Multi-organ spatiotemporal information aware model for sepsis mortality prediction.

Background: Sepsis is a syndrome involving multi-organ dysfunction, and the mortality in sepsis patients correlates with the number of lesioned organs. Precise prognosis models play a pivotal role in enabling healthcare practitioners to administer timely and accurate interventions for sepsis, thereby augmenting patient outcomes. Nevertheless, the majority of available models consider the overall physiological attributes of patients, overlooking the asynchronous spatiotemporal interactions among multiple organ systems.

Reinforcement Learning Model for Managing Noninvasive Ventilation Switching Policy.

Noninvasive ventilation (NIV) has been recognized as a first-line treatment for respiratory failure in patients with chronic obstructive pulmonary disease (COPD) and hypercapnia respiratory failure, which can reduce mortality and burden of intubation. However, during the long-term NIV process, failure to respond to NIV may cause overtreatment or delayed intubation, which is associated with increased mortality or costs. Optimal strategies for switching regime in the course of NIV treatment remain to be explored.

Identification of novel biomarkers for sepsis diagnosis via serum proteomic analysis using iTRAQ-2D-LC-MS/MS.

Background: Sepsis is a common cause of morbidity and mortality in the ICU patients. Early diagnosis and appropriate patient management is the key to improve the patient survival and to limit disabilities in sepsis patients. This study was aimed to find new diagnostic biomarkers of sepsis.

Development of Novel Fractal Method for Characterizing the Distribution of Blood Flow in Multi-Scale Vascular Tree.

Blood perfusion is an important index for the function of the cardiovascular system and it can be indicated by the blood flow distribution in the vascular tree. As the blood flow in a vascular tree varies in a large range of scales and fractal analysis owns the ability to describe multi-scale properties, it is reasonable to apply fractal analysis to depict the blood flow distribution. The objective of this study is to establish fractal methods for analyzing the blood flow distribution which can be applied to real vascular trees.

Dynamic prediction of late noninvasive ventilation failure in intensive care unit using a time adaptive machine model.

Background: Noninvasive ventilation (NIV) failure is strongly associated with poor prognosis. Nowadays, plenty of mature studies have been proposed to predict early NIV failure (within 48 hours of NIV), however, the prediction for late NIV failure (after 48 hours of NIV) lacks sufficient research. Late NIV failure delays intubation resulting in the increasing mortality of the patients.

Macrophages enhance lipopolysaccharide induced apoptosis via Ang1 and NF-κB pathways in human umbilical vein endothelial cells.

Lipopolysaccharide (LPS) could induce apoptosis and dysfunction of endothelial cells. We aimed to reveal the effects of macrophages on cell proliferation and apoptosis in LPS induced human umbilical vein endothelial cells (HUVECs). THP-1 derived macrophages and HUVECs were co-cultured in the presence of LPS.

An adaptive fractal model for sublingual microcirculation.

The hemodynamic conditions and partial pressure of oxygen in microcirculation generally indicate the status of tissue perfusion, which provides essential information for the assessment and treatment of critical diseases such as sepsis. The human tongue is known to have abundant microcirculation and is an ideal window to observe the microcirculation. At present, the monitoring of sublingual microcirculation is mostly achieved using handheld vital microscopy (HVM).

[Prognostic model of small sample critical diseases based on transfer learning].

Aiming at the problem that the small samples of critical disease in clinic may lead to prognostic models with poor performance of overfitting, large prediction error and instability, the long short-term memory transferring algorithm (transLSTM) was proposed. Based on the idea of transfer learning, the algorithm leverages the correlation between diseases to transfer information of different disease prognostic models, constructs the effictive model of target disease of small samples with the aid of large data of related diseases, hence improves the prediction performance and reduces the requirement for target training sample quantity. The transLSTM algorithm firstly uses the related disease samples to pretrain partial model parameters, and then further adjusts the whole network with the target training samples.

A Long Short-Term Memory Ensemble Approach for Improving the Outcome Prediction in Intensive Care Unit.

In intensive care unit (ICU), it is essential to predict the mortality of patients and mathematical models aid in improving the prognosis accuracy. Recently, recurrent neural network (RNN), especially long short-term memory (LSTM) network, showed advantages in sequential modeling and was promising for clinical prediction. However, ICU data are highly complex due to the diverse patterns of diseases; therefore, instead of single LSTM model, an ensemble algorithm of LSTM (eLSTM) is proposed, utilizing the superiority of the ensemble framework to handle the diversity of clinical data.

Diagnostic efficacy of serum procalcitonin, C-reactive protein concentration and clinical pulmonary infection score in Ventilator-Associated Pneumonia.

Objective: The aim of this study was to evaluate the diagnostic efficacy of serum procalcitonin (PCT), c-reactive protein (CRP) concentration and clinical pulmonary infection score(CPIS) in ventilator-associated pneumonia(VAP).

Methods: Forty-nine patients who were admitted to the intensive care unit (ICU) of Zhejiang Hospital with suspected VAP were recruited in this study. The serum level of PCT and CRP of all patients were measured and CPIS was calculated at the time of VAP suspected diagnosis.

Dimensionality Reduction in Complex Medical Data: Improved Self-Adaptive Niche Genetic Algorithm.

With the development of medical technology, more and more parameters are produced to describe the human physiological condition, forming high-dimensional clinical datasets. In clinical analysis, data are commonly utilized to establish mathematical models and carry out classification. High-dimensional clinical data will increase the complexity of classification, which is often utilized in the models, and thus reduce efficiency.

[The effects of early goal-directed therapy on mortality rate in patients with severe sepsis and septic shock: a systematic literature review and Meta-analysis].

Objective: To investigate whether early goal-directed therapy (EGDT) could lower the mortality rate in patients with severe sepsis and septic shock.

Methods: Articles with items sepsis, severe sepsis, septic shock, EGDT were retrieved from MEDLINE, EMBASE, Cochrane, Wanfang Data and CNKI. Inclusion criteria included randomized controlled trial, subjects concerning patients with severe sepsis or septic shock, endpoints with short-term mortality [ in-hospital, intensive care unit (ICU) or 28-day] and long-term mortality (60-day or 90-day).

[Efficacies of fluid resuscitation as guided by lactate clearance rate and central venous oxygen saturation in patients with septic shock].

Objective: To estimate the efficacies of fluid resuscitations as guided by lactate clearance rate (LC) and central venous oxygen saturation (ScvO₂) in patients with septic shock.

Methods: 100 patients diagnosed with septic shock from June 2012 to June 2014 in department of critical care medicine of sixteen hospitals were enrolled. They were randomly divided into two groups of study and control (each n = 50).

[The prediction value of noninvasive bioreactance-based passive leg raising test in assessing fluid responsiveness in elderly patients with sepsis].

Objective: To investigate the value of bioreactance-based passive leg raising (PLR) test predicting fluid responsiveness of elderly patients with sepsis.

Methods: This prospective and self-controlled clinical study included 31 elderly patients with sepsis in the Department of Intensive Care Medicine of Zhejiang Hospital. Hemodynamic parameters including cardiac output (CO), stroke volume variation (SVV) were continuously recorded by bioreactance-based device (noninvasive cardiac output monitoring, NICOM) before and after PLR and volume expansion (VE) test.

[Microcirculation characters in the elderly septic patients].

Objective: To explore the changes of sublingual microcirculation in elderly patients with severe sepsis/septic shock.

Methods: Twenty-three patients with sepsis, 10 patients without sepsis and 10 healthy elderly patients were enrolled. Sublingual microcirculation was evaluated by sidestream darkfield (SDF) imaging.

Value of plasma brain natriuretic peptide levels for predicting postoperative atrial fibrillation: a systemic review and meta-analysis.

Background: Blood natriuretic peptide (NP) levels have been reported to be useful for predicting postoperative atrial fibrillation (AF). We aimed to quantitatively synthesize the current evidence of the accuracy of using NP levels in predicting postoperative AF.

Methods And Results: Medline, Embase, and reference lists were searched.

[An evaluation of stroke volume variation as a predictor of fluid responsiveness in mechanically ventilated elderly patients with severe sepsis].

Objective: To evaluate stroke volume variation (SVV) as a predictor of fluid responsiveness in mechanically ventilated (MV) elderly patients with severe sepsis.

Methods: A prospective observation of 31 fluid challenges during fluid resuscitation for treatment of hemodynamic instability in 17 elderly MV patients with severe sepsis was conducted. SVV was measured by pulse indicator continuous cardiac output (PiCCO) system.

[A novel missense mutation, K124N, in the troponin T gene of Chinese populations with hypertrophic cardiomyopathy].

Objective: To study the cardiac troponin T (TNNT2) gene mutation in Chinese patients with hypertrophic cardiomyopathy (HCM) and to analyze the correlation between the genotype and phenotype.

Methods: Specimens of peripheral blood were collected from 71 unrelated Chinese probands with HCM, aged 40 +/- 18. The genome DNA was extracted.