Journal of clinical monitoring and computing
-
J Clin Monit Comput · Dec 2016
Case ReportsMassive pulmonary embolism leading to cardiac arrest: one pathology, two different ECMO modes to assist patients.
Massive acute pulmonary embolism (MAPE) represents a significant risk for morbidity and mortality. The potential for sudden and fatal deterioration highlights the need for a prompt diagnosis and appropriate intervention. Using two cases reports, we describe two different modes of successful ECMO implantation (VA-ECMO vs. ⋯ A VV-ECMO was successfully implemented, leading to a rapid improvement in both oxygenation and RV function. ECMO can provide lifesaving hemodynamic and respiratory support in critically ill patients with a MAPE who are too unstable to tolerate other interventions or have failed other therapies. An important determinant of success in the use of ECMO for MAPE is the return of adequate RV function, which allows physicians to appropriately identify which type of ECMO to implant.
-
J Clin Monit Comput · Dec 2016
Case ReportsElectroencephalographic evoked pain response is suppressed by spinal cord stimulation in complex regional pain syndrome: a case report.
Pain is a subjective response that limits assessment. The purpose of this case report was to explore how the objectivity of the electroencephalographic response to thermal stimuli would be affected by concurrent spinal cord stimulation. A patient had been implanted with a spinal cord stimulator for the management of complex regional pain syndrome of both hands for 8 years. ⋯ The patient reported a clinically significant reduction in thermal induced pain using the numerical rating scale (71.4 % reduction) with spinal cord stimulator switched on. Analysis of electroencephalogram recordings indicated the occurrence of contact heat evoked potentials (N2-P2) with spinal cord stimulator off, but not with spinal cord stimulator on. This case report suggests that thermal pain can be reduced in complex regional pain syndrome patients with the use of spinal cord stimulation and offers objective validation of the reported outcomes with this treatment.
-
J Clin Monit Comput · Dec 2016
Utility of the bispectral index for assessing natural physiological sleep stages in children and young adults.
Polysomnography (PSG) is the gold standard for the analysis of sleep architecture but is not always available in routine practice, as it is time consuming and cumbersome for patients. Bispectral index (BIS), developed to quantify the deepness of general anesthesia, may be used as a simplified tool to evaluate natural sleep depth. We objectively recorded sleep architecture in young patients using the latest BIS Vista monitor and correlated BIS values with PSG sleep stages in order to determine BIS thresholds. ⋯ BIS threshold that identified stage N3 was <55 (AUC = 0.964, p < 0.001) with an 87 %-sensitivity and a 93 %-specificity. BIS identified stage N3 with satisfactory sensitivity and specificity but is limited by its inability to distinguish REM sleep from wake. Further studies combining BIS with chin electromyogram and/or electrooculogram could be of interest.
-
J Clin Monit Comput · Dec 2016
Adaptive online monitoring for ICU patients by combining just-in-time learning and principal component analysis.
Offline general-type models are widely used for patients' monitoring in intensive care units (ICUs), which are developed by using past collected datasets consisting of thousands of patients. However, these models may fail to adapt to the changing states of ICU patients. Thus, to be more robust and effective, the monitoring models should be adaptable to individual patients. ⋯ The proposed method was compared with the traditional PCA and fast moving-window PCA (Fast MWPCA). The experimental results demonstrated that the fault detection rates respectively increased by 20 % and 47 % compared with PCA and Fast MWPCA. L-PCA is first introduced into ICU patients monitoring and achieves the best monitoring performance in terms of adaptability to changes in patient status and sensitivity for abnormality detection.
-
J Clin Monit Comput · Dec 2016
Real alerts and artifact classification in archived multi-signal vital sign monitoring data: implications for mining big data.
Huge hospital information system databases can be mined for knowledge discovery and decision support, but artifact in stored non-invasive vital sign (VS) high-frequency data streams limits its use. We used machine-learning (ML) algorithms trained on expert-labeled VS data streams to automatically classify VS alerts as real or artifact, thereby "cleaning" such data for future modeling. 634 admissions to a step-down unit had recorded continuous noninvasive VS monitoring data [heart rate (HR), respiratory rate (RR), peripheral arterial oxygen saturation (SpO2) at 1/20 Hz, and noninvasive oscillometric blood pressure (BP)]. Time data were across stability thresholds defined VS event epochs. ⋯ ML algorithms applied to the Block 1 training/cross-validation set (tenfold cross-validation) gave area under the curve (AUC) scores of 0.97 RR, 0.91 BP and 0.76 SpO2. Performance when applied to Block 2 test data was AUC 0.94 RR, 0.84 BP and 0.72 SpO2. ML-defined algorithms applied to archived multi-signal continuous VS monitoring data allowed accurate automated classification of VS alerts as real or artifact, and could support data mining for future model building.