Polygenic Risk Score for Cardiovascular Diseases in Artificial Intelligence Paradigm: A Review

Cardiovascular disease (CVD) related mortality and morbidity heavily strain society. The relationship between external risk factors and our genetics have not been well established.It is widely acknowledged that environmental influence and individual behaviours play a significant role in CVD vulnerability, leading to the development of polygenic risk scores (PRS). We employed the PRISMA search method to locate pertinent research and literature to extensively review artificial intelligence (AI)-based PRS models for CVD risk prediction.Furthermore, we analyzed and compared conventional vs. AI-based solutions for PRS. We summarized the recent advances in our understanding of the use of AI-based PRS for risk prediction of CVD. Our study proposes three hypotheses: i) Multiple genetic variations and risk factors can be incorporated into AI-based PRS to improve the accuracy of CVD risk predicting. ii) AI-based PRS for CVD circumvents the drawbacks of conventional PRS calculators by incorporating a larger variety of genetic and non-genetic components, allowing for more precise and individualised risk estimations. iii) Using AI approaches, it is possible to significantly reduce the dimensionality of huge genomic datasets, resulting in more accurate and effective disease risk prediction models. Our study highlighted that the AI-PRS model outperformed traditional PRS calculators in predicting CVD risk. Furthermore, using AI-based methods to calculate PRS may increase the precision of risk predictions for CVD and have significant ramifications for individualized prevention and treatment plans.

Lipid Abnormalities in Type 2 Diabetes Mellitus Patients with Overt Nephropathy

BACKGROUND: Diabetic nephropathy is a major complication of diabetes and an established risk factor for cardiovascular events. Lipid abnormalities occur in patients with diabetic nephropathy, which further increase their risk for cardiovascular events. We compared the degree of dyslipidemia among type 2 diabetes mellitus (T2DM) subjects with and without nephropathy and analyzed the factors associated with nephropathy among them. METHODS: In this retrospective study, T2DM patients with overt nephropathy were enrolled in the study group (n=89) and without nephropathy were enrolled in the control group (n=92). Both groups were matched for age and duration of diabetes. Data on total cholesterol (TC), triglycerides (TG), high density lipoprotein cholesterol (HDL-C), low density lipoprotein cholesterol (LDL-C), urea and creatinine were collected from the case sheets. TG/HDL-C ratio, a surrogate marker for small, dense, LDL particles (sdLDL) and estimated glomerular filtration rate (eGFR) were calculated using equations. Multivariate analysis was done to determine the factors associated with eGFR. RESULTS: Dyslipidemia was present among 56.52% of control subjects and 75.28% of nephropathy subjects (P=0.012). The percentage of subjects with atherogenic dyslipidemia (high TG+low HDL-C+sdLDL) was 14.13 among controls and 14.61 among nephropathy subjects. Though serum creatinine was not significantly different, mean eGFR value was significantly lower among nephropathy patients (P=0.002). Upon multivariate analysis, it was found that TC (P=0.007) and HDL-C (P=0.06) were associated with eGFR among our study subjects. CONCLUSION: Our results show that dyslipidemia was highly prevalent among subjects with nephropathy. Regular screening for dyslipidemia may be beneficial in controlling the risk for adverse events among diabetic nephropathy patients.

Clinical significance of urinary Monocyte Chemoattractant Protein-1 [uMCP-1] in Indian type 2 diabetic patients at different stages of diabetic nephropathy

Monocyte Chemoattractant Protein-1 [MCP-1] is the strongest known chemotactic factor for monocytes and is upregulated in diabetic nephropathy. So measuring urinary MCP-1 is of great significance in the diagnosis and intervention of early diabetic nephropathy. This study aims at determining the levels of urinary MCP-1 [uMCP-1] at different stages of diabetic nephropathy and to see its correlation with other parameters in Indian type2 diabetic subjects. A total of 64 [M:F; 40:24] type 2 diabetic subjects were divided into three groups based on their renal function and were compared with non-diabetic controls [Group 1] n = 20 [M:F; 13:7]. The study groups were Group 2 [normoalbuminuria] n = 16, Group 3 [microalbuminuria] n = 23 and Group 4 [macroalbuminuria] n = 25. Demographic, anthropometric and biochemical details were recorded for all the subjects. Urinary MCP-1 levels were measured by using solid phase ELISA method. Mean levels of uMCP-1 in subjects with type 2 diabetes were significantly higher than in controls [p < 0.05]. The levels of uMCP-1 in type 2 diabetic subjects increased gradually with deteriorating renal function [p = 0.006]. There was a significant difference in urinary MCP-1 levels between Group 2 and Group 1 [p < 0.001]. Levels of uMCP-1 were significantly higher in subjects with eGFR <60 ml/min compared to eGFR >60 ml/min [p = 0.008]. uMCP-1 levels correlated positively with uACR or uPCR [r = 0.551, p< 0.0001], urea [r = 0.43, p< 0.0001] and creatinine [r= 0.478, p< 0.0001]. A negative correlation between uMCP-1 and eGFR [r = -0.338, p = 0.006] was noted. Our study demonstrated that urinary MCP-1 levels increased gradually in type 2 diabetic subjects with deteriorating renal function. It is significantly associated with the other risk factors of diabetic nephropathy

Levels of glycated albumin at different stages of diabetic nephropathy in India

Glycated haemoglobin [HbAlc] which is an index of long term glycaemic control in diabetic patients is measured in majority of patients worldwide. Glycated albumin [GA] is useful for the evaluation of short term glycaemic control [2 weeks] in patients with diabetes. The aim of this study was to assess the GA levels at different stages of diabetic nephropathy in Indian population. A total of 147 subjects [M:F; 95:52] were selected for this study and were divided into three groups based on their renal function and compared with a non diabetic control group [n = 50, M:F; 14:36]. The groups were as follows; group1 [control] n = 50, group2 [normoalbuminuria] n = 42, group 3 [microalbuminuria] n = 55, group 4 [proteinuria] n = 50. GA was measured by enzymatic procedure using the Lucica GA - L kit [Asahi Kasei Pharma Corp, Japan]. The normal cutoff value for GA was derived using control group and it was found to be 15% [range 7-17%]. GA was significantly higher in diabetic patients at different stages of diabetic nephropathy compared to non diabetic control group [cont: 12.9 +/- 1.8, normo: 20.8 +/- 5.8, micro: 26.1 +/- 8.6, macro: 23.5 +/- 8.3]. Microalbuminuric patients had significantly higher GA levels than normoalbuminuric patients [p< 0.05]. Proteinuric subjects had slightly lower GA levels compared to microalbuminuric group but it was not statistically significant. GA was found to be a better marker for evaluating short term glycaemic status among diabetic patients with different degree of renal impairment prior to ESRD