Related Experiment Video
Updated: Jul 16, 2025

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
A Predictive Rule for COVID-19 Pneumonia Among COVID-19 Patients: A Classification and Regression Tree (CART)
Sayato Fukui1, Akihiro Inui1, Takayuki Komatsu2
1Department of General Medicine, Faculty of Medicine, Juntendo University, Tokyo, JPN.
This study identified key factors to predict complicated pneumonia in COVID-19 patients. High-risk individuals, identified by C-reactive protein, age, LDH, and hemoglobin levels, should undergo computed tomography (CT) scans.
Area of Science:
- Medical Imaging and Diagnostics
- Infectious Diseases
- Pulmonology
Background:
- Coronavirus disease 2019 (COVID-19) can lead to complicated pneumonia.
- Identifying patients who require computed tomography (CT) is crucial for effective management.
- Predictive factors for severe COVID-19 pneumonia are not fully established.
Purpose of the Study:
- To identify predictive factors for complicated pneumonia in COVID-19 patients.
- To determine criteria for performing CT scans in COVID-19 patients using classification and regression tree (CART) analysis.
Main Methods:
- Retrospective cross-sectional study at a university hospital.
- Analysis of clinical data from 221 COVID-19 patients diagnosed in 2020.
- Classification and regression tree (CART) analysis to identify pneumonia predictors.
Main Results:
- 160 out of 221 patients (72.4%) developed pneumonia.
- CART analysis identified high-risk groups based on C-reactive protein (CRP), age, lactate dehydrogenase (LDH), and hemoglobin levels.
- The predictive model demonstrated sufficient explanatory power with an ROC curve area of 0.860.
Conclusions:
- The developed model aids in deciding whether to perform CT scans for COVID-19 patients.
- High-risk COVID-19 patients, identified by specific clinical and laboratory markers, warrant CT imaging.
More Related Videos
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
08:05Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
Related Concept Videos
Survival Tree
Building a Survival Tree
Constructing a...
Residuals and Least-Squares Property
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
Classification of Illness
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
Receiver Operating Characteristic Plot
Pneumonia III: Complications and Assessment
Pulmonary Hypertension: Classification and Pathogenesis
There are various classifications for PH, each relating to different underlying causes and also...