Computational Methods for Identifying Hypertrophic Cardiomyopathy using 12-lead ECG

Hypertrophic cardiomyopathy (HCM) is a cardiovascular disease where the heart muscle is partially thickened and blood flow is - potentially fatally - obstructed. It is one of the leading causes of sudden cardiac death in young people. Electrocardiography (ECG) and Echocardiography (Echo) are the standard tests for identifying HCM and other cardiac abnormalities. The American Heart Association has recommended using a pre-participation questionnaire for young athletes instead of ECG or Echo tests due to considerations of cost and time involved in interpreting the results of these tests by an expert cardiologist. Initially we set out to develop a classifier for automated prediction of young athletes’ heart conditions based on the answers to the questionnaire. Classification results and further in-depth analysis using computational and statistical methods indicated significant shortcomings of the questionnaire in predicting cardiac abnormalities. Automated methods for analyzing ECG signals can help reduce cost and save time in the pre-participation screening process by detecting HCM and other cardiac abnormalities. Therefore, the main goal of this dissertation work is to identify HCM through computational analysis of 12-lead ECG. ECG signals recorded on one or two leads have been analyzed in the past for classifying individual heartbeats into different types of arrhythmia as annotated primarily in the MIT-BIH database. In contrast, we classify complete sequences of 12-lead ECGs to assign patients into two groups: HCM vs. non-HCM. The challenges and issues we address include missing ECG waves in one or more leads and the dimensionality of a large feature-set. We address these by proposing imputation and feature-selection methods. We develop heartbeat-classifiers by employing Random Forests and Support Vector Machines, and propose a method to classify full 12-lead ECGs based on the proportion of heartbeats classified as HCM. The results from our experiments show that the classifiers developed using our methods perform well in identifying HCM. Thus the two contributions of this thesis are the utilization of computational and statistical methods for discovering shortcomings in a current screening procedure and the development of methods to identify HCM through computational analysis of 12-lead ECG signals.

Cardiopulmonary adaptation to short-term high altitude exposure in adult Fontan patients

OBJECTIVE High altitude-related hypoxia induces pulmonary vasoconstriction. In Fontan patients without a contractile subpulmonary ventricle, an increase in pulmonary artery pressure is expected to decrease circulatory output and reduce exercise capacity. This study investigates the direct effects of short-term high altitude exposure on pulmonary blood flow (PBF) and exercise capacity in Fontan patients. METHODS 16 adult Fontan patients (mean age 28±7 years, 56% female) and 14 matched controls underwent cardiopulmonary exercise testing with measurement of PBF with a gas rebreathing system at 540 m (low altitude) and at 3454 m (high altitude) within 12 weeks. RESULTS PBF at rest and at exercise was higher in controls than in Fontan patients, both at low and high altitude. PBF increased twofold in Fontan patients and 2.8-fold in the control group during submaximal exercise, with no significant difference between low and high altitude (p=0.290). A reduction in peak oxygen uptake at high compared with low altitude was observed in Fontan patients (22.8±5.1 and 20.5±3.8 mL/min/kg, p<0.001) and the control group (35.0±7.4 and 29.1±6.5 mL/min/kg, p<0.001). The reduction in exercise capacity was less pronounced in Fontan patients compared with controls (9±12% vs 17±8%, p=0.005). No major adverse clinical event was observed. CONCLUSIONS Short-term high altitude exposure has no negative impact on PBF and exercise capacity in Fontan patients when compared with controls, and was clinically well tolerated. TRIAL REGISTRATION NUMBER NCT02237274: Results.

Is ultrasound perfusion imaging capable of detecting mismatch? A proof-of-concept study in acute stroke patients.

In this study, we compared contrast-enhanced ultrasound perfusion imaging with magnetic resonance perfusion-weighted imaging or perfusion computed tomography for detecting normo-, hypo-, and nonperfused brain areas in acute middle cerebral artery stroke. We performed high mechanical index contrast-enhanced ultrasound perfusion imaging in 30 patients. Time-to-peak intensity of 10 ischemic regions of interests was compared to four standardized nonischemic regions of interests of the same patient. A time-to-peak >3 s (ultrasound perfusion imaging) or >4 s (perfusion computed tomography and magnetic resonance perfusion) defined hypoperfusion. In 16 patients, 98 of 160 ultrasound perfusion imaging regions of interests of the ischemic hemisphere were classified as normal, and 52 as hypoperfused or nonperfused. Ten regions of interests were excluded due to artifacts. There was a significant correlation of the ultrasound perfusion imaging and magnetic resonance perfusion or perfusion computed tomography (Pearson`s chi-squared test 79.119, p < 0.001) (OR 0.1065, 95% CI 0.06-0.18). No perfusion in ultrasound perfusion imaging (18 regions of interests) correlated highly with diffusion restriction on magnetic resonance imaging (Pearson's chi-squared test 42.307, p < 0.001). Analysis of receiver operating characteristics proved a high sensitivity of ultrasound perfusion imaging in the diagnosis of hypoperfused area under the curve, (AUC = 0.917; p < 0.001) and nonperfused (AUC = 0.830; p < 0.001) tissue in comparison with perfusion computed tomography and magnetic resonance perfusion. We present a proof of concept in determining normo-, hypo-, and nonperfused tissue in acute stroke by advanced contrast-enhanced ultrasound perfusion imaging.

Dysfunction of respiratory muscles in critically ill patients on the intensive care unit.

Muscular weakness and muscle wasting may often be observed in critically ill patients on intensive care units (ICUs) and may present as failure to wean from mechanical ventilation. Importantly, mounting data demonstrate that mechanical ventilation itself may induce progressive dysfunction of the main respiratory muscle, i.e. the diaphragm. The respective condition was termed 'ventilator-induced diaphragmatic dysfunction' (VIDD) and should be distinguished from peripheral muscular weakness as observed in 'ICU-acquired weakness (ICU-AW)'. Interestingly, VIDD and ICU-AW may often be observed in critically ill patients with, e.g. severe sepsis or septic shock, and recent data demonstrate that the pathophysiology of these conditions may overlap. VIDD may mainly be characterized on a histopathological level as disuse muscular atrophy, and data demonstrate increased proteolysis and decreased protein synthesis as important underlying pathomechanisms. However, atrophy alone does not explain the observed loss of muscular force. When, e.g. isolated muscle strips are examined and force is normalized for cross-sectional fibre area, the loss is disproportionally larger than would be expected by atrophy alone. Nevertheless, although the exact molecular pathways for the induction of proteolytic systems remain incompletely understood, data now suggest that VIDD may also be triggered by mechanisms including decreased diaphragmatic blood flow or increased oxidative stress. Here we provide a concise review on the available literature on respiratory muscle weakness and VIDD in the critically ill. Potential underlying pathomechanisms will be discussed before the background of current diagnostic options. Furthermore, we will elucidate and speculate on potential novel future therapeutic avenues.

The measurement of liver circulation by means of the colloid disapperance rate.

Unclassified Health and Biology.

Hypertension in Pagothenia borchgrevinki caused by X-cell disease

Approximately 15% of a population of the cryopelagic nototheniid fish Pagothenia borchgrevinki, found constantly swimming immediately beneath the annual fast ice, in McMudro Sound. Ross Sea, Antarctica, was affected by X-cell gill disease. This disease affected blood flow through the gill lamellae, and this in turn affected oxygen uptake. Exercise caused increases in heart rate and ventral aortic blood pressure. Heart rate increased from 15.1 +/- 1.55 to 23.1 +/- 0.93 beats min(-1) in healthy fish, with a similar increase from 15.1 +/- 1.55 to 23.1 +/- 0.93 beats min(-1) in healthy fish, with a similar increase (to 24.6 +/- 0.26 beats min(-1)) in X-cell-affected animals. In healthy fish, pressures rose with exercise (from 2.72 +/- 0.11 to 3.75 +/- 0.19 kPa) and then rapidly returned to resting levels during recovery. In X-cell fish pressures rose during exercise, but then continued to rise, to reach a high of 4.18 +/- 0.13 kPa, close to the predicted maximum pressure able to be generated by these hearts. Recovery was rapid in healthy fish, but was prolonged in diseased animals. As they are constantly swimming, there is the potential that X-cell-affected fish suffer from chronic hypertension. (C) 2003 The Fisheries Society of the British Isles.