Flow starvation during square-flow assisted ventilation detected by supervised deep learning techniques
© 2024. The Author(s)..
BACKGROUND: Flow starvation is a type of patient-ventilator asynchrony that occurs when gas delivery does not fully meet the patients' ventilatory demand due to an insufficient airflow and/or a high inspiratory effort, and it is usually identified by visual inspection of airway pressure waveform. Clinical diagnosis is cumbersome and prone to underdiagnosis, being an opportunity for artificial intelligence. Our objective is to develop a supervised artificial intelligence algorithm for identifying airway pressure deformation during square-flow assisted ventilation and patient-triggered breaths.
METHODS: Multicenter, observational study. Adult critically ill patients under mechanical ventilation > 24 h on square-flow assisted ventilation were included. As the reference, 5 intensive care experts classified airway pressure deformation severity. Convolutional neural network and recurrent neural network models were trained and evaluated using accuracy, precision, recall and F1 score. In a subgroup of patients with esophageal pressure measurement (ΔPes), we analyzed the association between the intensity of the inspiratory effort and the airway pressure deformation.
RESULTS: 6428 breaths from 28 patients were analyzed, 42% were classified as having normal-mild, 23% moderate, and 34% severe airway pressure deformation. The accuracy of recurrent neural network algorithm and convolutional neural network were 87.9% [87.6-88.3], and 86.8% [86.6-87.4], respectively. Double triggering appeared in 8.8% of breaths, always in the presence of severe airway pressure deformation. The subgroup analysis demonstrated that 74.4% of breaths classified as severe airway pressure deformation had a ΔPes > 10 cmH2O and 37.2% a ΔPes > 15 cmH2O.
CONCLUSIONS: Recurrent neural network model appears excellent to identify airway pressure deformation due to flow starvation. It could be used as a real-time, 24-h bedside monitoring tool to minimize unrecognized periods of inappropriate patient-ventilator interaction.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:28 |
---|---|
Enthalten in: |
Critical care (London, England) - 28(2024), 1 vom: 14. März, Seite 75 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
de Haro, Candelaria [VerfasserIn] |
---|
Links: |
---|
Anmerkungen: |
Date Completed 18.03.2024 Date Revised 05.04.2024 published: Electronic Citation Status MEDLINE |
---|
doi: |
10.1186/s13054-024-04845-y |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM369759583 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM369759583 | ||
003 | DE-627 | ||
005 | 20240405233832.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240315s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1186/s13054-024-04845-y |2 doi | |
028 | 5 | 2 | |a pubmed24n1366.xml |
035 | |a (DE-627)NLM369759583 | ||
035 | |a (NLM)38486268 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a de Haro, Candelaria |e verfasserin |4 aut | |
245 | 1 | 0 | |a Flow starvation during square-flow assisted ventilation detected by supervised deep learning techniques |
264 | 1 | |c 2024 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 18.03.2024 | ||
500 | |a Date Revised 05.04.2024 | ||
500 | |a published: Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a © 2024. The Author(s). | ||
520 | |a BACKGROUND: Flow starvation is a type of patient-ventilator asynchrony that occurs when gas delivery does not fully meet the patients' ventilatory demand due to an insufficient airflow and/or a high inspiratory effort, and it is usually identified by visual inspection of airway pressure waveform. Clinical diagnosis is cumbersome and prone to underdiagnosis, being an opportunity for artificial intelligence. Our objective is to develop a supervised artificial intelligence algorithm for identifying airway pressure deformation during square-flow assisted ventilation and patient-triggered breaths | ||
520 | |a METHODS: Multicenter, observational study. Adult critically ill patients under mechanical ventilation > 24 h on square-flow assisted ventilation were included. As the reference, 5 intensive care experts classified airway pressure deformation severity. Convolutional neural network and recurrent neural network models were trained and evaluated using accuracy, precision, recall and F1 score. In a subgroup of patients with esophageal pressure measurement (ΔPes), we analyzed the association between the intensity of the inspiratory effort and the airway pressure deformation | ||
520 | |a RESULTS: 6428 breaths from 28 patients were analyzed, 42% were classified as having normal-mild, 23% moderate, and 34% severe airway pressure deformation. The accuracy of recurrent neural network algorithm and convolutional neural network were 87.9% [87.6-88.3], and 86.8% [86.6-87.4], respectively. Double triggering appeared in 8.8% of breaths, always in the presence of severe airway pressure deformation. The subgroup analysis demonstrated that 74.4% of breaths classified as severe airway pressure deformation had a ΔPes > 10 cmH2O and 37.2% a ΔPes > 15 cmH2O | ||
520 | |a CONCLUSIONS: Recurrent neural network model appears excellent to identify airway pressure deformation due to flow starvation. It could be used as a real-time, 24-h bedside monitoring tool to minimize unrecognized periods of inappropriate patient-ventilator interaction | ||
650 | 4 | |a Observational Study | |
650 | 4 | |a Multicenter Study | |
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, Non-U.S. Gov't | |
650 | 4 | |a Airway pressure deformation | |
650 | 4 | |a Artificial intelligence algorithms | |
650 | 4 | |a Asynchronies | |
650 | 4 | |a Flow starvation | |
650 | 4 | |a Patient–ventilator interaction | |
700 | 1 | |a Santos-Pulpón, Verónica |e verfasserin |4 aut | |
700 | 1 | |a Telías, Irene |e verfasserin |4 aut | |
700 | 1 | |a Xifra-Porxas, Alba |e verfasserin |4 aut | |
700 | 1 | |a Subirà, Carles |e verfasserin |4 aut | |
700 | 1 | |a Batlle, Montserrat |e verfasserin |4 aut | |
700 | 1 | |a Fernández, Rafael |e verfasserin |4 aut | |
700 | 1 | |a Murias, Gastón |e verfasserin |4 aut | |
700 | 1 | |a Albaiceta, Guillermo M |e verfasserin |4 aut | |
700 | 1 | |a Fernández-Gonzalo, Sol |e verfasserin |4 aut | |
700 | 1 | |a Godoy-González, Marta |e verfasserin |4 aut | |
700 | 1 | |a Gomà, Gemma |e verfasserin |4 aut | |
700 | 1 | |a Nogales, Sara |e verfasserin |4 aut | |
700 | 1 | |a Roca, Oriol |e verfasserin |4 aut | |
700 | 1 | |a Pham, Tai |e verfasserin |4 aut | |
700 | 1 | |a López-Aguilar, Josefina |e verfasserin |4 aut | |
700 | 1 | |a Magrans, Rudys |e verfasserin |4 aut | |
700 | 1 | |a Brochard, Laurent |e verfasserin |4 aut | |
700 | 1 | |a Blanch, Lluís |e verfasserin |4 aut | |
700 | 1 | |a Sarlabous, Leonardo |e verfasserin |4 aut | |
700 | 0 | |a BEARDS study investigators |e verfasserin |4 aut | |
700 | 1 | |a Brochard, Laurent |e investigator |4 oth | |
700 | 1 | |a Telias, Irene |e investigator |4 oth | |
700 | 1 | |a Damiani, Felipe |e investigator |4 oth | |
700 | 1 | |a Artigas, Ricard |e investigator |4 oth | |
700 | 1 | |a Santis, Cesar |e investigator |4 oth | |
700 | 1 | |a Pham, Tài |e investigator |4 oth | |
700 | 1 | |a Mauri, Tommaso |e investigator |4 oth | |
700 | 1 | |a Spinelli, Elena |e investigator |4 oth | |
700 | 1 | |a Grasselli, Giacomo |e investigator |4 oth | |
700 | 1 | |a Spadaro, Savino |e investigator |4 oth | |
700 | 1 | |a Volta, Carlo Alberto |e investigator |4 oth | |
700 | 1 | |a Mojoli, Francesco |e investigator |4 oth | |
700 | 1 | |a Georgopoulos, Dimitris |e investigator |4 oth | |
700 | 1 | |a Kondili, Eumorfia |e investigator |4 oth | |
700 | 1 | |a Soundoulounaki, Stella |e investigator |4 oth | |
700 | 1 | |a Becher, Tobias |e investigator |4 oth | |
700 | 1 | |a Weiler, Norbert |e investigator |4 oth | |
700 | 1 | |a Schaedler, Dirk |e investigator |4 oth | |
700 | 1 | |a Roca, Oriol |e investigator |4 oth | |
700 | 1 | |a Santafe, Manel |e investigator |4 oth | |
700 | 1 | |a Mancebo, Jordi |e investigator |4 oth | |
700 | 1 | |a Rodríguez, Nuria |e investigator |4 oth | |
700 | 1 | |a Heunks, Leo |e investigator |4 oth | |
700 | 1 | |a de Vries, Heder |e investigator |4 oth | |
700 | 1 | |a Chen, Chang-Wen |e investigator |4 oth | |
700 | 1 | |a Zhou, Jian-Xin |e investigator |4 oth | |
700 | 1 | |a Chen, Guang-Qiang |e investigator |4 oth | |
700 | 1 | |a Rit-Tayamai, Nuttapol |e investigator |4 oth | |
700 | 1 | |a Tiribelli, Norberto |e investigator |4 oth | |
700 | 1 | |a Fredes, Sebastian |e investigator |4 oth | |
700 | 1 | |a Artigas, Ricard Mellado |e investigator |4 oth | |
700 | 1 | |a Ortolá, Carlos Ferrando |e investigator |4 oth | |
700 | 1 | |a Beloncle, François |e investigator |4 oth | |
700 | 1 | |a Mercat, Alain |e investigator |4 oth | |
700 | 1 | |a Arnal, Jean-Michel |e investigator |4 oth | |
700 | 1 | |a Diehl, Jean-Luc |e investigator |4 oth | |
700 | 1 | |a Demoule, Alexandre |e investigator |4 oth | |
700 | 1 | |a Dres, Martin |e investigator |4 oth | |
700 | 1 | |a Fossé, Quentin |e investigator |4 oth | |
700 | 1 | |a Jochmans, Sébastien |e investigator |4 oth | |
700 | 1 | |a Chelly, Jonathan |e investigator |4 oth | |
700 | 1 | |a Terzi, Nicolas |e investigator |4 oth | |
700 | 1 | |a Guérin, Claude |e investigator |4 oth | |
700 | 1 | |a Kassis, E Baedorf |e investigator |4 oth | |
700 | 1 | |a Beitler, Jeremy |e investigator |4 oth | |
700 | 1 | |a Chiumello, Davide |e investigator |4 oth | |
700 | 1 | |a Bol-Giaghi, Erica Ferrari Luca |e investigator |4 oth | |
700 | 1 | |a Thille, Arnaud W |e investigator |4 oth | |
700 | 1 | |a Coudroy, Rémi |e investigator |4 oth | |
700 | 1 | |a Papazian, Laurent |e investigator |4 oth | |
773 | 0 | 8 | |i Enthalten in |t Critical care (London, England) |d 1997 |g 28(2024), 1 vom: 14. März, Seite 75 |w (DE-627)NLM097399787 |x 1466-609X |7 nnns |
773 | 1 | 8 | |g volume:28 |g year:2024 |g number:1 |g day:14 |g month:03 |g pages:75 |
856 | 4 | 0 | |u http://dx.doi.org/10.1186/s13054-024-04845-y |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 28 |j 2024 |e 1 |b 14 |c 03 |h 75 |