Search

Septic Shock is a critical pathological state that affects patients entering the intensive care unit (ICU). Many studies have been directed to characterize and predict the onset of the septic shock, both in ICU and in the Emergency Department employing data extracted from the Electronic Health Records. Recently, machine learning algorithms have been successfully employed to help characterize septic shock in a more objective and automatic fashion. Only a few of these studies employ information contained in the continuously recorded vital signs such as electrocardiogram and arterial blood pressure. In particular, we have devised a novel feature estimation procedure able to consider instantaneous dynamics related to cardiovascular control. This work aims at developing a short-term prediction algorithm for identifying patients experiencing septic shock among a population of 100 septic patients extracted from the MIMIC-III clinical and waveform database. Among all the results obtained from several trained machine learning models, the best performance reached an AUC on the test set equal to 0.93 (Accuracy=0.85, Sensitivity=0.89 and Specificity=0.82).

Although the literature demonstrates that cardiac autonomic control (CAC) might be impaired in patients with chronic pulmonary diseases, the interplay between CAC and disease severity in end-stage lung disease has not been studied yet. We investigated the effects of end-stage lung disease on CAC through the analysis of heart rate variability (HRV) among patients awaiting lung transplantation. Forty-nine patients on the waiting list for lung transplantation (LTx; 19 men, age 38 ± 15 years) and 49 healthy non-smoking controls (HC; 22 men, age 40 ± 16 years) were enrolled in a case-control study at Policlinico Hospital in Milan, Italy. LTx patients were divided into two groups, according to disease severity evaluated by the Lung Allocation Score (LAS). To assess CAC, electrocardiogram (ECG) and respiration were recorded at rest for 10 min in supine position and for 10 min during active standing. Spectral analysis identified low and high frequencies (LF, sympathetic, and HF, vagal). Symbolic analysis identified three patterns, i.e., 0V% (sympathetic) and 2UV% and 2LV% (vagal). Compared to HCs, LTx patients showed higher markers of sympathetic modulation and lower markers of vagal modulation. However, more severely affected LTx patients, compared to less severely affected ones, showed an autonomic profile characterized by loss of sympathetic modulation and predominant vagal modulation. This pattern can be due to a loss of sympathetic rhythmic oscillation and a subsequent prevalent respiratory modulation of heart rate in severely affected patients.