Prediction of COVID-19 Hospitalization and Mortality Using Artificial Intelligence
Abstract
:1. Introduction
2. Literature Review
3. Materials and Methods
- Data preprocessing:
- a.
- Data cleaning and transformation: The data were cleaned through the handling of missing values. Missing values in the dataset were handled by using a boxplot. Records lacking essential data points were excluded from the analysis to maintain the models’ integrity. The categorical variables were coded according to categorical variables, and the quantitative variables’ missing values were replaced by their mean. The outcome variable (hospital mortality) was properly labeled as death = 0 or survival = 1. All the baseline investigations, clinical symptoms, and laboratory findings were labeled as predictors.
- b.
- Dataset splitting: The data were divided into training and testing sets, with the training set used for model development and the testing set reserved for performance evaluation. To optimize the models’ hyperparameters and enhance generalizability, a 5-fold cross-validation technique was applied. This approach helps minimize variance and bias in the models’ performance.
- Machine learning algorithms:
- Hyperparameters:
- a.
- Decision trees: The model’s hyperparameters include a maximum depth of 10 and a minimum sample split of 2. The criterion used for measuring the quality of splits is Gini impurity.
- b.
- Support vector machines (SVMs): The model used a radial basis function (RBF) kernel, which is effective in high-dimensional spaces. The regularization parameter was set to 1.0, balancing the trade-off between maximizing the margin and minimizing classification errors. The kernel coefficient
\( \gamma\) was set to ‘scale’. This helps in capturing the non-linear relationships in the data. The tolerance for stopping criteria was set to 0.001. A 5-fold cross-validation was performed to ensure robustness and prevent overfitting. - c.
- Random forest: The model used 100 trees, balancing computational efficiency and model performance. The maximum depth of each tree was set to none, allowing trees to grow until all leaves were pure or until all leaves contained less than the minimum samples required to split. The minimum number of samples required to split an internal node was set to 2. The model used the Gini impurity criterion to measure the quality of a split. Bootstrap samples were used when building trees to reduce overfitting. A 5-fold cross-validation was performed to tune the hyperparameters and validate the model’s performance.
- Training process:
- Technical characteristics of computer used:
- Block diagram:
4. Results
4.1. Demographics and Baselines of COVID-19 Patients
4.2. Laboratory Parameters in COVID-19 Patients
4.3. Prediction of Mortality
4.4. Hypothetical Confusion Matrix for SVM
5. Discussion
6. Conclusions
7. Limitations of the Study
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Domingo, E.J. Introduction to virus origins and their role in biological evolution. In Virus as Populations; Academic Press: Cambridge, MA, USA, 2020; pp. 1–33. [Google Scholar]
- Kang, S.; Peng, W.; Zhu, Y.; Lu, S.; Zhou, M.; Lin, W.; Wu, W.; Huang, S.; Jiang, L.; Luo, X.; et al. Recent progress in understanding 2019 novel coronavirus (SARS-CoV-2) associated with human respiratory disease: Detection, mechanisms and treatment. Int. J. Antimicrob. Agents 2020, 55, 105950. [Google Scholar] [CrossRef] [PubMed]
- Mohapatra, R.K.; Pintilie, L.; Kandi, V.; Sarangi, A.K.; Das, D.; Sahu, R.; Perekhoda, L. The recent challenges of highly contagious COVID-19, causing respiratory infections: Symptoms, diagnosis, transmission, possible vaccines, animal models, and immunotherapy. Chem. Biol. Drug Des. 2020, 96, 1187–1208. [Google Scholar] [CrossRef] [PubMed]
- Mohan, B.; Nambiar, V.J. COVID-19: An insight into the SARS-CoV-2 pandemic originated at Wuhan City in Hubei Province of China. J. Infect. Dis. Epidemiol. 2020, 6, 146. [Google Scholar] [CrossRef]
- Zhang, J.-j.; Dong, X.; Liu, G.-H.; Gao, Y.-D. Risk and protective factors for COVID-19 morbidity, severity, and mortality. Clin. Rev. Allergy Immunol. 2023, 64, 90–107. [Google Scholar] [CrossRef]
- Ragnoli, B.; Da Re, B.; Galantino, A.; Kette, S.; Salotti, A.; Malerba, M. Interrelationship between COVID-19 and coagulopathy: Pathophysiological and clinical evidence. Int. J. Mol. Sci. 2023, 24, 8945. [Google Scholar] [CrossRef] [PubMed]
- Wilder-Smith, A.; Osman, S. Public health emergencies of international concern: A historic overview. J. Travel Med. 2020, 27, taaa227. [Google Scholar] [CrossRef] [PubMed]
- Zanke, A.A.; Thenge, R.R.; Adhao, V.S. COVID-19: A pandemic declared by the World Health Organization. IP Int. J. Compr. Adv. Pharmacol. 2020, 5, 49–57. [Google Scholar] [CrossRef]
- Sohrabi, C.; Alsafi, Z.; O’neill, N.; Khan, M.; Kerwan, A.; Al-Jabir, A.; Iosifidis, C.; Agha, R. World Health Organization declares global emergency: A review of the 2019 novel coronavirus (COVID-19). Int. J. Surg. 2020, 76, 71–76. [Google Scholar] [CrossRef]
- Yang, Y.; Peng, F.; Wang, R.; Guan, K.; Jiang, T.; Xu, G.; Sun, J.; Chang, C. The deadly coronaviruses: The 2003 SARS pandemic and the 2020 novel coronavirus epidemic in China. J. Autoimmun. 2020, 109, 102434. [Google Scholar] [CrossRef]
- Adil, M.T.; Rahman, R.; Whitelaw, D.; Jain, V.; Al-Taan, O.; Rashid, F.; Munasinghe, A.; Jambulingam, P. SARS-CoV-2 and the pandemic of COVID-19. Postgrad. Med. J. 2021, 97, 110–116. [Google Scholar] [CrossRef]
- Mallah, S.I.; Ghorab, O.K.; Al-Salmi, S.; Abdellatif, O.S.; Tharmaratnam, T.; Iskandar, M.A.; Sefen, J.A.N.; Sidhu, P.; Atallah, B.; El-Lababidi, R.; et al. COVID-19: Breaking down a global health crisis. Ann. Clin. Microbiol. Antimicrob. 2021, 20, 35. [Google Scholar] [CrossRef]
- Lan, L.; Xu, D.; Ye, G.; Xia, C.; Wang, S.; Li, Y.; Xu, H. Positive RT-PCR test results in patients recovered from COVID-19. JAMA 2020, 323, 1502–1503. [Google Scholar] [CrossRef]
- Fields, B.K.; Demirjian, N.L.; Gholamrezanezhad, A. Coronavirus Disease 2019 (COVID-19) diagnostic technologies: A country-based retrospective analysis of screening and containment procedures during the first wave of the pandemic. Clin. Imaging 2020, 67, 219–225. [Google Scholar] [CrossRef] [PubMed]
- Piccialli, F.; Di Cola, V.S.; Giampaolo, F.; Cuomo, S. The role of artificial intelligence in fighting the COVID-19 pandemic. Inf. Syst. Front. 2021, 23, 1467–1497. [Google Scholar] [CrossRef] [PubMed]
- Aruleba, R.T.; Adekiya, T.A.; Ayawei, N.; Obaido, G.; Aruleba, K.; Mienye, I.D.; Aruleba, I.; Ogbuokiri, B. COVID-19 Diagnosis: A Review of Rapid Antigen, RT-PCR and Artificial Intelligence Methods. Bioengineering 2022, 9, 153. [Google Scholar] [CrossRef] [PubMed]
- Majumder, D.D. A unified approach to artificial intelligence, pattern recognition, image processing and computer vision in fifth-generation computer systems. Inf. Sci. 1988, 45, 391–431. [Google Scholar] [CrossRef]
- Tsephe, R.; Makoele, L. Rethinking Pedagogy in the 4IR and Innovation-Driven Economy: Challenges and Opportunities. In Proceedings of the 18th International Technology, Education and Development Conference, Valencia, Spain, 4–6 March 2024; pp. 5042–5049. [Google Scholar]
- Elshawi, R.; Maher, M.; Sakr, S. Automated machine learning: State-of-the-art and open challenges. arXiv 2019, arXiv:1906.02287. [Google Scholar] [CrossRef]
- Gudigar, A.; Raghavendra, U.; Nayak, S.; Ooi, C.P.; Chan, W.Y.; Gangavarapu, M.R.; Dharmik, C.; Samanth, J.; Kadri, N.A.; Hasikin, K.; et al. Role of artificial intelligence in COVID-19 detection. Sensors 2021, 21, 8045. [Google Scholar] [CrossRef]
- Yang, Y.; Lure, F.Y.; Miao, H.; Zhang, Z.; Jaeger, S.; Liu, J.; Guo, L. Using artificial intelligence to assist radiologists in distinguishing COVID-19 from other pulmonary infections. J. X-ray Sci. Technol. 2021, 29, 1–17. [Google Scholar] [CrossRef]
- Sharma, S.; Gupta, Y.K. Predictive analysis and survey of COVID-19 using machine learning and big data. J. Interdiscip. Math. 2021, 24, 175–195. [Google Scholar] [CrossRef]
- Guan, X.; Zhang, B.; Fu, M.; Li, M.; Yuan, X.; Zhu, Y.; Peng, J.; Guo, H.; Lu, Y. Clinical and inflammatory features based machine learning model for fatal risk prediction of hospitalized COVID-19 patients: Results from a retrospective cohort study. Ann. Med. 2021, 53, 257–266. [Google Scholar] [CrossRef]
- Yan, L.; Zhang, H.-T.; Goncalves, J.; Xiao, Y.; Wang, M.; Guo, Y.; Sun, C.; Tang, X.; Jing, L.; Zhang, M.; et al. An interpretable mortality prediction model for COVID-19 patients. Nat. Mach. Intell. 2020, 2, 283–288. [Google Scholar] [CrossRef]
- Maghded, H.S.; Ghafoor, K.Z.; Sadiq, A.S.; Curran, K.; Rawat, D.B.; Rabie, K. A novel AI-enabled framework to diagnose coronavirus COVID-19 using smartphone embedded sensors: Design study. In Proceedings of the 2020 IEEE 21st International Conference on Information Reuse and Integration for Data Science (IRI), Las Vegas, NV, USA, 11–13 August 2020. [Google Scholar]
- Serte, S.; Dirik, M.A.; Al-Turjman, F. Deep learning models for COVID-19 detection. Sustainability 2022, 14, 5820. [Google Scholar] [CrossRef]
- Wynants, L.; Van Calster, B.; Collins, G.S.; Riley, R.D.; Heinze, G.; Schuit, E.; Bonten, M.M.J.; Dahly, D.L.; Damen, J.A.; Debray, T.P.A.; et al. Prediction models for diagnosis and prognosis of COVID-19: Systematic review and critical appraisal. BMJ 2020, 369, m1328. [Google Scholar] [CrossRef]
- Yaşar, Ş.; Çolak, C.; Yoloğlu, S. Artificial intelligence-based prediction of COVID-19 severity on the results of protein profiling. Comput. Methods Programs Biomed. 2021, 202, 105996. [Google Scholar] [CrossRef]
- Zhang, Z.; Navarese, E.P.; Zheng, B.; Meng, Q.; Liu, N.; Ge, H.; Pan, Q.; Yu, Y.; Ma, X. Analytics with artificial intelligence to advance the treatment of acute respiratory distress syndrome. J. Evid.-Based Med. 2020, 13, 301–312. [Google Scholar] [CrossRef] [PubMed]
- Suri, J.S.; Agarwal, S.; Gupta, S.K.; Puvvula, A.; Biswas, M.; Saba, L.; Bit, A.; Tandel, G.S.; Agarwal, M.; Patrick, A.; et al. A narrative review on characterization of acute respiratory distress syndrome in COVID-19-infected lungs using artificial intelligence. Comput. Biol. Med. 2021, 130, 104210. [Google Scholar] [CrossRef] [PubMed]
- Zhang, J.; Jun, T.; Frank, J.; Nirenberg, S.; Kovatch, P.; Huang, K.-L. Prediction of individual COVID-19 diagnosis using baseline demographics and lab data. Sci. Rep. 2021, 11, 13913. [Google Scholar] [CrossRef]
- Badiola-Zabala, G.; Lopez-Guede, J.M.; Estevez, J.; Graña, M. Machine learning first response to COVID-19: A systematic literature review of clinical decision assistance approaches during pandemic years from 2020 to 2022. Electronics 2024, 13, 1005. [Google Scholar] [CrossRef]
- Bilinski, A.; Emanuel, E.J. COVID-19 and excess all-cause mortality in the US and 18 comparison countries. JAMA 2020, 324, 2100–2102. [Google Scholar] [CrossRef]
- Sjoding, M.W.; Taylor, D.; Motyka, J.; Lee, E.; Co, I.; Claar, D.; McSparron, J.I.; Ansari, S.; Kerlin, M.P.; Reilly, J.P.; et al. Deep learning to detect acute respiratory distress syndrome on chest radiographs: A retrospective study with external validation. Lancet Digit. Health 2021, 3, e340–e348. [Google Scholar] [CrossRef]
- Kassirian, S.; Taneja, R.; Mehta, S. Diagnosis and management of acute respiratory distress syndrome in a time of COVID-19. Diagnostics 2020, 10, 1053. [Google Scholar] [CrossRef] [PubMed]
- Aktar, S.; Talukder, A.; Ahamad, M.; Kamal, A.H.M.; Khan, J.R.; Protikuzzaman, M.; Hossain, N.; Azad, A.K.M.; Quinn, J.M.W.; Summers, M.A.; et al. Machine learning approaches to identify patient comorbidities and symptoms that increase the risk of mortality in COVID-19. Diagnostics 2021, 11, 1383. [Google Scholar] [CrossRef] [PubMed]
- Tayarani, M. Applications of artificial intelligence in battling against COVID-19: A literature review. Chaos Solitons Fractals 2020, 142, 110338. [Google Scholar] [CrossRef]
- Bai X, Fang C, Zhou Y, Bai S, Liu Z, Chen Q, Xu Y, Xia T, Gong S, Xie X, Song D. Predicting COVID-19 malignant progression with AI techniques. MedRxiv. [CrossRef]
- Chen, J.H.; Asch, S.M. Machine learning and prediction in medicine—Beyond the peak of inflated expectations. N. Engl. J. Med. 2017, 376, 2507. [Google Scholar] [CrossRef]
- Wang, A.; Li, F.; Chiang, S.; Fulcher, J.; Yang, O.; Wong, D.; Wei, F. Machine learning prediction of COVID-19 severity levels from salivaomics data. arXiv 2022, arXiv:2207.07274v1. [Google Scholar]
- Feng, C.; Kephart, G.; Juarez-Colunga, E. Predicting COVID-19 mortality risk in Toronto, Canada: A comparison of tree-based and regression-based machine learning methods. BMC Med. Res. Methodol. 2021, 21, 267. [Google Scholar] [CrossRef]
- Shakibfar, S.; Nyberg, F.; Li, H.; Zhao, J.; Nordeng, H.M.E.; Sandve, G.K.F.; Pavlovic, M.; Hajiebrahimi, M.; Andersen, M.; Sessa, M. Artificial intelligence-driven prediction of COVID-19-related hospitalization and death: A systematic review. Front. Public Health 2023, 11, 1183725. [Google Scholar] [CrossRef] [PubMed]
- Lv, C.; Guo, W.; Yin, X.; Liu, L.; Huang, X.; Li, S.; Zhang, L. Innovative applications of artificial intelligence during the COVID-19 pandemic. Infect. Med. 2024, 3, 100095. [Google Scholar] [CrossRef]
- Carreras, J. Artificial intelligence analysis of celiac disease using an autoimmune discovery transcriptomic panel highlighted pathogenic genes including BTLA. Healthcare 2022, 10, 1550. [Google Scholar] [CrossRef]
Variables | ||
Age (Mean ± SD) | 50.9 ± 15.09 | |
Hospital Stay (Days) | 14.6 ± 2.8 | |
Frequency | Percentages (%) | |
Gender | ||
Male | 28 | 56.0 |
Female | 22 | 44.0 |
Disease Severity | ||
Mild | 17 | 34.0 |
Moderate | 23 | 46.0 |
Severe | 7 | 14.0 |
Critical | 3 | 6.0 |
Sign and Symptoms | ||
Fever | 24 | 48.0 |
Cough | 18 | 36.0 |
Sore throat | 12 | 24.0 |
Diarrhea | 12 | 24.0 |
Fatigue | 19 | 38.0 |
Nausea | 8 | 16.0 |
Abdominal pain | 5 | 10.0 |
Outcome | ||
Death | 6 | 12.0 |
Survived | 44 | 88.0 |
Laboratory Parameters | Normal Range | Mean ± SD | Minimum | Maximum | Range |
---|---|---|---|---|---|
White blood cell × 109/L | 3.5–9.5 | 11.91 ± 12.9 | 0.741 | 76.6 | 75.85 |
Platelets × 109/L | 125–350 | 220.0 ± 80.5 | 40.0 | 418.0 | 378.0 |
CRP (mg/L) | <3 | 60.18 ± 83.01 | 0.10 | 322.13 | 322.03 |
LDH (U/L) | 140 to 280 | 296.98 ± 163.01 | 155.0 | 1044.0 | 889.0 |
Ferritin (ng/mL) | 12 to 300 | 479.89 ± 436.07 | 8.0 | 1675 | 1667 |
D-Dimers (mg/L) | >0.5 | 438.59 ± 443.0 | 0.2 | 1600.0 | 1599.8 |
Alkaline phosphatase (ALP), (U/L) | 44–147 | 85.12 ± 23.64 | 40.0 | 135.00 | 95.0 |
Gamma-glutamyl transferase (GGT), (U/L) | 0–30 | 40.12 ± 16.54 | 10.0 | 79.0 | 69.0 |
Alanine transaminase (ALT), (U/L) | 7–50 | 33.28 ± 11.12 | 17.0 | 60.0 | 43.0 |
Aspartate aminotransferase (AST), (U/L) | 15–40 | 38.64 ± 13.93 | 18.0 | 75.0 | 57.0 |
Bilirubin (mg/dL) | <0.3 | 0.63 ± 0.32 | 0.2 | 1.4 | 1.2 |
Prothrombin time/sec | 10–13/sec | 11.6 ± 1.47 | 8.0 | 14.0 | 6.0 |
Calcium (mg/dL) | 8.5 to 10.2 | 8.8 ± 0.33 | 8.0 | 9.6 | 1.6 |
Potassium (mEq/L) | 3.5–5 | 4.05 ± 0.80 | 2.9 | 8.8 | 5.9 |
Laboratory Findings | Outcome | Mean ± SD | p-Value |
---|---|---|---|
WCC | Survival | 10.81 ± 9.34 | 0.104 |
Death | 19.99 ± 28.37 | ||
PLT | Survival | 222.25 ± 72.39 | 0.605 |
Death | 203.83 ± 134.95 | ||
CRP | Survival | 51.17 ± 69.86 | ≤0.05 * |
Death | 124.80 ± 139.48 | ||
LDH | Survival | 271.52 ± 102.10 | ≤0.001 ** |
Death | 483.67 ± 351.06 | ||
Ferritin | Survival | 439.42 ± 365.26 | ≤0.05 * |
Death | 835.98 ± 819.24 | ||
D-Dimers | Survival | 332.47395 ± 345.07 | ≤0.001 ** |
Death | 1216.8 ± 271.52 | ||
ALP | Survival | 81.73 ± 22.25 | ≤0.001 ** |
Death | 110.00 ± 19.48 | ||
GGT | Survival | 38.80 ± 16.88 | 0.127 |
Death | 49.83 ± 10.21 | ||
ALT | Survival | 32.68 ± 11.53 | 0.308 |
Death | 37.67 ± 6.53 | ||
AST | Survival | 37.70 ± 14.41 | 0.202 |
Death | 45.50 ± 7.31 | ||
Bilirubin | Survival | 0.60 ± 0.30 | ≤0.05 * |
Death | 0.88 ± 0.39 | ||
Prothrombin time | Survival | 11.64 ± 1.40 | 0.641 |
Death | 11.33 ± 2.07 | ||
Calcium | Survival | 8.81 ± 0.35 | 0.595 |
Death | 8.73 ± 0.23 | ||
Potassium | Survival | 4.07 ± 0.83 | 0.665 |
Death | 3.92 ± 0.62 | ||
Hospital stay | Survival | 14.57 ± 2.96 | ≤0.001 ** |
Death | 23.00 ± 2.83 |
Algorithms | Accuracy (%) |
---|---|
Decision tree | 76% |
Random forest | 80% |
SVM | 82% |
Actual Findings | Results from SVM | |
---|---|---|
Positive (Survived) | Negative (Died) | |
Positive (survived) | 41 | 9 |
Negative (died) | 8 | 42 |
Sensitivity | 83.67% | |
Specificity | 82.35% | |
Positive predicted value (PP V) | 82.0% | |
Negative predictive value (NPV) | 84.0% | |
Accuracy | 83.0% |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Halwani, M.A.; Halwani, M.A. Prediction of COVID-19 Hospitalization and Mortality Using Artificial Intelligence. Healthcare 2024, 12, 1694. https://doi.org/10.3390/healthcare12171694
Halwani MA, Halwani MA. Prediction of COVID-19 Hospitalization and Mortality Using Artificial Intelligence. Healthcare. 2024; 12(17):1694. https://doi.org/10.3390/healthcare12171694
Chicago/Turabian StyleHalwani, Marwah Ahmed, and Manal Ahmed Halwani. 2024. "Prediction of COVID-19 Hospitalization and Mortality Using Artificial Intelligence" Healthcare 12, no. 17: 1694. https://doi.org/10.3390/healthcare12171694