Symbolic dynamics to discriminate healthy and ischaemic dilated cardiomyopathy populations: an application to the variability of heart period and QT interval

Analyzing Electronic Medical Records to Predict Risk of DIT (Death, Intubation, or Transfer to ICU) in Pediatric Respiratory Failure or Related Conditions

Large volumes of data are generated in hospital settings, including clinical and physiological data generated during the course of patient care. Our goal, as proof of concept, was to identify early clinical factors or traits useful for predicting the outcome, of death, intubation, or transfer to ICU, for children with pediatric respiratory failure. We implemented both supervised and unsupervised methods to extend our understanding on statistical relationships in clinical and physiological data. As a supervised learning method, we use binary logistic regression to predict the risk of developing DIT outcome. Next, we implemented unsupervised k-means algorithm on principal components of clinical and physiological data to further explore the contribution of clinical and physiological data on developing DIT outcome. Our results show that early signals of DIT can be detected in physiological data, and two risk factors, blood pressure and oxygen level, are the most important determinant of developing DIT.

Cardiovascular coupling during graded postural challenge: comparison between linear tools and joint symbolic analysis

Background

A joint symbolic analysis (JSA) is applied to assess the strength of the cardiovascular coupling from spontaneous beat-to-beat variability of the heart period (HP) and the systolic arterial pressure (SAP) during an experimental protocol inducing a gradual baroreflex unloading evoked by postural change (i.e. graded head-up tilt).

Method:

The adopted JSA can quantify the degree of association between the HP and SAP variabilities as a function of the time scale of the HP and SAP patterns. Traditional linear tools assessing the HP-SAP coupling strength, such as squared correlation coefficient, squared coherence function, and percentage of baroreflex sequences, were computed as well for comparison.

Results:

We found that: i) JSA indicated that the strength of the cardiovascular coupling at slow temporal scales gradually increased with the magnitude of the orthostatic challenge, while that at fast temporal scales gradually decreased; ii) the squared correlation coefficient and percentage of baroreflex sequences did not detect this behavior; iii) even though squared coherence function could measure the magnitude of the HP-SAP coupling as a function of the time scale, it was less powerful than JSA owing to the larger dispersion of the frequency domain indexes.

Conclusion:

Due to its peculiar features and high statistical power, JSA deserves applications to pathological groups in which the link between HP and SAP variabilities is lost or decreased due to the overall depression or impairment of the cardiovascular control.