Association between high-density lipoprotein cholesterol and renal function in elderly hypertension: a cross-sectional study in Chinese population

Application of back propagation neural network model optimized by particle swarm algorithm in predicting the risk of hypertension

The structure of a back propagation neural network was optimized by a particle swarm optimization (PSO) algorithm, and a back propagation neural network model based on a PSO algorithm was constructed. By comparison with a general back propagation neural network and logistic regression, the fitting performance and prediction performance of the PSO algorithm is discussed. Furthermore, based on the back propagation neural network optimized by the PSO algorithm, the risk factors related to hypertension were further explored through the mean influence value algorithm to construct a risk prediction model. In the evaluation of the fitting effect, the root mean square error and coefficient of determination of the back propagation neural network based on the PSO algorithm were 0.09 and 0.29, respectively. In the comparison of prediction performance, the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve of the back propagation neural network based on PSO algorithm were 85.38%, 43.90%, 96.66%, and 0.86, respectively. The results showed that the backpropagation neural network optimized by PSO had the best fitting effect and prediction performance. Meanwhile, the mean impact value algorithm could screen out the risk factors related to hypertension and build a disease prediction model, which can provide clues for exploring the pathogenesis of hypertension and preventing hypertension.

Two-year follow-up of patients with septic shock presenting with low HDL: the effect upon acute kidney injury, death and estimated glomerular filtration rate

BACKGROUND

Sepsis is associated with decreased levels of high-density lipoprotein (HDL) cholesterol. HDL has anti-inflammatory properties, and the use of Apo A-I mimetic peptides is associated with renal function improvement in animal models of sepsis. However, it is not known whether decreased HDL level results in impaired renal function in human sepsis. We investigated whether low levels of HDL conferred an increased risk of sepsis-associated acute kidney injury (AKI) or long-term decreased estimated glomerular filtration rate (eGFR) after sepsis.

METHODS

HDL concentration (mg dL^-1 ) was measured in plasma samples from 180 patients with septic shock at admission to the Emergency Department (ED). We divided the patients using median HDL as a cut-off value and assessed the frequency of sepsis-associated AKI and long-term decreased eGFR after sepsis. Univariate and multivariate analyses were performed.

RESULTS

Patients with low HDL had a significantly greater frequency of KDIGO 2 or 3 sepsis-associated AKI [39/90 (43.3%) vs. 12/90 (13.3%), P < 0.001] and decreased long-term eGFR [24/58 (41.4%) vs. 11/57 (19.3%), P = 0.018] compared to those with high HDL. The adjusted OR for sepsis-associated AKI and decreased eGFR after sepsis in the lower HDL group was 2.80 (95% CI 1.08-7.25, P = 0.033) and 5.45 (95% CI 1.57-18.93, P = 0.008), respectively.

CONCLUSION

Low HDL levels during sepsis are associated with increased risk of sepsis-associated AKI, and/or subsequent decreased eGFR. These results suggest that HDL may be involved and/or may be a marker of kidney injury during and after sepsis.