Respiratory failure & ventilation
Artificial Intelligence Algorithm to Monitor Inspiratory Muscle Effort and Patient-Ventilator Dyssynchrony During Mechanical Ventilation
Authors' conclusion
AI presented good performance in detecting high and low Pmus , and allowed the automatic detection of specific types of dyssynchronies. This novel noninvasive method was comparable to intermittent techniques requiring occlusion maneuvers.
Study context
- Population
- Adults under pressure support ventilation in 2 ICUs, University of São Paulo, Brazil4,918 cycles analysed
- Participants
- 48 participants
- Comparison
- Artificial intelligence (AI)-estimated Pmus vs esophageal manometry and occlusion-based techniques
- Outcome
- Agreement with Pmus,es
Methodological detailsprospective, 2 ICUs
- Prospective
- 2 ICUs
Performance
As reported in the abstract
| Test or model | Bias | 95% limits of agreement |
|---|---|---|
| Pmus,AI | 0.9 | −5.1, 6.9 |
Pmus,AI
Bias0.9
95% limits of agreement−5.1, 6.9
- Pmus,es range
- 1.0 to 28.4 cm H 2 O
Further findings
| Outcome | Pmus,AI |
|---|---|
| Detection of extreme values of Pmus,es and dynamic driving pressure | |
| AUC | greater than 0.8 |
| Detection of ineffective effort, autotriggering or reverse triggering vs experts' classification | |
| Sensitivity | 86.5% |
| Specificity | 77.4% |
Accuracy vs occlusion-based techniques (pressure muscle index, Pocc)
- Pmus,AI accuracy comparable to occlusion-based techniques
Parts of this Brief are withheld: the automatic checks could not confirm them against the abstract.
Original publication
Artificial Intelligence Algorithm to Monitor Inspiratory Muscle Effort and Patient-Ventilator Dyssynchrony During Mechanical Ventilation. Crit Care Med. Published 21 May 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →