Skip to main content

Advertisement

Table 1 Comparison of some automated methods for patient-ventilator asynchrony detection

From: Patient-ventilator asynchronies during mechanical ventilation: current knowledge and research priorities

 Type of PVAAlgorithmPerformance
Gholami et al. (2018) [69]Cycling asynchrony (premature and delayed cycling)ML: Random forest and k-fold cross validationPressure and airflow signalsN = 11 patients (1377 breaths)Se 89–97%, Sp 93–99%, Kappa index 0.9
ventMAP platformAdams et al. (2017) [70]Double-trigger and breath stackingRule-based algorithmPressure and airflow signalsDerivation cohort, N = 16 patients (5075 breaths); validation cohort, N = 17 patients (4644 breaths)Se 94–96.7%, Sp 92–98%, Acc 92.2–97.7%(on the validation cohort)
NeuroSync indexSinderby et al. (2013) [71]Patient-ventilator interaction classification (asynchronous, dyssynchronous or synchronous)Rule-based timings algorithmEAdi and pressure signalsN = 24 patientsICC 0.95 vs. Colombo et al. (2011) [5]
Better Care® systemBlanch et al. (2012) [37]Ineffective efforts during expirationRule-based combining digital signal processing techniques and ROC curvesAirflow signalCohort 1: N = 8 patients (1024 breaths)Cohort 2: N = 8 patients (9600 breaths) with EAdi signal as referenceSe 91.5%, Sp 91.7%, PPV 80.3%, NPV 96.7%, Kappa index 0.797(vs. the expert’s classification)Se 65.2%, Sp 99.3%, PPV 90.8%, NPV 96.5%, Kappa index 0.739(vs. EAdi signal)
Gutierrez et al. (2011) [72]Index for asynchronous/no asynchronous breathsTime-frequency analysisAirflow signalsN = 110 patientsSe 83%, Sp 83% when index < 43% for AI > 10%
Mulqueeny et al. (2007) [73]Ineffective triggering and double triggeringRule-based and digital signal processing methodsAirflow and pressure signalsN = 20 patients (3343 breaths)Se 91%, Sp 97%
PVI monitorYounes et al. (2007) [74]Ineffective effortsRule-basedEquation of motion from pressure, airflow, and Peso signalsN = 21 patientsSe 79.7%
  1. Abbreviations: ML machine learning, Se sensitivity, Sp specificity, ICC intraclass correlation coefficient, Acc overall accuracy, Peso esophageal pressure, PPV positive predictive value, NPV negative predictive value, ROC receiver operating characteristics, AI asynchrony index according to the definition from Thille et al. [7]