APOE polymorphisms influence longitudinal lipid trends preceding intracerebral hemorrhage

Machine learning-based prediction of cerebral hemorrhage in patients with hemodialysis: A multicenter, retrospective study

Background

Intracerebral hemorrhage (ICH) is one of the most serious complications in patients with chronic kidney disease undergoing long-term hemodialysis. It has high mortality and disability rates and imposes a serious economic burden on the patient's family and society. An early prediction of ICH is essential for timely intervention and improving prognosis. This study aims to build an interpretable machine learning-based model to predict the risk of ICH in patients undergoing hemodialysis.

Methods

The clinical data of 393 patients with end-stage kidney disease undergoing hemodialysis at three different centers between August 2014 and August 2022 were retrospectively analyzed. A total of 70% of the samples were randomly selected as the training set, and the remaining 30% were used as the validation set. Five machine learning (ML) algorithms, namely, support vector machine (SVM), extreme gradient boosting (XGB), complement Naïve Bayes (CNB), K-nearest neighbor (KNN), and logistic regression (LR), were used to develop a model to predict the risk of ICH in patients with uremia undergoing long-term hemodialysis. In addition, the area under the curve (AUC) values were evaluated to compare the performance of each algorithmic model. Global and individual interpretive analyses of the model were performed using importance ranking and Shapley additive explanations (SHAP) in the training set.

Results

A total of 73 patients undergoing hemodialysis developed spontaneous ICH among the 393 patients included in the study. The AUC of SVM, CNB, KNN, LR, and XGB models in the validation dataset were 0.725 (95% CI: 0.610 ~ 0.841), 0.797 (95% CI: 0.690 ~ 0.905), 0.675 (95% CI: 0.560 ~ 0.789), 0.922 (95% CI: 0.862 ~ 0.981), and 0.979 (95% CI: 0.953 ~ 1.000), respectively. Therefore, the XGBoost model had the best performance among the five algorithms. SHAP analysis revealed that the levels of LDL, HDL, CRP, and HGB and pre-hemodialysis blood pressure were the most important factors.

Conclusion

The XGB model developed in this study can efficiently predict the risk of a cerebral hemorrhage in patients with uremia undergoing long-term hemodialysis and can help clinicians to make more individualized and rational clinical decisions. ICH events in patients undergoing maintenance hemodialysis (MHD) are associated with serum LDL, HDL, CRP, HGB, and pre-hemodialysis SBP levels.

Sex Differences in Outcomes After Spontaneous Intracerebral Hemorrhage Among Patients With Low Total Cholesterol Levels

BACKGROUND

Low total cholesterol (TC) levels were shown to be an independent predictor of intracerebral hemorrhagic stroke in previous studies. However, the role of sex in risk and outcome of patients with ICH and low TC levels is unclear. Therefore, the objective of our study was to assess the sex differences in the risk factors and outcomes after spontaneous intracerebral hemorrhage (ICH) in patients with low TC levels in China.

METHODS

This study recruited consecutive patients diagnosed with ICH who were admitted to the Stroke Registry System in Tianjin between May 2005 and May 2018. Patients with low TC levels (defined as TC<200mg/dl) were analyzed in this study. Sex differences in clinical features, risk factors, and outcomes at hospital discharge, 3 months, and 12 months after ICH were evaluated.

RESULTS

Of the 824 patients with low TC levels, 610 men (74%) and 214 women (26%). The mean age at ICH onset was younger in men than in women (60.93±12.54 vs. 64.5±12.28, P<0.001), and men were more likely to have higher educational levels than women. There were higher prevalence rates of hypertension, current smoking status, and alcohol consumption in men. Urinary tract infections were more prevalent in women, and hepatic/renal dysfunctions were more prevalent in men. Women had significantly higher neurological function deficits. With lower Barthel indices (BIs) and higher modified Rankin scale (mRS) scores at admission; but there was no significant difference between men and women in National Institutes of Health Stroke Scale (NIHSS) scores. The study showed that there was no significant difference in mortality and dependency rates at hospital discharge, 3 months, and 12 months after ICH.

CONCLUSIONS

Our study showed that there were no sex differences in clinical outcomes of patients with ICH and low TC levels, which suggests that the effect of low cholesterol as a risk factor for cerebral hemorrhage is the same on patients of different sexs. The possible mechanisms need larger, prospective, multicenter studies to further research.

Low-Density Lipoprotein Cholesterol and Risk of Hemorrhagic Stroke: a Systematic Review and Dose-Response Meta-analysis of Prospective Studies

PURPOSE OF REVIEW

To systematically examine the association between low-density lipoprotein cholesterol (LDL-C) and risk of hemorrhagic stroke.

RECENT FINDINGS

A previous meta-analysis of prospective studies published in 2013 showed that higher concentrations of LDL-C were associated with lower risk of hemorrhagic stroke. Recently, seven large cohort studies were published examining LDL-C and risk of hemorrhagic stroke in different populations. Twelve prospective studies with 476,173 participants and 7587 hemorrhagic stroke cases were included in the current meta-analysis. The results showed that a 10 mg/dL increase in LDL-C was associated with 3% lower risk of hemorrhagic stroke (pooled relative risk [RR] 0.97, 95% confidence interval [CI] 0.95-0.98). The association appeared to be more pronounced in Asians (pooled RR 0.95, 95% CI 0.92-0.98), relative to Caucasians (pooled RR 0.98, 95% CI 0.97-1.00), with a p heterogeneity of 0.05 between two ethnic groups. Further genetic studies and clinical trials with a stricter safety monitoring strategy are warranted to understand the underlying pathogenesis and determine the treatment target of LDL-C range with the lowest risk of hemorrhagic stroke in different population groups.

Low-density lipoprotein cholesterol and risk of intracerebral hemorrhage: A prospective study

OBJECTIVE

To prospectively examine the association between low-density lipoprotein (LDL) cholesterol (LDL-C) concentrations and intracerebral hemorrhage (ICH) risk.

METHODS

The current cohort study included 96,043 participants (mean age 51.3 years) who were free of stroke, myocardial infarction, and cancer at baseline (2006). Serum LDL-C concentrations were assessed in 2006, 2008, 2010, and 2012. Cumulative average LDL-C concentrations were calculated from all available LDL-C data during that period. Incident ICH was confirmed by review of medical records.

RESULTS

We identified 753 incident ICH cases during 9 years of follow-up. The ICH risk was similar among participants with LDL concentrations of 70 to 99 mg/dL and those with LDL-C concentrations ≥100 mg/dL. In contrast, participants with LDL-C concentrations <70 mg/dL had a significantly higher risk of developing ICH than those with LDL-C concentrations of 70 to 99 mg/dL; adjusted hazard ratios were 1.65 (95% confidence interval [CI] 1.32-2.05) for LDL-C concentrations of 50 to 69 mg/dL and 2.69 (95% CI 2.03-3.57) for LDL-C concentrations <50 mg/dL.

CONCLUSIONS

We observed a significant association between lower LDL-C and higher risk of ICH when LDL-C was <70 mg/dL, and the association became nonsignificant when LDL-C ≥70 mg/dL. These data can help determination of the ideal LDL range in patients who are at increased risk of both atherosclerotic disease and hemorrhagic stroke and guide planning of future lipid-lowering studies.

17p12 Influences Hematoma Volume and Outcome in Spontaneous Intracerebral Hemorrhage

BACKGROUND AND PURPOSE

Hematoma volume is an important determinant of clinical outcome in spontaneous intracerebral hemorrhage (ICH). We performed a genome-wide association study (GWAS) of hematoma volume with the aim of identifying novel biological pathways involved in the pathophysiology of primary brain injury in ICH.

METHODS

We conducted a 2-stage (discovery and replication) case-only genome-wide association study in patients with ICH of European ancestry. We utilized the admission head computed tomography to calculate hematoma volume via semiautomated computer-assisted technique. After quality control and imputation, 7 million genetic variants were available for association testing with ICH volume, which was performed separately in lobar and nonlobar ICH cases using linear regression. Signals with P<5×10-8 were pursued in replication and tested for association with admission Glasgow coma scale and 3-month post-ICH dichotomized (0-2 versus 3-6) modified Rankin Scale using ordinal and logistic regression, respectively.

RESULTS

The discovery phase included 394 ICH cases (228 lobar and 166 nonlobar) and identified 2 susceptibility loci: a genomic region on 22q13 encompassing PARVB (top single-nucleotide polymorphism rs9614326: β, 1.84; SE, 0.32; P=4.4×10-8) for lobar ICH volume and an intergenic region overlying numerous copy number variants on 17p12 (top single-nucleotide polymorphism rs11655160: β, 0.95; SE, 0.17; P=4.3×10-8) for nonlobar ICH volume. The replication included 240 ICH cases (71 lobar and 169 nonlobar) and corroborated the association for 17p12 (P=0.04; meta-analysis P=2.5×10-9; heterogeneity, P=0.16) but not for 22q13 (P=0.49). In multivariable analysis, rs11655160 was also associated with lower admission Glasgow coma scale (odds ratio, 0.17; P=0.004) and increased risk of poor 3-month modified Rankin Scale (odds ratio, 1.94; P=0.045).

CONCLUSIONS

We identified 17p12 as a novel susceptibility risk locus for hematoma volume, clinical severity, and functional outcome in nonlobar ICH. Replication in other ethnicities and follow-up translational studies are needed to elucidate the mechanism mediating the observed association.