Jaundice (hyperbilirubinemia) is a common disease in newborn babies. Under certain circumstances, elevated bilirubin levels may have detrimental neurological effects. In some cases, phototherapy is needed to lower the level of total serum bilirubin, which indicates the presence and severity of jaundice. Recently, diagnosis and treatment modeling of disease have been considered by many researchers. In this paper, we present two models for classification and prediction of neonatal jaundice. The models are based on recorded data of Iranian Neonates. This study is oriented on the basis of following procedures: a short review on physiology of Jaundice, and then description of the models. Two three-layer feed forward neural networks were used in the modeling. The neural network model for classification is able to specify the type of jaundice, and the model for prediction can evaluate the risk of jaundice for newborns. These models can be used to decrease the risk in the critical cases as well as the cost of treatment.

In this paper, a new simple method is presented for the estimation of the Toxicity of nitroaromatic compounds including some well-known explosives. This method can predict the 50% lethal dose concentration for rats (LD50) as the estimation of Toxicity in vivo. The prediction of LD50 of nitroaromatics through a new general correlation is based on the number of alkyl and nitro groups per molecular weight of the nitroaromatic compound as a core function. The existence of some specific structural parameters can decrease or increase the predicted results on the basis of the core function. The predicted results of various nitroaromatic compounds afford reliable prediction of LD50 with respect to experimental data. prediction of Toxicity for 28 nitroaromatic compounds, where the experimental data were available, and new nitroaromatic derivatives produce comparable results to those of several models of Quantitative Structure Activity Relation (QSAR).

BACKGROUND AND OBJECTIVES: The focus of this study is on the importance of reliable and precise forecasting of acute oral Toxicity to bolster chemical safety and advance sustainable development goals, particularly sustainable development goals-3 (good health and well-being), sustainable development goals-6 (clean water and sanitation), and sustainable development goals-12 (responsible consumption and production). Traditional Toxicity assessments are often time-consuming and costly, necessitating the exploration of more efficient approaches. The focus of this study is to establish the most efficient method for constructing reliable and precise models for Toxicity prediction.METHODS: The random forests were evaluated, a robust ensemble method, for predicting acute oral Toxicity using a comprehensive dataset from National Toxicology Program/Interagency Center for the Evaluation of Alternative Toxicological Methods and Environmental Protection Agency/National Center for Competency Testing, which presented significant class imbalance, 8 percent very toxic 92 percent not very toxic. To address this imbalance, strategies such as cost-sensitive learning and data resampling techniques, including both under sampling and oversampling, were utilized. A diverse set of two-dimensional molecular descriptors generated via rational discovery kit were used as input features, and model preprocessing involved normalization, validation, and feature selection. Hyper-parameter tuning was conducted using Bayesian optimization and cross-validation, while the performance of random forests was evaluated in comparison to gradient boosting, extreme gradient boosting, artificial neural networks, and the generalized linear model.FINDINGS: The random forests models, particularly those utilizing under sampling and cost-sensitive learning, demonstrated superior performance, achieving sensitivity of 0.81, Specificity of 0.85, accuracy of 0.85, and an area under the receiver operating characteristic curve of 0.89 on an independent test set. An examination of feature importance has shown that the primary molecular descriptors are those related to the Van der waals surface area and molecular quantum numbers. A surrogate decision tree developed from random forests predictions reached an area under the curve of 0.929.CONCLUSION: Random forest models effectively predicted acute oral Toxicity, particularly when addressing class imbalance through cost-sensitive learning and resampling. leveraging explainable artificial intelligence techniques, including permutation feature importance, surrogate decision tree analysis and local interpretable model-agnostic explanations, this study identified key molecular descriptors driving Toxicity. This advancement improves model interpretability and represents a significant step toward enhancing chemical safety while supporting sustainable development goals.