BackgroundMounting evidence has suggested that plasminogen activator inhibitor-1 (PAI-1) is a candidate for increased risk of diabetic retinopathy. Studies have reported that insertion/deletion polymorphism in the PAI-1 gene may influence the risk of this disease. To comprehensively address this issue, we performed a meta-analysis to evaluate the association of PAI-1 4G/5G polymorphism with diabetic retinopathy in type 2 diabetes.MethodsData were retrieved in a systematic manner and analyzed using Review Manager and STATA Statistical Software. Crude odds ratios (ORs) with 95% confidence intervals (CIs) were used to assess the strength of associations.ResultsNine studies with 1, 217 cases and 1, 459 controls were included. Allelic and genotypic comparisons between cases and controls were evaluated. Overall analysis suggests a marginal association of the 4G/5G polymorphism with diabetic retinopathy (for 4G versus 5G: OR 1.13, 95%CI 1.01 to 1.26; for 4G/4G versus 5G/5G: OR 1.30, 95%CI 1.04 to 1.64; for 4G/4G versus 5G/5G + 4G/5G: OR 1.26, 95%CI 1.05 to 1.52). In subgroup analysis by ethnicity, we found an association among the Caucasian population (for 4G versus 5G: OR 1.14, 95% CI 1.00 to 1.30; for 4G/4G versus 5G/5G: OR 1.33, 95%CI 1.02 to 1.74; for 4G/4G versus 5G/5G + 4G/5G: OR 1.41, 95%CI 1.13 to 1.77). When stratified by the average duration of diabetes, patients with diabetes histories longer than 10 years have an elevated susceptibility to diabetic retinopathy than those with shorter histories (for 4G/4G versus 5G/5G: OR 1.47, 95%CI 1.08 to 2.00). We also detected a higher risk in hospital-based studies (for 4G/4G versus 5G/5G+4G/5G: OR 1.27, 95%CI 1.02 to 1.57).ConclusionsThe present meta-analysis suggested that 4G/5G polymorphism in the PAI-1 gene potentially increased the risk of diabetic retinopathy in type 2 diabetes and showed a discrepancy in different ethnicities. A higher susceptibility in patients with longer duration of diabetes (more than 10 years) indicated a gene-environment interaction in determining the risk of diabetic retinopathy.

Numerous applications in data mining and machine learning require recovering a matrix of minimal rank. Robust principal component analysis (RPCA) is a general framework for handling this kind of problems. Nuclear norm based convex surrogate of the rank function in RPCA is widely investigated. Under certain assumptions, it can recover the underlying true low rank matrix with high probability. However, those assumptions may not hold in real-world applications. Since the nuclear norm approximates the rank by adding all singular values together, which is essentially a 1norm of the singular values, the resulting approximation error is not trivial and thus the resulting matrix estimator can be significantly biased. To seek a closer approximation and to alleviate the above-mentioned limitations of the nuclear norm, we propose a nonconvex rank approximation. This approximation to the matrix rank is tighter than the nuclear norm. To solve the associated nonconvex minimization problem, we develop an efficient augmented Lagrange multiplier based optimization algorithm. Experimental results demonstrate that our method outperforms current state-of-the-art algorithms in both accuracy and efficiency.

No abstract