| Summary: | Data analysis in the healthcare sector can be an important tool for identifying patterns in the data. When it comes to low-density lipoprotein (LDL) cholesterol test results, lower values are preferable. This paper details a factor analytical method whose main objective is to create a very effective risk prediction model for cardiovascular incidence. Both qualitative and quantitative methods were used to generate and test the hypothesis. To investigate the attributes' associations with and relevance to cardiovascular, a data understanding analysis is specifically carried out. This paper aims to evaluate the variables affecting LDL-C by using data analytics. Consistency, convergent, and discriminant have all been considered when evaluating the prediction model. The results showed that high-density lipoprotein (HDL) significantly reduces LDL with (P 0.001, = 0.04), whereas, total cholesterol (TC) has a considerable impact on LDL with (P 0.001, r = 0.92), whereas, Very-low-density lipoprotein (VLDL) significantly affects LDL with (P 0.001, = −0.16) and, triglycerides (TG) significantly affects LDL with (P 0.001, = −0.20). The outcome will be a prediction model based on a neural network and data analysis.
|
|---|