Application of a Decision Tree Model to Predict the Outcome of Non-Intensive Inpatients Hospitalized for COVID-19
Abstract
:1. Introduction
2. Materials and Methods
2.1. Participants and Procedures
2.2. Statistical Analysis
2.3. Software
3. Results
4. Discussion
5. Study Limitation
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Lu, R.; Zhao, X.; Li, J.; Niu, P.; Yang, B.; Wu, H.; Wang, W.; Song, H.; Huang, B.; Zhu, N.; et al. Genomic Characterisation and Epidemiology of 2019 Novel Coronavirus: Implications for Virus Origins and Receptor Binding. Lancet 2020, 395, 565–574. [Google Scholar] [CrossRef] [Green Version]
- A Novel Coronavirus Genome Identified in a Cluster of Pneumonia Cases—Wuhan, China 2019−2020. Available online: https://weekly.chinacdc.cn/en/article/id/a3907201-f64f-4154-a19e-4253b453d10c (accessed on 7 March 2022).
- Iser, B.P.M.; Sliva, I.; Raymundo, V.T.; Poleto, M.B.; Schuelter-Trevisol, F.; Bobinski, F. Suspected COVID-19 Case Definition: A Narrative Review of the Most Frequent Signs and Symptoms among Confirmed Cases. Epidemiol. Serv. Saúde 2020, 29. [Google Scholar] [CrossRef]
- Ejaz, H.; Alsrhani, A.; Zafar, A.; Javed, H.; Junaid, K.; Abdalla, A.E.; Abosalif, K.O.A.; Ahmed, Z.; Younas, S. COVID-19 and Comorbidities: Deleterious Impact on Infected Patients. J. Infect. Public Health 2020, 13, 1833–1839. [Google Scholar] [CrossRef]
- Alizadehsani, R.; Alizadeh Sani, Z.; Behjati, M.; Roshanzamir, Z.; Hussain, S.; Abedini, N.; Hasanzadeh, F.; Khosravi, A.; Shoeibi, A.; Roshanzamir, M.; et al. Risk Factors Prediction, Clinical Outcomes, and Mortality in COVID-19 Patients. J. Med. Virol. 2021, 93, 2307–2320. [Google Scholar] [CrossRef] [PubMed]
- Huang, C.; Wang, Y.; Li, X.; Ren, L.; Zhao, J.; Hu, Y.; Zhang, L.; Fan, G.; Xu, J.; Gu, X.; et al. Clinical Features of Patients Infected with 2019 Novel Coronavirus in Wuhan, China. Lancet 2020, 395, 497–506. [Google Scholar] [CrossRef] [Green Version]
- Odone, A.; Delmonte, D.; Scognamiglio, T.; Signorelli, C. COVID-19 Deaths in Lombardy, Italy: Data in Context. Lancet Public Health 2020, 5, e310. [Google Scholar] [CrossRef]
- Yang, X.; Yu, Y.; Xu, J.; Shu, H.; Xia, J.; Liu, H.; Wu, Y.; Zhang, L.; Yu, Z.; Fang, M.; et al. Clinical Course and Outcomes of Critically Ill Patients with SARS-CoV-2 Pneumonia in Wuhan, China: A Single-Centered, Retrospective, Observational Study. Lancet Respir. Med. 2020, 8, 475–481. [Google Scholar] [CrossRef] [Green Version]
- Bartolomeo, N.; Giotta, M.; Trerotoli, P. In-Hospital Mortality in Non-COVID-19-Related Diseases before and during the Pandemic: A Regional Retrospective Study. Int. J. Environ. Res. Public Health 2021, 18, 10886. [Google Scholar] [CrossRef]
- Yadaw, A.S.; Li, Y.-C.; Bose, S.; Iyengar, R.; Bunyavanich, S.; Pandey, G. Clinical Features of COVID-19 Mortality: Development and Validation of a Clinical Prediction Model. Lancet Digit Health 2020, 2, e516–e525. [Google Scholar] [CrossRef]
- Tjendra, Y.; Al Mana, A.F.; Espejo, A.P.; Akgun, Y.; Millan, N.C.; Gomez-Fernandez, C.; Cray, C. Predicting Disease Severity and Outcome in COVID-19 Patients: A Review of Multiple Biomarkers. Arch. Pathol. Lab. Med. 2020, 144, 1465–1474. [Google Scholar] [CrossRef]
- Chen, G.; Wu, D.; Guo, W.; Cao, Y.; Huang, D.; Wang, H.; Wang, T.; Zhang, X.; Chen, H.; Yu, H.; et al. Clinical and Immunological Features of Severe and Moderate Coronavirus Disease 2019. J. Clin. Investig. 2020, 130, 2620–2629. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Chen, N.; Zhou, M.; Dong, X.; Qu, J.; Gong, F.; Han, Y.; Qiu, Y.; Wang, J.; Liu, Y.; Wei, Y.; et al. Epidemiological and Clinical Characteristics of 99 Cases of 2019 Novel Coronavirus Pneumonia in Wuhan, China: A Descriptive Study. Lancet 2020, 395, 507–513. [Google Scholar] [CrossRef] [Green Version]
- Henry, B.M.; de Oliveira, M.H.S.; Benoit, S.; Plebani, M.; Lippi, G. Hematologic, Biochemical and Immune Biomarker Abnormalities Associated with Severe Illness and Mortality in Coronavirus Disease 2019 (COVID-19): A Meta-Analysis. Clin. Chem. Lab. Med. 2020, 58, 1021–1028. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Liang, W.; Liang, H.; Ou, L.; Chen, B.; Chen, A.; Li, C.; Li, Y.; Guan, W.; Sang, L.; Lu, J.; et al. Development and Validation of a Clinical Risk Score to Predict the Occurrence of Critical Illness in Hospitalized Patients With COVID-19. JAMA Intern. Med. 2020, 180, 1081–1089. [Google Scholar] [CrossRef]
- Ertekin, B.; Yortanlı, M.; Özelbaykal, O.; Doğru, A.; Girişgin, A.S.; Acar, T. The Relationship between Routine Blood Parameters and the Prognosis of COVID-19 Patients in the Emergency Department. Emerg. Med. Int. 2021, 2021, 7489675. [Google Scholar] [CrossRef]
- Marietta, M.; Ageno, W.; Artoni, A.; De Candia, E.; Gresele, P.; Marchetti, M.; Marcucci, R.; Tripodi, A. COVID-19 and Haemostasis: A Position Paper from Italian Society on Thrombosis and Haemostasis (SISET). Blood Transfus. 2020, 18, 167–169. [Google Scholar] [CrossRef]
- Iwendi, C.; Bashir, A.K.; Peshkar, A.; Sujatha, R.; Chatterjee, J.M.; Pasupuleti, S.; Mishra, R.; Pillai, S.; Jo, O. COVID-19 Patient Health Prediction Using Boosted Random Forest Algorithm. Front. Public Health 2020, 8, 357. [Google Scholar] [CrossRef]
- Bottino, F.; Tagliente, E.; Pasquini, L.; Napoli, A.D.; Lucignani, M.; Figà-Talamanca, L.; Napolitano, A. COVID Mortality Prediction with Machine Learning Methods: A Systematic Review and Critical Appraisal. J. Pers. Med. 2021, 11, 893. [Google Scholar] [CrossRef]
- RStudio Team. RStudio: Integrated Development Environment for R. RStudio, PBC, Boston, MA. 2021. Available online: http://www.rstudio.com/ (accessed on 8 March 2022).
- Kuhn, M.; Quinlan, R. C50: C5.0 Decision Trees and Rule-Based Models. R Package Version 0.1.5. 2021. Available online: https://cran.r-project.org/package=c50 (accessed on 8 March 2022).
- Warnes, G.R.; Bolker, B.; Lumley, T.; Johnson, R.C. Gmodels: Various R Programming Tools for Model Fitting. Available online: https://CRAN.R-project.org/package=gmodels (accessed on 8 March 2022).
- Robin, X.; Turck, N.; Hainard, A.; Tiberti, N.; Lisacek, F.; Sanchez, J.; Müller, M. pROC: An open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinform. 2011, 12, 77. [Google Scholar] [CrossRef]
- Adamidi, E.S.; Mitsis, K.; Nikita, K.S. Artificial Intelligence in Clinical Care amidst COVID-19 Pandemic: A Systematic Review. Comput. Struct. Biotechnol. J. 2021, 19, 2833–2850. [Google Scholar] [CrossRef]
- De Souza, F.S.H.; Hojo-Souza, N.S.; Dos Santos, E.B.; Da Silva, C.M.; Guidoni, D.L. Predicting the Disease Outcome in COVID-19 Positive Patients Through Machine Learning: A Retrospective Cohort Study With Brazilian Data. Front. Artif. Intell. 2021, 4, 579931. [Google Scholar] [CrossRef] [PubMed]
- Rokach, L.; Maimon, O. Decision Trees. In Data Mining and Knowledge Discovery Handbook; Maimon, O., Rokach, L., Eds.; Springer: Boston, MA, USA, 2005; pp. 165–192. ISBN 978-0-387-25465-4. [Google Scholar]
- Rochmawati, N.; Hidayati, H.B.; Yamasari, Y.; Yustanti, W.; Rakhmawati, L.; Tjahyaningtijas, H.P.A.; Anistyasari, Y. Covid Symptom Severity Using Decision Tree. In Proceedings of the 2020 Third International Conference on Vocational Education and Electrical Engineering (ICVEE), Surabaya, Indonesia, 3–4 October 2020; pp. 1–5. [Google Scholar]
- Migriño, J.R.; Batangan, A.R.U. Using Machine Learning to Create a Decision Tree Model to Predict Outcomes of COVID-19 Cases in the Philippines. West. Pac. Surveill. Response J. 2021, 12, 56–64. [Google Scholar] [CrossRef] [PubMed]
- Altini, N.; Brunetti, A.; Mazzoleni, S.; Moncelli, F.; Zagaria, I.; Prencipe, B.; Lorusso, E.; Buonamico, E.; Carpagnano, G.E.; Bavaro, D.F.; et al. Predictive Machine Learning Models and Survival Analysis for COVID-19 Prognosis Based on Hematochemical Parameters. Sensors 2021, 21, 8503. [Google Scholar] [CrossRef] [PubMed]
- Naseem, M.; Arshad, H.; Hashmi, S.A.; Irfan, F.; Ahmed, F.S. Predicting Mortality in SARS-COV-2 (COVID-19) Positive Patients in the Inpatient Setting Using a Novel Deep Neural Network. Int. J. Med. Inform. 2021, 154, 104556. [Google Scholar] [CrossRef] [PubMed]
- Hirsh, J.; Poller, L. The International Normalized Ratio. A Guide to Understanding and Correcting Its Problems. Arch. Intern. Med. 1994, 154, 282–288. [Google Scholar] [CrossRef]
- Perera, A.; Chowdary, P.; Johnson, J.; Lamb, L.; Drebes, A.; Mir, N.; Sood, T. A 10-Fold and Greater Increase in D-Dimer at Admission in COVID-19 Patients Is Highly Predictive of Pulmonary Embolism in a Retrospective Cohort Study. Ther. Adv. Hematol. 2021, 12, 20406207211048364. [Google Scholar] [CrossRef]
- Li, P.; Zhao, W.; Kaatz, S.; Latack, K.; Schultz, L.; Poisson, L. Factors Associated With Risk of Postdischarge Thrombosis in Patients With COVID-19. JAMA Netw. Open 2021, 4, e2135397. [Google Scholar] [CrossRef]
- COVID-19-Associated Coagulopathy—PubMed. Available online: https://pubmed.ncbi.nlm.nih.gov/32683333/ (accessed on 8 March 2022).
- Iba, T.; Warkentin, T.E.; Thachil, J.; Levi, M.; Levy, J.H. Proposal of the Definition for COVID-19-Associated Coagulopathy. J. Clin. Med. 2021, 10, 191. [Google Scholar] [CrossRef]
- Gao, Y.D.; Ding, M.; Dong, X.; Zhang, J.J.; Kursat Azkur, A.; Azkur, D.; Gan, H.; Sun, Y.L.; Fu, W.; Li, W.; et al. Risk factors for severe and critically ill COVID-19 patients: A review. Allergy 2021, 76, 428–455. [Google Scholar] [CrossRef]
- Malik, P.; Patel, U.; Mehta, D.; Patel, N.; Kelkar, R.; Akrmah, M.; Gabrilove, J.L.; Sacks, H. Biomarkers and outcomes of COVID-19 hospitalisations: Systematic review and meta-analysis. BMJ Evid. Based Med. 2021, 26, 107–108. [Google Scholar] [CrossRef]
- Mesas, A.E.; Cavero-Redondo, I.; Álvarez-Bueno, C.; Sarriá Cabrera, M.A.; Maffei de Andrade, S.; Sequí-Dominguez, I.; Martínez-Vizcaíno, V. Predictors of in-hospital COVID-19 mortality: A comprehensive systematic review and meta-analysis exploring differences by age, sex and health conditions. PLoS ONE 2020, 15, e0241742. [Google Scholar] [CrossRef]
- Suryawanshi, S.Y.; Priya, S.; Sinha, S.S.; Soni, S.; Haidry, N.; Verma, S.; Singh, S. Dynamic Profile and Clinical Implications of Hematological and Immunological Parameters in COVID-19 Patients. A Retrospective Study. J. Fam. Med. Prim. Care 2021, 10, 2518–2523. [Google Scholar] [CrossRef]
- Yuan, X.; Huang, W.; Ye, B.; Chen, C.; Huang, R.; Wu, F.; Wei, Q.; Zhang, W.; Hu, J. Changes of Hematological and Immunological Parameters in COVID-19 Patients. Int. J. Hematol. 2020, 112, 553–559. [Google Scholar] [CrossRef] [PubMed]
- De Vito, D.; Di Ciaula, A.; Palmieri, V.O.; Trerotoli, P.; Larocca, A.M.V.; Montagna, M.T.; Portincasa, P. Reduced COVID-19 mortality linked with early antibodies against SARS-CoV-2, irrispective of age. Eur. J. Int. Med. 2022, 98, 77–82. [Google Scholar] [CrossRef] [PubMed]
- Grokking Machine Learning. Available online: https://www.manning.com/books/grokking-machine-learning (accessed on 8 March 2022).
- Sun, C.; Hong, S.; Song, M.; Li, H.; Wang, Z. Predicting COVID-19 Disease Progression and Patient Outcomes Based on Temporal Deep Learning. BMC Med. Inform. Decis. Mak. 2021, 21, 45. [Google Scholar] [CrossRef]
Death or Transferred to Intensive Care Unit (n = 32) | Discharged Alive (n = 113) | ||||
---|---|---|---|---|---|
N | % | N | % | p-Value | |
Sex | |||||
Male | 18 | 56.25% | 61 | 53.98% | 1.00 |
Female | 14 | 43.75% | 52 | 46.02% | |
Symptoms | |||||
Dyspnea | 12 | 37.50% | 52 | 46.02% | 0.999 |
Cough | 5 | 15.63% | 35 | 30.97% | 1.00 |
Fatigue | 7 | 21.88% | 30 | 26.55% | 1.00 |
Headache | 2 | 6.25% | 12 | 10.62% | 1.00 |
Confusion | 1 | 3.13% | 9 | 7.96% | 1.00 |
Nausea | 1 | 3.13% | 8 | 7.08% | 1.00 |
Sick | 1 | 3.13% | 6 | 5.31% | 1.00 |
Pharyngitis | 1 | 3.13% | 6 | 5.31% | 1.00 |
Nasal congestion | 1 | 3.13% | 3 | 2.65% | 0.999 |
Arthralgia | 0 | 0.00% | 3 | 2.65% | 1.00 |
Myalgia | 1 | 3.13% | 2 | 1.77% | 0.997 |
Arrhythmia | 3 | 9.38% | 12 | 10.62% | 1.00 |
Comorbidity | |||||
Hypertension | 12 | 37.50% | 71 | 62.83% | 0.356 |
Cardiovascular disease | 12 | 37.50% | 43 | 38.05% | 1.00 |
Diabetes | 11 | 34.38% | 35 | 30.97% | 1.00 |
Cerebrovascular disease | 9 | 28.13% | 19 | 16.81% | 0.896 |
Chronic kidney disease | 8 | 25.00% | 14 | 12.39% | 0.585 |
COPD | 5 | 15.63% | 14 | 12.39% | 0.999 |
Tumors | 5 | 15.63% | 11 | 9.73% | 0.986 |
Hepatitis B | 0 | 0.00% | 6 | 5.31% | 0.974 |
Immunopathological disease | 1 | 3.13% | 5 | 4.42% | 1.00 |
Patients Deaths or Transferred in ICU (n =32) | Patients Alive (n = 113) | p-Value | |||||
---|---|---|---|---|---|---|---|
Median | Q1 | Q3 | Median | Q1 | Q3 | ||
Age (years) | 78.0 | 67.0 | 85.75 | 70.0 | 57.0 | 82.0 | 0.011 |
Temperature (°C) | 36.5 | 36.0 | 36.6 | 36.4 | 36.2 | 36.67 | 0.715 |
Respiratory rate (rpm) | 20.0 | 18.0 | 20.0 | 18.0 | 15.0 | 20.0 | 0.110 |
Cardiac frequency (bpm) | 79.0 | 70.0 | 99.0 | 82.5 | 75.0 | 92.5 | 0.515 |
Systolic blood pressure (mmHg) | 137.5 | 116.0 | 150.0 | 130.0 | 122.5 | 145.0 | 0.947 |
Diastolic blood pressure (mmHg) | 77.of 5 | 65.0 | 82.5 | 77.0 | 70.0 | 85.75 | 0.643 |
Temperature at admission (°C) | 36.5 | 36.0 | 36.6 | 36.4 | 36.2 | 36.67 | 0.715 |
Percentage of O2 saturation | 97.0 | 94.75 | 97.25 | 97.0 | 96.0 | 99.0 | 0.017 |
FiO2 (%) | 50.0 | 28.0 | 80.0 | 37.5 | 21.0 | 60.0 | 0.227 |
Neutrophil count (×103%µL) | 79.8 | 74.525 | 85.32 | 77.4 | 69.25 | 84.4 | 0.124 |
Lymphocyte count (×103%µL) | 13.4 | 8.9 | 16.35 | 14.95 | 9.4 | 21.3 | 0.115 |
Platelet count (×103%µL) | 202,000 | 147,250 | 272,250 | 222,500 | 168,500 | 292,000 | 0.212 |
Hemoglobin level (g%dL) | 127.0 | 116.75 | 143.0 | 123.0 | 108.0 | 137.0 | 0.162 |
Procalcitonin levels (ng%mL) | 0.11 | 0.09 | 0.27 | 0.12 | 0.06 | 0.23 | 0.712 |
CRP (mg%mL) | 79.7 | 30.6 | 105.5 | 37.6 | 14.0 | 97.6 | 0.066 |
LDH (mg%mL) | 307.0 | 258.75 | 368.0 | 256.0 | 207.0 | 309.0 | 0.007 |
Albumin (mg%mL) | 27.0 | 24.0 | 30.5 | 28.0 | 25.0 | 31.0 | 0.098 |
ALT (mg%mL) | 23.0 | 14.75 | 52.0 | 27.0 | 20.0 | 47.0 | 0.413 |
AST (mg%mL) | 30.0 | 22.0 | 48.0 | 28.5 | 21.0 | 38.5 | 0.371 |
ALP (mg%mL) | 72.0 | 58.5 | 87.0 | 64.0 | 53.0 | 83.0 | 0.441 |
Direct bilirubin (mg%mL) | 0.01 | 0.009 | 0.0168 | 0.01 | 0.007 | 0.0139 | 0.041 |
Indirect bilirubin (mg%mL) | 0.015 | 0.012 | 0.022 | 0.015 | 0.01 | 0.02 | 0.900 |
Total bilirubin (mg%mL) | 0.027 | 0.022 | 0.037 | 0.027 | 0.02 | 0.034 | 0.586 |
Creatinine (mg%mL) | 1.063 | 0.76 | 1.637 | 0.83 | 0.695 | 1.16 | 0.019 |
CPK (mg%mL) | 92.0 | 46.0 | 165.5 | 72.5 | 41 | 145.0 | 0.406 |
Sodium (mg%mL) | 140.0 | 138.0 | 142.0 | 139.0 | 137 | 141.0 | 0.014 |
Potassium (mg%mL) | 4.0 | 3.6 | 4.275 | 4.1 | 3.8 | 4.5 | 0.104 |
D-dimers (mg%L) | 0.771 | 0.528 | 2.265 | 0.908 | 0.502 | 1.962 | 0.882 |
INR | 1.12 | 1.052 | 1.202 | 1.04 | 1.0 | 1.09 | <0.001 |
IL-6 (pg%mL) | 38.3 | 17.3 | 123.0 | 29.2 | 7.05 | 83.5 | 0.183 |
IgM(g%L) AU/mL | 0.68 | 0.07 | 8.842 | 4.19 | 0.473 | 13.303 | 0.032 |
IgG(g%L) AU/mL | 0.3 | 0.065 | 3.955 | 2.51 | 0.185 | 5.74 | 0.023 |
Length of stay (days) | 11.0 | 5.75 | 15 | 9.0 | 5.0 | 16.0 | 0.837 |
Parameter | Value (%) |
---|---|
Accuracy | 75.93% |
Sensitivity | 99.61% |
Specificity | 23.43% |
PPV | 82.18% |
NPV | 40.07% |
F1-score | 89.17% |
MCC | 17.94% |
Balanced accuracy | 61.52% |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 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
Giotta, M.; Trerotoli, P.; Palmieri, V.O.; Passerini, F.; Portincasa, P.; Dargenio, I.; Mokhtari, J.; Montagna, M.T.; De Vito, D. Application of a Decision Tree Model to Predict the Outcome of Non-Intensive Inpatients Hospitalized for COVID-19. Int. J. Environ. Res. Public Health 2022, 19, 13016. https://doi.org/10.3390/ijerph192013016
Giotta M, Trerotoli P, Palmieri VO, Passerini F, Portincasa P, Dargenio I, Mokhtari J, Montagna MT, De Vito D. Application of a Decision Tree Model to Predict the Outcome of Non-Intensive Inpatients Hospitalized for COVID-19. International Journal of Environmental Research and Public Health. 2022; 19(20):13016. https://doi.org/10.3390/ijerph192013016
Chicago/Turabian StyleGiotta, Massimo, Paolo Trerotoli, Vincenzo Ostilio Palmieri, Francesca Passerini, Piero Portincasa, Ilaria Dargenio, Jihad Mokhtari, Maria Teresa Montagna, and Danila De Vito. 2022. "Application of a Decision Tree Model to Predict the Outcome of Non-Intensive Inpatients Hospitalized for COVID-19" International Journal of Environmental Research and Public Health 19, no. 20: 13016. https://doi.org/10.3390/ijerph192013016