We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Computational statistical modelling for parameters optimization of LDL-cholesterol levels in patients with type 2 diabetes.
- Authors
Ahmad, Wan Muhamad Amir W.; Mohamad Ghazali, Farah Muna; Bin Shahzad, Hazik; Adnan, Mohamad Nasarudin; Aleng, Nor Azlida
- Abstract
Introduction LDL is the acronym used to denote low-density lipoproteins. When the level of LDL is high, it leads to the accumulation of cholesterol in the arteries, and as a result, it is commonly known as "bad" cholesterol. Recognizing the significance, a study is conducted on computational and statistical modelling for parameter optimization of LDL-cholesterol levels. In recent years, there has been an increase in the application of precise statistical analysis methodologies. Consequently, scientists are more focused on producing reliable results and are more determined to provide credible findings. Objective This study aims to develop and validate a proposed hybrid method that combines Multilayer Feedforward Neural Network (MLFFNN), and Multiple Linear Model (MLR) and to present the R-syntax applications of the proposed hybrid method with clinical study data. Material and Methods The proposed hybrid model will be built using the generalized mixture model, which is formulated using an MLFFNN framework and Linear Model (LM). The performance of the hybrid model will be assessed utilizing the predicted mean square error neural network (MSE.net) and the predicted mean square error (P.MSE), which will serve as a benchmark for precision and efficacy. Results: The result indicates that hybrid method modelling is superior, with the highest R-squared value and the lowest MSE.net value. The hybrid model technique was found to produce a more precise forecast of the outcome when the data is separated into training and testing datasets. The R-square score in this report demonstrates that the LM model is a good fit (84.97%), and the MSE.net value of 0.00529 indicates that the model is both accurate and predictive. Conclusion The research concludes that the hybrid model method proposed is preferable. This critical conclusion helps us comprehend the hybrid method's proportional contribution to this illustration's result.
- Subjects
LDL cholesterol; TYPE 2 diabetes; FEEDFORWARD neural networks; STATISTICAL models; LOW density lipoproteins
- Publication
Bangladesh Journal of Medical Science, 2024, Vol 23, Issue 2, p498
- ISSN
2223-4721
- Publication type
Article
- DOI
10.3329/bjms.v23i2.72191