Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Pneumonia III: Complications and Assessment

Pneumonia III: Complications and Assessment

Pneumonia poses the potential for numerous complications that warrant consideration. These complications include the following:

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Craving for a Robust Methodology: A Systematic Review of Machine Learning Algorithms on Substance-Use Disorders Treatment Outcomes.

International journal of mental health and addiction·2026

Same author

Biomarkers.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2026

Same author

Public Health.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2025

Same author

Public Health.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2025

Same author

Evaluating the Role of α-Synuclein Seed Amplification as a Disease Progression Marker: Evidence and Uncertainties.

Movement disorders clinical practice·2025

Same author

Stratifying dementia risk factors: A prediction model and hypothesis-driven analysis.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2025

Search research articles

Related Experiment Video

Updated: Oct 4, 2025

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

Explainable Machine Learning for COVID-19 Pneumonia Classification With Texture-Based Features Extraction in Chest

Luís Vinícius de Moura¹, Christian Mattjie^1,2, Caroline Machado Dartora^1,2

¹Medical Image Computing Laboratory, School of Technology, Pontifical Catholic University of Rio Grande do Sul, PUCRS, Porto Alegre, Brazil.

Frontiers in Digital Health

|February 3, 2022

Summary

This study used machine learning to analyze chest X-rays for diagnosing coronavirus disease 2019 (COVID-19) pneumonia. Radiomic features from specific lung zones helped differentiate COVID-19 from other lung patterns with 82% accuracy.

Keywords:

SHAP X-rays coronavirus explainable models machine learning radiological findings radiomics

More Related Videos

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models

Published on: June 20, 2025

Related Experiment Videos

Last Updated: Oct 4, 2025

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models

Published on: June 20, 2025

Area of Science:

Radiology
Artificial Intelligence
Medical Imaging

Background:

Chest X-rays and reverse transcription-PCR (RT-PCR) are diagnostic tools for coronavirus disease 2019 (COVID-19).
COVID-19 pneumonia lacks distinct radiological findings, necessitating advanced analysis techniques.
Radiomic feature analysis offers potential for differentiating COVID-19 pneumonia from other lung conditions on chest X-rays.

Purpose of the Study:

To investigate radiomic features and machine learning models for differentiating COVID-19 pneumonia from other lung patterns on chest X-rays.
To identify distinctive radiographic texture features of COVID-19 pneumonia using explainable AI.
To leverage supervised ensemble tree-based methods and Shapley Additive Explanations (SHAP) for improved diagnostic insights.

Main Methods:

Utilized a dataset of 2,611 COVID-19 and 2,611 non-COVID-19 chest X-ray images.
Performed lung segmentation into three zones, followed by histogram normalization and radiomic feature extraction.
Employed SHAP recursive feature elimination for feature selection and random search for hyperparameter optimization of XGBoost and Random Forest models.

Main Results:

The XGBoost model achieved the highest classification performance, with an accuracy of 0.82 and a sensitivity of 0.82.
The explainable AI model highlighted the significance of the middle left and superior right lung zones in accurate classification.
Ensemble tree-based models demonstrated effectiveness in identifying patterns indicative of COVID-19 pneumonia.

Conclusions:

Machine learning models, particularly XGBoost, can effectively differentiate COVID-19 pneumonia from other lung conditions using radiomic features from chest X-rays.
Radiomic analysis, guided by explainable AI, can reveal specific textural patterns in distinct lung zones crucial for COVID-19 diagnosis.
This approach provides a foundation for developing more accurate and interpretable AI-driven diagnostic tools for respiratory diseases.