Background: The goal of this study is to illustrate an optimum variable selection method using established Multiple Linear Regression (MLR) models and to validate the variable using Multilayer Perceptron Neural Network (MLP) models. Initially, all selected variables will be passed through the bootstrap methodology, and they were screened for significant relationships. Objective: The goal of this work is to analyze and construct a model for the factor linked with total crime cases by combining an Applied Linear Regression Model (ALRM) and a Multilayer Perceptron (MLP). Material and Methods: Around 200 data was simulated to build the methodology. Advanced computational statistical modeling methodologies were used to evaluate data descriptions of several variables in this retrospective study, including the total victim, gender, age, marital status, social class, adult in the household, children in household, burglary’s victim, sexual’s victim, victim’s report, and household location. The case study was developed and implemented using the R-Studio program and syntax. Results: The statistical method demonstrated that regression modeling surpasses R-squared and mean square error test in most situations. Researchers observed that when data is divided into two datasets for training and testing, the hybrid model approach performs significantly better at predicting the experiment’s outcome. When it came time to determine variable validity, the well-established bootstrap-integrated MLR approach was applied. Ten characteristics are taken into consideration in this case: Gender (: -0.4369700; p< 0.25), age (: -0.0086757; p< 0.25), marital status (: 0.2646097; p< 0.25), social class ( : 0.0602540; p< 0.25), adult in household (: -0.0211293; p> 0.25), children in household (: -0.0025346; p> 0.25), burglary’s victim (: 1.3473593; p< 0.25), sexual’s victim (: 1.0382444; p< 0.25), victim’s report (: -0.3176104; p< 0.25), and location of household (: -0.1355046; p< 0.25).There is a 0.07745823 MSE for the linear model in this scenario. Conclusion: The neural network’s Predicted Mean Square Error (PMSE) was used to assess MLP’s performance (MSE-forecasts the Network). PMSE is used to determine how far our projections are from the actual data, and the lowest MSE from the MLP indicates the best achievement. The R syntax for MLR and MLP is also included in this research article.As a result, the study’s conclusion establishes the superiority of the hybrid model technique. Bangladesh Journal of Medical Science Vol. 22 No. 01 January’23 Page : 38-46

Background:Hypertension is a public health problem used to describe high blood pressure where the blood vessels are persistently increased in force. According to WHO, hypertension has been reported in one in four men and one in five women. Worldwide, hypertension is a common health problem that affects 20-30% of the adult population and more than 5-8% of pregnancies, and it is frequently curable when detected and treated early enough. Objective: This paper aims to validate the factor associatedwith hypertension status among patients with dyslipidemia and type 2 diabetes mellitus. This could help to improve the prediction of the probability of hypertension among studied patients. Material and Methods: 39 patients were recruited from the Hospital Universiti Sains Malaysia (USM). In this retrospective study, advanced computational statistical modeling methodologies were used to evaluate data descriptions of several variables such as hypertension, marital status, smoking status, systolic blood pressure, fasting blood glucose, total cholesterol, high-density lipoprotein, alanine transferase, alkaline phosphatase, and urea reading. The R-Studio software and syntax were used to implement and test the hazard ratio. The statistics for each sample were calculated using a combination model that included bootstrap and multiple logistic regression methods. Results: The statistical strategy showed R demonstrates that regression modeling outperforms an R-squared. It revealed that the hybrid model technique better predicts the outcome when data is partitioned into a training and testing dataset. The variable validation was determined using the well-established bootstrap-integrated MLRtechnique. In this case, eight variables are considered: marital status, systolic blood pressure, fasting blood glucose, total cholesterol, high-density lipoprotein, alanine transferase, alkaline phosphatase, and urea reading. It’s important to note that six things affect the hazard ratio: Marital status (β1: 1.183519; p< 0.25), systolic blood pressure ( :-0.144516; p< 0.25), total cholesterol (β2: 0.9585890; p< 0.25), high-density lipoprotein ( :-5.927411; p< 0.25), alkaline phosphatase ( :-0.008973; p> 0.25), and urea reading ( :0.064169; p< 0.25).There is a 0.003469102 MSE for the linear model in this scenario. Conclusion: In this study, a hybrid approach combining bootstrapping and multiple logistic regression will be developed and extensively tested. The R syntax for this methodology was designed to ensure that the researcher completely understood the illustration. In this case, a hybrid model demonstrates how this critical conclusion enables us to understand better the utility and relative contribution of the hybrid method to the outcome. The statistical technique used in this study, R, demonstrates that regression modelingoutperforms R-squared values of 0.9014 and 0.00882 for the Predicted Mean Squared Error, respectively. Thus, the study’s conclusion establishes the superiority of the hybrid model technique used in the study. Bangladesh Journal of Medical Science Vol. 22 No. 02 April’23 Page : 422-431

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