Simulation of liver function enzymes as determinants of thyroidism: a novel ensemble machine learning approach

Abstract

Background Hormone production by the thyroid gland is a prime aspect of maintaining body homeostasis. In this study, the ability of single artificial intelligence (AI)-based models, namely multi-layer perceptron (MLP), support vector machine (SVM), and Hammerstein–Weiner (HW) models, were used in the simulation of thyroidism status. The study's primary aim is to unveil the best performing model for the simulation of thyroidism status using hepatic enzymes and hormones as the independent variables. Three statistical metrics were used in evaluating the performance of the models, namely determination coefficient (R2), correlation coefficient (R), and mean squared error (MSE). Results Considering the quantitative and visual presentation of the results obtained, it has been observed that the MLP model showed higher performance skills than SVM and HW, which improved their performances up to 3.77% and 12.54%, respectively, in the testing stages. Furthermore, to boost the performance of the single AI-based models, three different ensemble approaches were employed, including neural network ensemble (NNE), weighted average ensemble (WAE), and simple average ensemble (SAE). The quantitative predictive performance of the NNE technique boosts the performance of SAE and WAE approaches up to 2.85% and 1.22%, respectively, in the testing stage. Conclusions Comparative performance of the ensemble techniques over the single models showed that NNE outperformed all the three AI-based models (MLP, SVM, and HW) and boosted their performance accuracy up to 7.44%, 11.212%, and 19.98%, respectively, in the testing stages.

COVID-19 Prediction Using Black-Box Based Pearson Correlation Approach

“…As an alternative to the complex k-fold method, the holdout strategy is often viewed as more user-friendly [ 27 ]. At this point, the data are typically split randomly in half, with one half used for training and the other for testing [ 28 ]. One of the main advantages of the k-fold cross-validation mechanism is that in each round, the validation set and the training sets are completely separate from one another.…”

Quantitative Forecasting of Malaria Parasite Using Machine Learning Models: MLR, ANN, ANFIS and Random Forest

“…The variables A 1 , B 1 , and B 2 are the membership functions for x and y, whereas the inputs p 1 , q 1 , r 1 , and p 2 , q 2 , r 2 provide the data for the output function. The ANFIS's formulation and structure are compatible with a 5-tiered neural network design [26].…”

Chemometrics Feasibility for Modelling Chromatographic Behavior of Diazepam using Linear and Non-Linear Techniques: A Data Mining Based Approach

“…The second one involves the small scale or sometimes considered as the local structures, which mainly focused on modelling and detecting some anomalies as well as decide if there is high performance for fitness to decide whether there is chance for their occurrence (Bala et al, 2023;Rezaei-Darzi et al, 2014; A. G. . Data mining has been in existence for long, which is recently known as derogatory way, fishing through data and trawling Abba, Benaafi, Usman, Ozsahin, et al, 2023;Jibril, Zayyan, et al, 2023;Madaki et al, 2022;Pham et al, 2019;Rong et al, 2018;A. G. Usman, Ghali, et al, 2022;D.…”