Machine learning algorithms to detect patient–ventilator asynchrony: a feasibility study
Background: Effective ventilatory support requires regular assessments of patient–ventilator interactions. Developing a dependable, automated method for this evaluation is crucial. We explored the feasibility of using machine learning algorithms to replicate the assessment of breathing pa...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Academia.edu Journals
2025-05-01
|
| Series: | Academia Medicine |
| Online Access: | https://www.academia.edu/129632610/Machine_learning_algorithms_to_detect_patient_ventilator_asynchrony_a_feasibility_study |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Background: Effective ventilatory support requires regular assessments of patient–ventilator interactions. Developing a dependable, automated method for this evaluation is crucial. We explored the feasibility of using machine learning algorithms to replicate the assessment of breathing patterns by experienced clinicians, based on airway flow and pressure signals. Methods: We conducted a prospective, observational study of 44 adult patients who were undergoing invasive mechanical ventilation. Airway flow and pressure signals were digitally acquired from the ventilator and recorded as 131 s epochs. Experienced clinicians analyzed and categorized 50,712 epochs, which included roughly 2.6 million breathing cycles. We developed four random forest algorithms to (1) detect asynchronous breathing, (2) classify types of breathing asynchrony, (3) assess the extent of signal disruption, and (4) identify dynamic hyperinflation. The accuracy of these algorithms was evaluated based on their ability to correctly identify epochs, and their clinical reliability was assessed by comparing their predictions to those of clinicians with different levels of experience in asynchrony classification. Results: The algorithms achieved accuracies of 91%, 81%, 87%, and 93% in detecting asynchronous breathing, classifying asynchrony types, assessing the severity of signal disruption, and identifying dynamic hyperinflation, respectively. The classifications of models 1, 2 and 3 were more consistent among expert clinicians (kappa scores 0.58, 0.46 and 0.59) than among non-experts (kappa scores 0.42, 0.25 and 0.38; p < 0.05). A longer duration of asynchronous breathing was associated with increased 28-day mortality (p = 0.015). Conclusions: Machine learning algorithms can effectively emulate expert clinicians’ assessments of breathing patterns in mechanically ventilated patients. Enhancements in algorithm accuracy will require larger databases and further advancements in artificial intelligence. |
|---|---|
| ISSN: | 2994-435X |