Journal of clinical monitoring and computing
-
J Clin Monit Comput · Feb 2023
Randomized Controlled TrialPrediction of acute postoperative pain based on intraoperative nociception level (NOL) index values: the impact of machine learning-based analysis.
The relationship between intraoperative nociception and acute postoperative pain is still not well established. The nociception level (NOL) Index (Medasense, Ramat Gan, Israel) uses a multiparametric approach to provide a 0-100 nociception score. The objective of the ancillary analysis of the NOLGYN study was to evaluate the ability of a machine-learning aglorithm to predict moderate to severe acute postoperative pain based on intraoperative NOL values. ⋯ Our results, even if limited by the small number of patients, suggest that acute postoperative pain is better predicted by a multivariate machine-learning algorithm rather than individual intraoperative nociception variables. Further larger multicentric trials are highly recommended to better understand the relationship between intraoperative nociception and acute postoperative pain. Trial registration Registered on ClinicalTrials.gov in October 2018 (NCT03776838).
-
J Clin Monit Comput · Feb 2023
Randomized Controlled TrialPerformance of the bispectral index and electroencephalograph derived parameters of anesthetic depth during emergence from xenon and sevoflurane anesthesia.
Many processed EEG monitors (pEEG) are unreliable when non-GABAergic anesthetic agents are used. The primary aim of the study was to compare the response of the Bispectral Index (BIS) during emergence from anesthesia maintained by xenon and sevoflurane. To better understand the variation in response of pEEG to these agents, we also compared several EEG derived parameters relevant to pEEG monitoring during emergence. Twenty-four participants scheduled for lithotripsy were randomized to receive xenon or sevoflurane anesthesia. ⋯ The spectral edge frequency and composite cortical state parameters increased significantly in both groups during emergence. The BIS index is lower at equivalent stages of behavioural response during emergence from xenon anesthesia when compared to sevoflurane anesthesia, most likely due to differences in how these two agents influence the relative beta ratio. The spectral edge frequency and composite cortical state might better reflect emergence from xenon anaesthesia. Clinical trial number and registry Australia New Zealand Clinical Trials Registry Number: ACTRN12618000916246.
-
J Clin Monit Comput · Feb 2023
Quantification of respiratory sounds by a continuous monitoring system can be used to predict complications after extubation: a pilot study.
To show that quantification of abnormal respiratory sounds by our developed device is useful for predicting respiratory failure and airway problems after extubation. A respiratory sound monitoring system was used to collect respiratory sounds in patients undergoing extubation. The recorded respiratory sounds were subsequently analyzed. ⋯ For bilateral lateral thoracic sounds, the QV of fine crackles was significantly higher in the outcome group vs the non-outcome group. Cervical inspiratory sounds volume (average of five breaths) immediately after extubation was significantly louder in the outcome group vs non-outcome group (63.3 dB vs 54.3 dB, respectively; p < 0.001). Quantification of abnormal respiratory sounds and respiratory volume may predict respiratory failure and airway problems after extubation.
-
J Clin Monit Comput · Feb 2023
Evaluation of machine learning models as decision aids for anesthesiologists.
Machine Learning (ML) models have been developed to predict perioperative clinical parameters. The objective of this study was to determine if ML models can serve as decision aids to improve anesthesiologists' prediction of peak intraoperative glucose values and postoperative opioid requirements. A web-based tool was used to present actual surgical case and patient information to 10 practicing anesthesiologists. ⋯ Feedback questionnaire responses revealed that the anesthesiologist primarily used the ML estimates as reference to modify their clinical judgement. ML models can improve anesthesiologists' estimation of clinical parameters. ML predictions primarily served as reference information that modified an anesthesiologist's clinical estimate.
-
J Clin Monit Comput · Feb 2023
Observational StudyValidation of a non-invasive pressure-time index of the inspiratory muscles in spontaneously breathing newborn infants.
To validate the pressure-time index of the inspiratory muscles as a non-invasive index of inspiratory muscle function in spontaneously breathing infants by comparing it against the gold-standard pressure-time index of the diaphragm. Prospective observational cohort study of consecutive infants breathing unsupported in room air in a tertiary neonatal intensive care unit, studied prior to discharge from neonatal care. The invasive pressure-time index of the diaphragm was calculated using a transdiaphragmatic dual-pressure catheter that measured transdiaphragmatic pressure by subtraction of the oesophageal from the gastric pressure. ⋯ The correlation coefficient for the two indices was 0.509 (p < 0.001). The mean (SD) absolute difference between the pressure-time index of the inspiratory muscles and pressure-time index of the diaphragm was 0.002 (0.021). In convalescent infants, the non-invasive pressure-time index of the inspiratory muscles had a moderate degree of correlation with the invasively derived pressure time index of the diaphragm measured with a transdiaphragmatic catheter.