Cargando…
A Predictive Rule for COVID-19 Pneumonia Among COVID-19 Patients: A Classification and Regression Tree (CART) Analysis Model
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 retrosp...
Autores principales: | , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Cureus
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10500617/ https://www.ncbi.nlm.nih.gov/pubmed/37720137 http://dx.doi.org/10.7759/cureus.45199 |
_version_ | 1785105945155600384 |
---|---|
author | Fukui, Sayato Inui, Akihiro Komatsu, Takayuki Ogura, Kanako Ozaki, Yutaka Sugita, Manabu Saita, Mizue Kobayashi, Daiki Naito, Toshio |
author_facet | Fukui, Sayato Inui, Akihiro Komatsu, Takayuki Ogura, Kanako Ozaki, Yutaka Sugita, Manabu Saita, Mizue Kobayashi, Daiki Naito, Toshio |
author_sort | Fukui, Sayato |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-10500617 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Cureus |
record_format | MEDLINE/PubMed |
spelling | pubmed-105006172023-09-15 A Predictive Rule for COVID-19 Pneumonia Among COVID-19 Patients: A Classification and Regression Tree (CART) Analysis Model Fukui, Sayato Inui, Akihiro Komatsu, Takayuki Ogura, Kanako Ozaki, Yutaka Sugita, Manabu Saita, Mizue Kobayashi, Daiki Naito, Toshio Cureus Internal Medicine 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. Cureus 2023-09-13 /pmc/articles/PMC10500617/ /pubmed/37720137 http://dx.doi.org/10.7759/cureus.45199 Text en Copyright © 2023, Fukui et al. https://creativecommons.org/licenses/by/3.0/This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Internal Medicine Fukui, Sayato Inui, Akihiro Komatsu, Takayuki Ogura, Kanako Ozaki, Yutaka Sugita, Manabu Saita, Mizue Kobayashi, Daiki Naito, Toshio A Predictive Rule for COVID-19 Pneumonia Among COVID-19 Patients: A Classification and Regression Tree (CART) Analysis Model |
title | A Predictive Rule for COVID-19 Pneumonia Among COVID-19 Patients: A Classification and Regression Tree (CART) Analysis Model |
title_full | A Predictive Rule for COVID-19 Pneumonia Among COVID-19 Patients: A Classification and Regression Tree (CART) Analysis Model |
title_fullStr | A Predictive Rule for COVID-19 Pneumonia Among COVID-19 Patients: A Classification and Regression Tree (CART) Analysis Model |
title_full_unstemmed | A Predictive Rule for COVID-19 Pneumonia Among COVID-19 Patients: A Classification and Regression Tree (CART) Analysis Model |
title_short | A Predictive Rule for COVID-19 Pneumonia Among COVID-19 Patients: A Classification and Regression Tree (CART) Analysis Model |
title_sort | predictive rule for covid-19 pneumonia among covid-19 patients: a classification and regression tree (cart) analysis model |
topic | Internal Medicine |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10500617/ https://www.ncbi.nlm.nih.gov/pubmed/37720137 http://dx.doi.org/10.7759/cureus.45199 |
work_keys_str_mv | AT fukuisayato apredictiveruleforcovid19pneumoniaamongcovid19patientsaclassificationandregressiontreecartanalysismodel AT inuiakihiro apredictiveruleforcovid19pneumoniaamongcovid19patientsaclassificationandregressiontreecartanalysismodel AT komatsutakayuki apredictiveruleforcovid19pneumoniaamongcovid19patientsaclassificationandregressiontreecartanalysismodel AT ogurakanako apredictiveruleforcovid19pneumoniaamongcovid19patientsaclassificationandregressiontreecartanalysismodel AT ozakiyutaka apredictiveruleforcovid19pneumoniaamongcovid19patientsaclassificationandregressiontreecartanalysismodel AT sugitamanabu apredictiveruleforcovid19pneumoniaamongcovid19patientsaclassificationandregressiontreecartanalysismodel AT saitamizue apredictiveruleforcovid19pneumoniaamongcovid19patientsaclassificationandregressiontreecartanalysismodel AT kobayashidaiki apredictiveruleforcovid19pneumoniaamongcovid19patientsaclassificationandregressiontreecartanalysismodel AT naitotoshio apredictiveruleforcovid19pneumoniaamongcovid19patientsaclassificationandregressiontreecartanalysismodel AT fukuisayato predictiveruleforcovid19pneumoniaamongcovid19patientsaclassificationandregressiontreecartanalysismodel AT inuiakihiro predictiveruleforcovid19pneumoniaamongcovid19patientsaclassificationandregressiontreecartanalysismodel AT komatsutakayuki predictiveruleforcovid19pneumoniaamongcovid19patientsaclassificationandregressiontreecartanalysismodel AT ogurakanako predictiveruleforcovid19pneumoniaamongcovid19patientsaclassificationandregressiontreecartanalysismodel AT ozakiyutaka predictiveruleforcovid19pneumoniaamongcovid19patientsaclassificationandregressiontreecartanalysismodel AT sugitamanabu predictiveruleforcovid19pneumoniaamongcovid19patientsaclassificationandregressiontreecartanalysismodel AT saitamizue predictiveruleforcovid19pneumoniaamongcovid19patientsaclassificationandregressiontreecartanalysismodel AT kobayashidaiki predictiveruleforcovid19pneumoniaamongcovid19patientsaclassificationandregressiontreecartanalysismodel AT naitotoshio predictiveruleforcovid19pneumoniaamongcovid19patientsaclassificationandregressiontreecartanalysismodel |