Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Sep 13;15(9):e45199.
doi: 10.7759/cureus.45199. eCollection 2023 Sep.

A Predictive Rule for COVID-19 Pneumonia Among COVID-19 Patients: A Classification and Regression Tree (CART) Analysis Model

Sayato Fukui  1 , Akihiro Inui  1 , Takayuki Komatsu  2 , Kanako Ogura  3 , Yutaka Ozaki  4 , Manabu Sugita  2 , Mizue Saita  1 , Daiki Kobayashi  5 , Toshio Naito  1
Affiliations

A Predictive Rule for COVID-19 Pneumonia Among COVID-19 Patients: A Classification and Regression Tree (CART) Analysis Model

Sayato Fukui et al. Cureus. .

Abstract

Background: In this study, we aimed to identify predictive factors for coronavirus disease 2019 (COVID-19) patients with complicated pneumonia and determine which COVID-19 patients should undergo computed tomography (CT) using classification and regression tree (CART) analysis.

Methods: This retrospective cross-sectional survey was conducted at a university hospital. We recruited patients diagnosed with COVID-19 between January 1 and December 31, 2020. We extracted clinical information (e.g., vital signs, symptoms, laboratory results, and CT findings) from patient records. Factors potentially predicting COVID-19 pneumonia were analyzed using Student's t-test, the chi-square test, and a CART analysis model.

Results: Among 221 patients (119 men (53.8%); mean age, 54.59±18.61 years), 160 (72.4%) had pneumonia. The CART analysis revealed that patients were at high risk of pneumonia if they had C-reactive protein (CRP) levels of >1.60 mg/dL (incidence of pneumonia: 95.7%); CRP levels of ≤1.60 mg/dL + age >35.5 years + lactate dehydrogenase (LDH)>225.5 IU/L (incidence of pneumonia: 95.5%); and CRP levels of ≤1.60 mg/dL + age >35.5 years + LDH≤225.5 IU/L + hemoglobin ≤14.65 g/dL (incidence of pneumonia: 69.6%). The area of the curve of the receiver operating characteristic of the model was 0.860 (95% CI: 0.804-0.915), indicating sufficient explanatory power.

Conclusions: The present results are useful for deciding whether to perform CT in COVID-19 patients. High-risk patients such as those mentioned above should undergo CT.

Keywords: blood testing; clinical feature; computed tomography; prevalent infection; severe acute respiratory syndrome coronavirus 2.

PubMed Disclaimer

Conflict of interest statement

The authors have declared that no competing interests exist.

Figures

Figure 1
Figure 1. Decision tree for COVID-19 patients complicating pneumonia using classification and regression tree (CART) analysis. The results were derived from CART analysis. Low-risk (≤30%), medium-risk (30-60%), and high-risk (>60%).
COVID-19, coronavirus disease 2019; CRP, C-reactive protein; LDH, lactate dehydrogenase; Hb, hemoglobin.
Figure 2
Figure 2. The area under the receiver operating characteristic curve of the model was 0.860 (95% confidence interval, 0.804–0.915).
AUC, area under the curve
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. The epidemiological characteristics of an outbreak of 2019 novel coronavirus diseases (COVID-19) in China (Article in Chinese) Zhonghua Liu Xing Bing Xue Za Zhi. 2020;41:145–151. - PubMed
    1. World Health Organization: Coronavirus disease (COVID-19) pandemic. [ Oct; 2020 ]. 2020. https://www.who.int/europe/emergencies/situations/covid-19 https://www.who.int/europe/emergencies/situations/covid-19
    1. Assay techniques and test development for COVID-19 diagnosis. Carter LJ, Garner LV, Smoot JW, et al. ACS Cent Sci. 2020;6:591–605. - PMC - PubMed
    1. Emerging 2019 novel Coronavirus (2019-nCoV) pneumonia. Song F, Shi N, Shan F, et al. Radiology. 2020;295:210–217. - PMC - PubMed
    1. A systematic review of the relationship between chest CT severity score and laboratory findings and clinical parameters in COVID-19 pneumonia. Majrashi NA, Alhulaibi RA, Nammazi IH, et al. Diagnostics (Basel) 2023;13:2223. - PMC - PubMed

LinkOut - more resources