الفهرس 
Development and validation of a prediction model for selection of organic extraction solvents for different drugs from aqueous-based matrices /
Abstract EnglishOnly 14 pages are availabe for public view
 |  | from | 121 |  |  |
| | | from | 121 | | |
Abstract
Analyte(s) extraction process is very crucial in most analytical procedures, especially bioanalytical ones. Method development of sample extraction procedure represents a challenging difficulty to most analysts as it consumes time and effort to develop the optimum extraction method for the desired analyte(s) from the aqueous matrix with the best achievable extraction recovery. Liquid-liquid extraction (LLE) is one of the most important samples extraction techniques. LLE can provide extracts with low levels of the co-extracted matrix material. The objective of the current study was to build a robust and reliable LLE prediction algorithm that can predict the solvent combination capable to achieve the optimum extraction results based on chosen descriptors for the cited analyte(s). Artificial neural networks (ANNs) are biologically inspired computer programs designed to simulate the way in which the human brain processes information.The power of neural computations comes from connecting neurons in a network. Each processing element has weighted inputs, transfer function, and one output.The model was designed on the MATLAB program by giving it the chosen descriptors for the cited analyte(s) as input then produces corresponding Hansen solubility parameters of the predicted extraction solvents as an output of the model. Then with visual inspection from the solvent mixtures’ appendix, the analyst can identify the proposed extraction solvents for the cited drug easily and quickly. Linear layer design was used for LLE model generation, and the model was validated. Bioanalysis could be much easier with the aid of the developed model