Search

Sepsis is one of the most frequent causes of death in Intensive Care Units, and its prognosis greatly depend on timeliness of diagnosis. MIMIC-III database is a frequent source of data for developing method for automatic sepsis detection. However, the heterogeneity of data jeopardize the feasibility of the task. In this work we propose a selection strategy for generating high quality data suitable for training a sepsis detection system based on the utilization of only plethysmographic data. Clinical relevance A system for detecting sepsis based only on PPG may be potentially at virtually no cost in any case clinicians suspect the possibility of developing sepsis.

Purpose: Sepsis is a life-threatening organ dysfunction. It is caused by a dysregulated immune response to an infection and is one of the leading causes of death in the intensive care unit (ICU). Early detection and treatment of sepsis can increase the survival rate of patients. The use of devices such as the photoplethysmograph could allow the early evaluation in addition to continuous monitoring of septic patients. The aim of this study was to verify the possibility of detecting sepsis in patients from whom the photoplethysmographic signal was acquired via a pulse oximeter. In this work, we developed a deep learning-based model for sepsis identification. The model takes a single input, the photoplethysmographic signal acquired by pulse oximeter, and performs a binary classification between septic and nonseptic samples. To develop the method, we used MIMIC-III database, which contains data from ICU patients. Specifically, the selected dataset includes 85 septic subjects and 101 control subjects. The PPG signals acquired from these patients were segmented, processed and used as input for the developed model with the aim of identifying sepsis. The proposed method achieved an accuracy of 76.37% with a sensitivity of 70.95% and a specificity of 81.04% on the test set. As regards the ROC curve, the Area Under Curve reached a value of 0.842. The results of this study indicate how the plethysmographic signal can be used as a warning sign for the early detection of sepsis with the aim of reducing the time for diagnosis and therapeutic intervention. Furthermore, the proposed method is suitable for integration in continuous patient monitoring.

Background: Emerging evidence suggests that specific (poly)phenols may constitute new preventative strategies to counteract cell oxidative stress and myocardial tissue inflammation, which have a key role in the patho-physiology of diabetic cardiomyopathy. In a rat model of early diabetes, we evaluated whether in vivo administration of urolithin A (UA) or urolithin B (UB), the main gut microbiota phenolic metabolites of ellagitannin-rich foods, can reduce diabetes-induced microenvironmental changes in myocardial tissue, preventing cardiac functional impairment. Methods: Adult Wistar rats with streptozotocin-induced type-1 diabetes (n = 29) were studied in comparison with 10 control animals. Diabetic rats were either untreated (n = 9) or subjected to daily i.p. injection of UA (n = 10) or UB (n = 10). After 3 weeks of hyperglycaemia, hemodynamics, cardiomyocyte contractile properties and calcium transients were measured to assess cardiac performance. The myocardial expression of the pro-inflammatory cytokine fractalkine and proteins involved in calcium dynamics (sarcoplasmic reticulum calcium ATPase, phospholamban and phosphorylated phospholamban) were evaluated by immunoblotting. Plasma, urine and tissue distribution of UA, UB and their phase II metabolites were determined. Results: In vivo urolithin treatment reduced by approximately 30% the myocardial expression of the pro-inflammatory cytokine fractalkine, preventing the early inflammatory response of cardiac cells to hyperglycaemia. The improvement in myocardial microenvironment had a functional counterpart, as documented by the increase in the maximal rate of ventricular pressure rise compared to diabetic group (+18% and +31% in UA and UB treated rats, respectively), and the parallel reduction in the isovolumic contraction time (-12%). In line with hemodynamic data, both urolithins induced a recovery of cardiomyocyte contractility and calcium dynamics, leading to a higher re-lengthening rate (+21%, on average)