Closed-loop ventilation

Arnal, Jean-Michel; Katayama, Shinshu; Howard, Christopher

doi:10.1097/mcc.0000000000001012

Cited by 7 publications

(3 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These systems continuously monitor changes in ventilation, interpret physiological changes in real time, and adapt ventilation. Closed-loop systems consist of an input that activates the system and an output and a protocol that integrates the two [ 51 ]. Despite the extensive development of new systems, a Chocrane review compared automated with traditional trials, the authors conclude by underlining the need for large randomized controlled trials that can effectively compare the efficacy of the two protocols [ 52 ].…”

Section: Ventilatory Strategymentioning

confidence: 99%

Difficult Respiratory Weaning after Cardiac Surgery: A Narrative Review

Nicolotti

Grossi

Nicolini

et al. 2023

JCM

View full text Add to dashboard Cite

Respiratory weaning after cardiac surgery can be difficult or prolonged in up to 22.7% of patients. The inability to wean from a ventilator within the first 48 h after surgery is related to increased short- and long-term morbidity and mortality. Risk factors are mainly non-modifiable and include preoperative renal failure, New York Heart Association, and Canadian Cardiac Society classes as well as surgery and cardio-pulmonary bypass time. The positive effects of pressure ventilation on the cardiovascular system progressively fade during the progression of weaning, possibly leading to pulmonary oedema and failure of spontaneous breathing trials. To prevent this scenario, some parameters such as pulmonary artery occlusion pressure, echography-assessed diastolic function, brain-derived natriuretic peptide, and extravascular lung water can be monitored during weaning to early detect hemodynamic decompensation. Tracheostomy is considered for patients with difficult and prolonged weaning. In such cases, optimal patient selection, timing, and technique may be important to try to reduce morbidity and mortality in this high-risk population.

show abstract

Section: Ventilatory Strategymentioning

confidence: 99%

Difficult Respiratory Weaning after Cardiac Surgery: A Narrative Review

Nicolotti

Grossi

Nicolini

et al. 2023

JCM

View full text Add to dashboard Cite

show abstract

“…In 2004, Chatburn [33] and Perchiazzi [34] mentioned the use of arti cial neural networks as a future tool to control respiratory support. However, their effective implementation in this usage is still pending, although closed-loop mechanical ventilation has moved different steps forward [7], mainly relying upon white-box approaches [35]. It is important to underline that the main aim of this contribution was not to model the many interactions between the respiratory centers, which per se is a quite complex task [20].…”

Section: Discussionmentioning

confidence: 99%

“…For the above-mentioned di culties in continuously quantifying the components of the respiratory system, a standard method to implement mechanical ventilation is based on taking intermittently blood samples from a peripheral artery, measuring the blood gases, and manually adjusting the ventilator. The quest for creating tools able to support patient ventilation in closed-loop has brought to systems that combine in different ways information derived from the expired CO 2 or the respiratory activity of the patient [7].…”

Section: Introductionmentioning

confidence: 99%

Imitating the respiratory activity of the brain stem by using artificial neural networks: exploratory study on an animal model of lactic acidosis and proof of concept

Perchiazzi,

Kawati,

Pellegrini

et al. 2024

Preprint

View full text Add to dashboard Cite

Purpose: Artificial neural networks (ANNs) are versatile tools capable of learning without prior knowledge. This study aims to evaluate whether ANN can calculate minute volume during spontaneous breathing after being trained using data from an animal model of metabolic acidosis. Methods: Data was collected from ten anesthetized, spontaneously breathing pigs divided randomly into two groups, one without dead space and the other with dead space at the beginning of the experiment. Each group underwent two equal sequences of pH lowering with pre-defined targets by continuous infusion of lactic acid. The inputs to ANNs were pH, DPaCO2 (variation of the arterial partial pressure of CO2), PaO2, and blood temperature which were sampled from the animal model. The output was the delta minute volume (DVM), (the change of minute volume as compared to the minute volume the animal had at the beginning of the experiment). The ANN performance was analyzed using mean squared error (MSE), linear regression, and the Bland-Altman (B-A) method. Results: The animal experiment provided the necessary data to train the ANN. The best architecture of ANN had 17 intermediate neurons; the best performance of the finally trained ANN had a linear regression with R2 of 0.99, an MSE of 0.001 [L/min], a B-A analysis with bias ± standard deviation of 0.006 ± 0.039 [L/min]. Conclusions: ANNs can accurately estimate DVM using the same information that arrives at the respiratory centers. This performance makes them a promising component for the future development of closed-loop artificial ventilators.

show abstract

Imitating the respiratory activity of the brain stem by using artificial neural networks: exploratory study on an animal model of lactic acidosis and proof of concept

Perchiazzi,

Kawati,

Pellegrini

et al. 2024

J Clin Monit Comput

View full text Add to dashboard Cite

Artificial neural networks (ANNs) are versatile tools capable of learning without prior knowledge. This study aims to evaluate whether ANN can calculate minute volume during spontaneous breathing after being trained using data from an animal model of metabolic acidosis. Data was collected from ten anesthetized, spontaneously breathing pigs divided randomly into two groups, one without dead space and the other with dead space at the beginning of the experiment. Each group underwent two equal sequences of pH lowering with pre-defined targets by continuous infusion of lactic acid. The inputs to ANNs were pH, ΔPaCO2 (variation of the arterial partial pressure of CO2), PaO2, and blood temperature which were sampled from the animal model. The output was the delta minute volume (ΔVM), (the change of minute volume as compared to the minute volume the animal had at the beginning of the experiment). The ANN performance was analyzed using mean squared error (MSE), linear regression, and the Bland-Altman (B-A) method. The animal experiment provided the necessary data to train the ANN. The best architecture of ANN had 17 intermediate neurons; the best performance of the finally trained ANN had a linear regression with R2 of 0.99, an MSE of 0.001 [L/min], a B-A analysis with bias ± standard deviation of 0.006 ± 0.039 [L/min]. ANNs can accurately estimate ΔVM using the same information that arrives at the respiratory centers. This performance makes them a promising component for the future development of closed-loop artificial ventilators.

show abstract

Closed-loop ventilation

Cited by 7 publications

References 66 publications

Difficult Respiratory Weaning after Cardiac Surgery: A Narrative Review

Difficult Respiratory Weaning after Cardiac Surgery: A Narrative Review

Imitating the respiratory activity of the brain stem by using artificial neural networks: exploratory study on an animal model of lactic acidosis and proof of concept

Imitating the respiratory activity of the brain stem by using artificial neural networks: exploratory study on an animal model of lactic acidosis and proof of concept

Contact Info

Product

Resources

About