Data processing pipeline for cardiogenic shock prediction using machine learning.

Introduction: Recent advances in machine learning provide new possibilities to process and analyse observational patient data to predict patient outcomes. In this paper, we introduce a data processing pipeline for cardiogenic shock (CS) prediction from the MIMIC III database of intensive cardiac care unit patients with acute coronary syndrome. The ability to identify high-risk patients could possibly allow taking pre-emptive measures and thus prevent the development of CS. Methods: We mainly focus on techniques for the imputation of missing data by generating a pipeline for imputation and comparing the performance of various multivariate imputation algorithms, including k-nearest neighbours, two singular value decomposition (SVD)-based methods, and Multiple Imputation by Chained Equations. After imputation, we select the final subjects and variables from the imputed dataset and showcase the performance of the gradient-boosted framework that uses a tree-based classifier for cardiogenic shock prediction. Results: We achieved good classification performance thanks to data cleaning and imputation (cross-validated mean area under the curve 0.805) without hyperparameter optimization. Conclusion: We believe our pre-processing pipeline would prove helpful also for other classification and regression experiments.

Plasmatic apelin shows a promising potential as a screening biomarker for atrial fibrillation.

OBJECTIVES: Purpose of this study was to evaluate properties of apelin, a peptide detectable in peripheral blood, for atrial fibrillation (AF) detection in a diverse population of patients covering a broad spectrum from healthy to polymorbid patients. BACKGROUND: AF is the most common cardiac arrhythmia with constantly increasing incidence and prevalence. Currently available diagnostic tools do not provide sufficient detection rate. Large proportion of patients with AF remains undiagnosed and the possibility of screening at-risk groups would be significantly beneficial. METHODS: We designed this study as a multi-centre retrospective study. Study population included 183 patients. 64 in non-AF and 119 in AF group. RESULTS: Apelin plasma concentration was significantly lower in AF group compared to non-AF group (p < 0.001). Receiver operating characteristic analysis of apelin as a predictor of AF scored area under the curve of 0.79, sensitivity = 0.941 and specificity = 0.578. Multivariate analysis using logistic regression adjusted for age, BMI, apelin, dilated LV, dilated LA, arterial hypertension, and gender showed only apelin and age to be statistically significant contributors for AF. CONCLUSION: Apelin might be a promising biomarker for detecting AF in our study population. These results suggest promising potential of apelin as a screening biomarker for AF (Tab. 2, Fig. 1, Ref. 46). Text in PDF www.elis.sk Keywords: biomarker, apelin, arrhythmia, atrial fibrillation.

Seroprevalence of Bartonella henselae and Bartonella quintana Infection and Impact of Related Risk Factors in People from Eastern Slovakia.

The genus Bartonella is a rapidly expanding group of ubiquitous bacteria that occur mainly in different animal species, but some can also be transmitted to humans. Three species, B. henselae, B. bacilliformis, and B. quintana, are responsible for the majority of human cases. The severity of the clinical symptoms often depends on the immune status of the patient, but others factors such as the species of the pathogen, virulence factors, and bacterial load also can play an important role. As the information on the occurrence of bartonellosis in the human population in Slovakia is absent, the aim of our pilot study was to determine the seroprevalence against B. henselae and B. quintana in the population of people living in Eastern Slovakia, and to identify the impact of related risk factors. Of 536 people included in the study, 126 (23.5%) showed positivity for anti-B. henselae antibodies and 133 (24.8%) against B. quintana. A statistically higher prevalence was confirmed only in the case of B. quintana in women regardless of the risk group. In analyzing the risk factors, we found significant differences between B. henselae seropositive and seronegative groups only in uric acid levels and serum creatinine, both, however, clinically irrelevant. Significant, but clinically irrelevant differences were observed also in alanine aminotransferase (ALT) levels and creatinine in people seropositive to B. quintana.

Association Between Apelin and Atrial Fibrillation in Patients With High Risk of Ischemic Stroke.

Background: Atrial fibrillation (AF) is associated with high risk of stroke preventable by timely initiation of anticoagulation. Currently available screening tools based on ECG are not optimal due to inconvenience and high costs. Aim of this study was to study the diagnostic value of apelin for AF in patients with high risk of stroke. Methods: We designed a multicenter, matched-cohort study. The population consisted of three study groups: a healthy control group (34 patients) and two matched groups of 60 patients with high risk of stroke (AF and non-AF group). Apelin levels were examined from peripheral blood. Results: Apelin was significantly lower in AF group compared to non-AF group (0.694 ± 0.148 vs. 0.975 ± 0.458 ng/ml, p = 0.001) and control group (0.982 ± 0.060 ng/ml, p < 0.001), respectively. Receiver operating characteristic (ROC) analysis of apelin as a predictor of AF scored area under the curve (AUC) of 0.658. Apelin's concentration of 0.969 [ng/ml] had sensitivity = 0.966 and specificity = 0.467. Logistic regression based on manual feature selection showed that only apelin and NT-proBNP were independent predictors of AF. Logistic regression based on selection from bivariate analysis showed that only apelin was an independent predictor of AF. A logistic regression model using repeated stratified K-Fold cross-validation strategy scored an AUC of 0.725 ± 0.131. Conclusions: Our results suggest that apelin might be used to rule out AF in patients with high risk of stroke.