Search

Artifacts in physiological signals acquired during intensive care have the potential to be recognized as critical pathological events and lead to misdiagnosis or mismanagement. Manual artifact removal necessitates significant labor-time intensity and is subject to inter- and intra-observer variability. Various methods have been proposed to automate the task; however, the methods are yet to be validated, possibly due to the diversity of artifact types. Deep belief networks (DBNs) have been shown to be capable of learning generative and discriminative feature extraction models, hence suitable for classifying signals with multiple features. This study proposed a DBN-based model for artifact elimination in pulse waveform signals, which incorporates pulse segmentation, pressure normalization and decision models using DBN, and applied the model to artifact removal in monitoring arterial blood pressure (ABP). When compared with a widely used ABP artifact removal algorithm (signal abnormality index; SAI), the DBN model exhibited significantly higher classification performance (net prediction of optimal DBN = 95.9%, SAI = 84.7%). In particular, DBN exhibited greater sensitivity than SAI for identifying various types of artifacts (motion = 93.6%, biological = 95.4%, cuff inflation = 89.1%, transducer flushing = 97%). The proposed model could significantly enhance the quality of signal analysis, hence may be beneficial for use in continuous patient monitoring in clinical practice.

Adenotonsillectomy is a short surgical procedure under general anaesthesia in children. An ideal muscle relaxant for adenotonsillectomy would create an intense neuromuscular block while having a quick recovery time without postoperative morbidity. We compared the effect of different doses of rocuronium for the tracheal intubation in children under 5% sevoflurane and fentanyl.75 children (aged 3-10 years, ASA I) scheduled for adenotonsillectomy were enrolled. Anaesthesia was induced with propofol 2.5 mg/kg, followed by fentanyl 2 μg/kg. After mask ventilation with 5 vol% sevoflurane in 100% oxygen for 2 min, 2 ml of study drug was administered intravenously, i.e., either normal saline (S Group) or one of two doses (0.15 or 0.3 mg/kg) of rocuronium. We assessed conditions during tracheal intubation and also recorded the surgical condition, the time from discontinuation of sevoflurane to extubation and PAED scale, pain scores in PACU.Rocuronium groups (96% and 100%, respectively; P 0.01) showed statistically superior clinically acceptable intubating conditions than the saline group (72%). The 0.3 mg/kg rocuronium (80%) treatment clearly resulted in excellent intubating conditions compared with the 0.15 mg/kg group (44%; p = 0.028). There was no significant difference in the time to extubation and surgical condition, and in the postoperative measures of emergence delirium, pain, and recovery time among the three groups.A dose of 0.3 mg/kg rocuronium may provide optimal intubating conditions without delayed recovery in 5% sevoflurane anaesthesia with fentanyl in children undergoing adenotonsillectomy.NCT02467595.