Journal of clinical monitoring and computing
-
J Clin Monit Comput · Mar 2024
Estimation of the transpulmonary pressure from the central venous pressure in mechanically ventilated patients.
Transpulmonary pressure (PL) calculation requires esophageal pressure (PES) as a surrogate of pleural pressure (Ppl), but its calibration is a cumbersome technique. Central venous pressure (CVP) swings may reflect tidal variations in Ppl and could be used instead of PES, but the interpretation of CVP waveforms could be difficult due to superposition of heartbeat-induced pressure changes. Thus, we developed a digital filter able to remove the cardiac noise to obtain a filtered CVP (f-CVP). ⋯ Both PLf-CVP and PLCVP correlated well with PLPES (r = 0.98, p < 0.001 vs. r = 0.94, p < 0.001), again with a lower bias in Bland Altman analysis in favor of PLf-CVP (0.15, LoA - 0.95, 1.26 cmH2O vs. 0.80, LoA - 1.51, 3.12, cmH2O). PLf-CVP discriminated high PL value with an area under the receiver operating characteristic curve 0.99 (standard deviation, SD, 0.02) (AUC difference = 0.01 [-0.024; 0.05], p = 0.48). In mechanically ventilated patients with acute respiratory failure, the digital filtered CVP estimated ΔPES and PL obtained from digital filtered CVP represented a reliable value of standard PL measured with the esophageal method and could identify patients with non-protective ventilation settings.
-
J Clin Monit Comput · Mar 2024
Early prediction of ventricular peritoneal shunt dependency in aneurysmal subarachnoid haemorrhage patients by recurrent neural network-based machine learning using routine intensive care unit data.
Aneurysmal subarachnoid haemorrhage (aSAH) can lead to complications such as acute hydrocephalic congestion. Treatment of this acute condition often includes establishing an external ventricular drainage (EVD). However, chronic hydrocephalus develops in some patients, who then require placement of a permanent ventriculoperitoneal (VP) shunt. ⋯ At that point, the accuracy of the prediction was 76% (CI: 75.98-83.09%), with a sensitivity of 85% (CI: 83-88%) and a specificity of 74% (CI: 71-78%). RNN-based machine learning has the potential to predict VP shunt dependency on Day 4 after ictus in aSAH patients using routine data collected in the ICU. The use of machine learning may allow early identification of patients with specific therapeutic needs and accelerate the execution of required procedures.
-
J Clin Monit Comput · Mar 2024
Visual lung ultrasound protocol (VLUP) in acute respiratory failure: description and application in clinical cases.
Lung ultrasound (LUS) is widely used as a diagnostic and monitoring tool in critically ill patients. Lung ultrasound score (LUSS) based on the examination of twelve thoracic regions has been extensively validated for pulmonary assessment. However, it has revealed significant limitations: when applied to heterogeneous lung diseases with intermediate LUSS pattern (LUSS 1 and 2), for instance, intra-observer consistency is relatively low. ⋯ VLUP enables a quick estimation of the quantitative-LUSS (qLUSS) as the percentage of pleura occupied by artifacts, more suitable than LUSS in inhomogeneous diseases. VLUP is designed as a standardized, point-of-care lung aeration assessment and monitoring tool. The purpose of the paper is to illustrate this new technique and to describe its applications.
-
J Clin Monit Comput · Mar 2024
Electronic health record data is unable to effectively characterize measurement error from pulse oximetry: a simulation study.
Large data sets from electronic health records (EHR) have been used in journal articles to demonstrate race-based imprecision in pulse oximetry (SpO2) measurements. These articles do not appear to recognize the impact of the variability of the SpO2 values with respect to time ("deviation time"). This manuscript seeks to demonstrate that due to this variability, EHR data should not be used to quantify SpO2 error. Using the MIMIC-IV Waveform dataset, SpO2 values are sampled from 198 patients admitted to an intensive care unit and used as reference samples. ⋯ Each analysis was repeated to evaluate whether the measurement errors were affected by increasing the deviation time. All error values increased linearly with respect to the logarithm of the time deviation. At 10 min, the ARMS error increased from a baseline of 2% to over 4%. EHR data cannot be reliably used to quantify SpO2 error. Caution should be used in interpreting prior manuscripts that rely on EHR data.