Artificial Neural Network versus Binary Logistic Regression for Determination of Risk Factors of Myocardial Infarction

Abstract Background Postoperative paediatric cerebellar mutism syndrome (pCMS) is a common but severe complication which may arise following the resection of posterior fossa tumours in children. Two previous studies have aimed to preoperatively predict pCMS, with varying results. In this work, we examine the generalisation of these models and determine if pCMS can be predicted more accurately using an artificial neural network (ANN). Methods An overview of reviews was performed to identify risk factors for pCMS, and a retrospective dataset collected as per these defined risk factors from children undergoing resection of primary posterior fossa tumours. The ANN was trained on this dataset and its performance evaluated in comparison to logistic regression and other predictive indices via analysis of receiver operator characteristic curves. Area under the curve (AUC) and accuracy were calculated and compared using a Wilcoxon signed rank test, with p<0.05 considered statistically significant. Results 204 children were included, of whom 80 developed pCMS. The performance of the ANN (AUC 0.949; accuracy 90.9%) exceeded that of logistic regression (p<0.05) and both external models (p<0.001). Conclusion Using an ANN, we show improved prediction of pCMS in comparison to previous models and conventional methods.

Download Full-text

Comparison of Predictive Models in Classification of Nutritional Status among Arsenic Affected People in Rural Areas in Bangladesh: An Artificial Neural Network (ANN) and Logistic Regression Approach

Journal of Shaheed Suhrawardy Medical College ◽

10.3329/jssmc.v6i2.31773 ◽

2017 ◽

Vol 6 (2) ◽

pp. 71-75

Author(s):

Azizur Rahman ◽

Mariam Akter ◽

Ajit Kumar Majumder ◽

Md Atiqul Islam ◽

AFM Arshedi Sattar

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Logistic Regression ◽

Clinical Data ◽

Predictive Models ◽

Rural Areas ◽

Binary Logistic Regression ◽

Binary Outcome ◽

Artificial Neural

Background: Clinical data play an important role in medical sector for binary outcome variables. Various methods can be applied to build predictive models for the clinical data with binary outcome variables.Objective: This research was aimed to explore and compare the process of constructing common predictive models.Methodology: Models based on an artificial neural network (the connectionist approach) and binary logistic regressions were compared in their ability to classifying malnourished subjects and those with over-weighted participants in rural areas of Bangladesh. Subjects were classified according to the indicator of nutritional status measured by body mass index (BMI). This study also investigated the effects of different factors on the BMI level of adults of six Villages in Bangladesh. Demographic, anthropometric and clinical data were collected based on aged over 30 years from six Villages in Bangladesh that were identified as mainly dependent on wells contaminated with arsenic.Result: A total of 460 participants were recruited for this study. Out of 460(140 male and 320 females) participants 186(40.44%) were identified as malnourished (BMK18.5 gm), and the remainder 274(59.56%) were found as over-weighted (BMI>18.5 gm). Among other factors, arsenic exposures were found as significant risk factors for low body mass index (BMI) with a higher value of odds ratio. This study shows that, binary logistic regression correctly classified 72.85% of cases with malnourished in the training datasets, 76.08% in the testing datasets and 75.26% of all subjects. The sensitivities of the neural network architecture for the training and testing datasets and for all subjects were 84.28%, 84.78% and 81 .72% respectively, indicate better performance than binary logistic regression model.Conclusion: This study demonstrates a significant performance of artificial neural network than the binary logistic regression models in classification of malnourished participants from over-weighted ones.J Shaheed Suhrawardy Med Coll, 2014; 6(2):71-75

Download Full-text

Predicting the outcomes of a single endoscopic correction of vesicoureteral reflux using a dextranomer/hyaluronic acid copolymer: selection of the optimal predictive model

Herald Urology ◽

10.21886/2308-6424-2021-9-2-45-55 ◽

2021 ◽

Vol 9 (2) ◽

pp. 45-55

Author(s):

V. I. Dubrov ◽

V. V. Sizonov ◽

I. M. Kagantsov ◽

K. N. Negmatova ◽

S. G. Bondarenko

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Logistic Regression ◽

Regression Model ◽

Logistic Regression Model ◽

Binary Logistic Regression ◽

Binary Logistic Regression Model ◽

Endoscopic Injection ◽

Acid Copolymer ◽

Artificial Neural

Introduction. Endoscopic dextranomer/hyaluronic acid copolymer (DxHA) injection is the most commonly used minimally invasive method of surgical treatment of vesicoureteral reflux (VUR) in children.Purpose of the study. To estimate the accuracy of logistic prognostic models and artificial neural network for prediction a single endoscopic injection DxHA in VUR.Materials and methods. We used endoscopic DxHA in 582 patients (783 ureteric units) of all grades reflux (I - 20, II - 133, III - 443, IV - 187), 53 ureters had complete duplication. A total effectiveness of surgery was 53.2%. A binary logistic regression model and an artificial neural network (multilayer perceptron) were created, taking the following as independent variables: grade of reflux, the patient's age and sex, the ureteral duplication and ureteral dilatation index.Results. The univariate logistic regression showed that the selected predictors were strongly related to the outcome of the treatment. Binary logistic regression and neural network developed high accuracy of the predictions, area under ROC-curve was 0,7 for logistic regression model (a sensitivity of 70.7%, and a specificity of 66.3%) and 0.74 for artificial neural network (a sensitivity of 85.5%, a specificity of 65.3%). Synaptic neural network weights and logistic regression parameters were used in a scoring model to predict the outcome of a single endoscopic injection of DxHA in 2 independent hospitals. An outcomes analysis using predictive models in independent clinics showed a good quality of prediction both with the use of logistic regression (75% and 90% of the correct prognosis) and using a neural network (89.7% and 77% of the correct prediction).Conclusion. An artificial neural network and a binary logistic regression model are an effective tool to assist urologists in identifying and applying endoscopic treatments for VUR in children.

Download Full-text