Journal of clinical monitoring and computing
-
J Clin Monit Comput · Aug 2013
Use of genetic programming, logistic regression, and artificial neural nets to predict readmission after coronary artery bypass surgery.
As many as 14 % of patients undergoing coronary artery bypass surgery are readmitted within 30 days. Readmission is usually the result of morbidity and may lead to death. The purpose of this study is to develop and compare statistical and genetic programming models to predict readmission. ⋯ Predictive accuracy of all three techniques fell in the Validation group. However, the accuracy of genetic programming (AU ROC = .654 ± .001) was still trivially but statistically non-significantly better than that of the logistic regression (AU ROC = .644 ± .020, p = .61). Genetic programming and logistic regression provide alternative methods to predict readmission that are similarly accurate.
-
J Clin Monit Comput · Aug 2013
A simple model of the right atrium of the human heart with the sinoatrial and atrioventricular nodes included.
Existing atrial models with detailed anatomical structure and multi-variable cardiac transmembrane current models are too complex to allow to combine an investigation of long time dycal properties of the heart rhythm with the ability to effectively simulate cardiac electrical activity during arrhythmia. Other ways of modeling need to be investigated. Moreover, many state-of-the-art models of the right atrium do not include an atrioventricular node (AVN) and only rarely--the sinoatrial node (SAN). ⋯ Our simulations support the hypothesis that the alternans of the conduction time between the atria and the ventricles in the AV orthodromic reciprocating tachycardia can occur within a single pathway. In the atrial parasystole simulation, we found a mathematical condition which allows for a rough estimation of the location of the parasystolic source within the atrium, both for simplified (planar) and the cylindrical geometry of the atrium. The planar and the cylindrical geometry yielded practically the same results of simulations.
-
J Clin Monit Comput · Aug 2013
The use of heart rate variability for the early detection of treatable complications after aneurysmal subarachnoid hemorrhage.
High-grade aneurysmal subarachnoid hemorrhage patients are monitored in the ICU for up to 21 days, as they are at risk for complications such as vasospasm of cerebral arteries, cardiac arrhythmias and neurogenic stress cardiomyopathy. The diagnosis of these treatable complications is often delayed by the limitations of monitoring capabilities. We applied computational analysis to a cohort of 24 aneurysmal subarachnoid hemorrhage patients, to identify heart rate variability and ECG frequency profiles that may be potential biomarkers of severe vasospasm, reversible cardiomyopathy and death.
-
J Clin Monit Comput · Jun 2013
Randomized Controlled TrialUltrasound-guided radial arterial cannulation: long axis/in-plane versus short axis/out-of-plane approaches?
Arterial cannulation with ultrasound (US) guidance increases the success rate and reduces complications. US-guided vascular access has two main approaches: long axis in-plane (LA-IP) and short axis out-of-plane (SA-OOP) approaches. The purpose of this study was to compare performance time and possible complications between two techniques. ⋯ Posterior wall damage during arterial cannulation were found in 30 patients with SA-OOP Group (56 %) and 11 patients with LA-IP Group (20 %), (p < 0.05). In our study, the use of LA-IP approach during US-guided radial artery cannulation has higher success rate at first insertion. We also found LA-IP approach results in shorter cannulation time and decreased the incidence of complications.