Computational statistical modelling for parameters optimization of LDL-cholesterol levels in patients with type 2 diabetes
DOI:
https://doi.org/10.3329/bjms.v23i2.72191Keywords:
Multiple linear regression; Multilayer feedforward neural network (MLFFNN); Hybrid methodology; BootstrappingAbstract
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.
Bangladesh Journal of Medical Science Vol. 23 No. 02 April’24 Page : 498-506
Downloads
76
148
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Wan Muhamad Amir W Ahmad, Farah Muna Mohamad Ghazali, Hazik Bin Shahzad, Mohamad Nasarudin Adnan, Nor Azlida Aleng
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish in the Bangladesh Journal of Medical Science agree to the following terms that:
- Authors retain copyright and grant Bangladesh Journal of Medical Science the right of first publication of the work.
Articles in Bangladesh Journal of Medical Science are licensed under a Creative Commons Attribution 4.0 International License CC BY-4.0.This license permits use, distribution and reproduction in any medium, provided the original work is properly cited.- Authors are able to enter into separate, additional contractual arrangements for the distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted to post their work online (e.g., in institutional repositories or on their website) as it can lead to productive exchanges, as well as greater citation of published work.
