This work employs the application of three artificial intelligence (AI) techniques namely; support vector machine (SVM), Hammerstein-Wiener (HW) and multi-layer perceptron (MLP) for predicting the qualitative properties of an anti-Alzheimer agent using high-pressure liquid chromatography technique. The mobile phase (inform of acetonitrile and trifluoroacetic acid) and the column temperature was used as the predictors in modelling the maximum retention time (tR-max) and resolution (Resol.) as the output variables of the analyte. The measured and predicted values were checked using three performance indices including; Nash-Sutcliffe efficiency (NSE), correlation coefficient (CC) as the goodness of fits and a statistical error inform of root-mean-square error (RMSE). The results obtained demonstrated the promising ability of AI-based models in modelling the qualitative properties of the anti-Alzheimer agent. Observation of different outputs of the AI-based models at various time intervals showed the necessity of ensembling the outputs of the AI-based models. Therefore, simple average ensemble and support vector machine ensemble (SVM-E) were employed to enhance the performance skills of the simple models. The comparative performance of SVM-E inform of NSE indicated its ability in boosting and enhancing the performance skills of the single models SVM, MLP and HW models up to 5, 13 and 20% respectively in the testing stage for modelling tR-max.

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.