JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Predicting and diagnosing pneumonia in patients undergoing elective cardiac surgery via machine learning analysis of exhaled volatile carbonyl compounds

  • 0Department of Cardiovascular and Thoracic Surgery, University of Louisville School of Medicine, Louisville, Ky.
The Journal of Thoracic and Cardiovascular Surgery +

|

July 4, 2025

|

July 4, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

This study shows that volatile organic compounds (VOCs) in exhaled breath can be analyzed using machine learning to diagnose and predict pneumonia after cardiac surgery, potentially improving patient care.

Area Of Science

  • Biochemistry
  • Medical Diagnostics
  • Computational Biology

Background

  • Pneumonia is a common complication following cardiac surgery, leading to increased healthcare costs and poorer patient outcomes.
  • Early detection and intervention are crucial for managing postoperative pneumonia.
  • Volatile organic compounds (VOCs) in breath offer a non-invasive method for diagnosing lung conditions.

Purpose Of The Study

  • To develop and validate machine learning (ML) models for diagnosing pneumonia post-cardiac surgery using VOCs.
  • To create an ML model for predicting the onset of pneumonia in cardiac surgery patients based on preoperative VOC analysis.

Main Methods

  • Seventy-five patients undergoing elective cardiac surgery provided breath samples preoperatively and postoperatively.
  • Breath samples were analyzed for carbonyl compounds using mass spectrometry.
  • Machine learning models were trained on VOC data to diagnose and predict pneumonia.

Main Results

  • The pneumonia diagnosis model identified 24 carbonyl compounds with an AUC of 0.833.
  • The pneumonia prediction model identified 4 preoperative carbonyl compounds with an AUC of 0.833.
  • The models demonstrated strong performance in diagnosing and predicting pneumonia onset.

Conclusions

  • Breath VOC analysis combined with ML is a promising tool for pneumonia diagnosis and prediction in cardiac surgery patients.
  • This approach can inform perioperative strategies to prevent pneumonia.
  • Further research can refine these non-invasive diagnostic and predictive tools.

Keywords:

Related Concept Videos

Pneumonia III: Complications and Assessment 01:30

452

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

• Pleurisy: indicates the inflammation of the pleura, which causes chest pain and discomfort.
• Pleural Effusion: indicates fluid buildup in the pleural space.
• Atelectasis: Partial collapse of a lung lobe due to mucus blockage or external compression.
• Bacteremia: Bacterial infection entering the bloodstream, commonly seen with...

Assessment of Respiration 01:23

1.3K

The respiratory system's basic structures and primary functions lay the foundation for nurses' comprehensive respiratory assessments. This assessment includes subjective and objective data to gauge the patient's respiratory health.
Subjective Assessment: Nurses interview the patient to gather information directly during the subjective assessment. It includes questions about the individual's medical history, medications, and symptoms, focusing on past respiratory conditions like...

Chronic Obstructive Pulmonary Disease-IV: Assessement and Diagnostic Studies 01:27

2.6K

Assessing and diagnosing Chronic Obstructive Pulmonary Disease (COPD) involves a detailed approach that includes a comprehensive review of medical history, physical examination, and a variety of diagnostic tests. This thorough evaluation is essential to ensure an accurate diagnosis and guide effective management strategies.
Medical History

• Symptom Review: Chronic symptoms such as persistent cough, sputum production, shortness of breath (dyspnea), and episodes of exacerbation are...