mariano K, Ferrara G, Santoro F, Tullo L, La Bella D, Vetuschi P, Cinnella G. Machine learning and predictive models: 2 years of Sars-CoV-2 pandemic in a single-center retrospective analysis. JOURNAL OF ANESTHESIA, ANALGESIA AND CRITICAL CARE 2022; 2:42. [PMCID: PMC9568961 DOI: 10.1186/s44158-022-00071-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 01/08/2023]
Abstract
Background Methods Results Conclusion
Collapse
Affiliation(s)
- Michela Rauseo
- grid.10796.390000000121049995Department of Anesthesia and Intensive Care Medicine, University Hospital “Policlinico Riuniti di Foggia”, University of Foggia, Viale Pinto, 1, 71122 Foggia, Italy
| | - Marco Perrini
- grid.10796.390000000121049995Department of Anesthesia and Intensive Care Medicine, University Hospital “Policlinico Riuniti di Foggia”, University of Foggia, Viale Pinto, 1, 71122 Foggia, Italy
| | - Crescenzio Gallo
- Department of Clinical and Experimental Medicine “InfoLab” Bioinformatics Facility Head, University Hospital “Policlinico Riuniti”, Viale Pinto 1, 71122 Foggia, Italy
| | - Lucia Mirabella
- grid.10796.390000000121049995Department of Anesthesia and Intensive Care Medicine, University Hospital “Policlinico Riuniti di Foggia”, University of Foggia, Viale Pinto, 1, 71122 Foggia, Italy
| | - Karim Mariano
- grid.10796.390000000121049995Department of Anesthesia and Intensive Care Medicine, University Hospital “Policlinico Riuniti di Foggia”, University of Foggia, Viale Pinto, 1, 71122 Foggia, Italy
| | - Giuseppe Ferrara
- grid.10796.390000000121049995Department of Anesthesia and Intensive Care Medicine, University Hospital “Policlinico Riuniti di Foggia”, University of Foggia, Viale Pinto, 1, 71122 Foggia, Italy
| | - Filomena Santoro
- grid.10796.390000000121049995Department of Anesthesia and Intensive Care Medicine, University Hospital “Policlinico Riuniti di Foggia”, University of Foggia, Viale Pinto, 1, 71122 Foggia, Italy
| | - Livio Tullo
- grid.10796.390000000121049995Department of Anesthesia and Intensive Care Medicine, University Hospital “Policlinico Riuniti di Foggia”, University of Foggia, Viale Pinto, 1, 71122 Foggia, Italy
| | - Daniela La Bella
- grid.10796.390000000121049995Department of Anesthesia and Intensive Care Medicine, University Hospital “Policlinico Riuniti di Foggia”, University of Foggia, Viale Pinto, 1, 71122 Foggia, Italy
| | - Paolo Vetuschi
- grid.10796.390000000121049995Department of Anesthesia and Intensive Care Medicine, University Hospital “Policlinico Riuniti di Foggia”, University of Foggia, Viale Pinto, 1, 71122 Foggia, Italy
| | - Gilda Cinnella
- grid.10796.390000000121049995Department of Anesthesia and Intensive Care Medicine, University Hospital “Policlinico Riuniti di Foggia”, University of Foggia, Viale Pinto, 1, 71122 Foggia, Italy
| |
Collapse
|