Related Experiment Video
Updated: May 22, 2026

Monitoring Lung Function with Electrical Impedance Tomography in the Intensive Care Unit
Published on: September 6, 2024
Artificial Intelligence Algorithm to Monitor Inspiratory Muscle Effort and Patient-Ventilator Dyssynchrony During
Glauco M Plens1,2, Caio César Araújo Morais1,3, Thaís Gregol1
1Divisao de Pneumologia, Faculdade de Medicina, Instituto do Coracao, Hospital das Clinicas Faculdade de Medicina, Universidade de Sao Paulo, Sao Paulo, Brazil.
A new artificial intelligence (AI) algorithm noninvasively estimates inspiratory muscle pressure (Pmus) during mechanical ventilation. This AI tool offers continuous monitoring comparable to invasive methods, improving patient care.
Area of Science:
- Critical Care Medicine
- Biomedical Engineering
- Respiratory Physiology
Background:
- Estimating inspiratory muscle pressure (Pmus) during mechanical ventilation is crucial for patient management.
- Current methods are often invasive or rely on intermittent occlusion maneuvers, limiting continuous monitoring.
- There is a need for noninvasive, real-time methods to assess Pmus and ventilator synchrony.
Purpose of the Study:
- To develop and evaluate a noninvasive artificial intelligence (AI) algorithm for real-time estimation of Pmus during mechanical ventilation.
- To compare the AI-based Pmus estimation (Pmus,AI) against the gold standard of esophageal manometry (Pmus,es).
- To assess the AI algorithm's ability to detect patient effort, driving pressure, and ventilator synchrony.
Main Methods:
- A prospective diagnostic accuracy study was conducted in two ICUs.
- Adult patients under pressure support ventilation were included.
- The AI algorithm's Pmus estimations were compared with esophageal manometry and occlusion-based techniques (Pocc).
Main Results:
- The AI algorithm (Pmus,AI) demonstrated good performance, with a bias of 0.9 cm H2O and limits of agreement of -5.1, 6.9 cm H2O compared to Pmus,es.
- Pmus,AI accurately detected extreme values of Pmus and dynamic driving pressure (AUC > 0.8).
- The AI showed high sensitivity (86.5%) and specificity (77.4%) in detecting ineffective effort and autotriggering.
Conclusions:
- The developed AI algorithm provides a noninvasive and accurate method for estimating Pmus during mechanical ventilation.
- This AI tool enables continuous monitoring of patient effort and ventilator synchrony, comparable to intermittent occlusion techniques.
- The algorithm facilitates automatic detection of specific dyssynchronies, offering potential benefits for clinical decision-making.
Related Concept Videos
Ventilatory Modes
There are three ventilatory modes: full support, partial support, and spontaneous. These are described below.
Full Support Modes
Full support modes include controlled mechanical ventilation, continuous mandatory...
Mechanical Ventilation I: Indication and Settings
Mechanical Ventilation II: Invasive Ventilation
Negative-Pressure Ventilators
Negative-pressure ventilators create a vacuum around the chest or body to draw air into the lungs, simulating breathing. This method does not require an...
Mechanical Ventilation III: Noninvasive Ventilation
Noninvasive Positive-Pressure Ventilation (NIPPV)
Assessment of Ventilation II: Respiratory Depth and Rhythm
Respiratory depth measures the volume of air inhaled or exhaled during a breath. It can vary from shallow to deep and typically remains consistent when a person is at rest or asleep. Occasionally, individuals will automatically inhale deeply, known as sighing, which inflates the lungs with more air than normal breathing.
To assess respiratory depth, observe the degree of chest excursion or movement:
Assessment of Ventilation I: Respiratory Rate
A Ventilation assessment is critical for monitoring a patient's health status. Respiration, one of the most accessible vital signs, provides insights into the function of numerous body systems and can indicate serious health issues, such as brainstem injuries from head trauma.
Critical Guidelines for Assessing Ventilation:

