Comparing the predictability of different chemometric models over UV-spectral data of isoxsuprine and its toxic photothermal degradation products Ahmed S. Saad a,b, ⁎, Eman S. Elzanfaly a , Michael K. Halim b , Khadiga M. Kelani a,c a Analytical Chemistry Department, Faculty of Pharmacy, Cairo University, El-Kasr El-Aini Street, ET-11562 Cairo, Egypt b Chemistry Department, Faculty of Pharmacy, October 6 University, 6 October City 12585, Egypt c Analytical Chemistry Department, Faculty of Pharmacy, Modern Technology and Information University, Cairo, Egypt abstract article info Article history: Received 28 December 2018 Received in revised form 2 April 2019 Accepted 22 April 2019 Available online 01 May 2019 Isoxsuprine (ISX) is widely used for cerebral and peripheral vascular diseases. A comparative study was held among different multivariate calibration models for selective determination of a complex mixture of Isoxsuprine and four of its toxic photothermal degradation products that impair kidney and liver functions. The Partial Least Squares (PLS) and Artificial Neural Network (ANN) models were applied on the specific spectrum and on selected wavelengths using genetic algorithm (GA) technique as an efficient variable selection tool. The effect of GA on the model construction and performance was evaluated. The multilevel multifactor experimental design was adopted for the construction of the calibration set. Optimized parameters were used for the development of the different models. The performances of the developed models were assessed by predicting the concentration of eight different mixtures composing the validation set. Results were compared to one another and to the official method using one-way ANOVA statistical test to assure the validity of the constructed models. The lower chance of overfitting offered by ANN minimized the RMSEP relative to the PLS. On the other hand, the application of GA prior to model implementation affected the number of latent variables the prediction ability of both PLS and ANN models. The validated models were successfully applied as stability indicating assay methods for the selective de- termination of ISX and its photothermal degradation products in ISX raw material and market formulations. © 2019 Elsevier B.V. All rights reserved. Keywords: Isoxsuprine Chemometric methods Photothermal degradation products PLS ANN GA 1. Introduction Isoxsuprine Hydrochloride (ISX) is (1RS, 2SR)-1-(4- hydroxyphenyl)-2-[[(1SR)-1-methyl-2-phenoxyethyl] amino] propan- 1-ol hydrochloride [1](Fig. 1a). ISX is used as β2 adrenoreceptors stim- ulant and α adrenoreceptors antagonist. It works by broadening veins to increase blood flow (enhance circulation) to specific parts of the body (e.g., hands/feet, head. It is widely utilized as a part of the manage- ment of cerebral and peripheral vascular disorders, effective in many diseases such as Raynaud's syndrome, obliterative arteriosclerosis, thromboangilitis daliterans and in the delays of premature labor [2,3]. ISX is approved in the B.P [4] and in the U.S.P [5] where it is analyzed by potentiometric titration and spectrophotometrically respectively. Pharmacologically active compounds may suffer degradation upon manufacture, transport and storage. Degradation can occur by different factors including light, air, heat, moisture, aging and micro-organisms [6]. The degradation process may be minor or severe, which can be ac- companied by partial or complete loss of the pharmacological activity or/and the formation of dangerous decomposition products [7]. As the number of components in a mixture increases, spectral over- lap and spectrophotometric quantification of each component becomes more difficult. However, chemometrics has represented a valuable solu- tion by gaining selective information from random data. Multivariate calibration, such as Partial Least Squares (PLS) and Principle Component Analysis (PCR) can be successfully applied for the determination of mul- ticomponent samples without the need for costly instrumentation, ex- pensive solvents and time-consuming separation procedures used in chromatographic methods [8]. More advanced artificial intelligence techniques such as Artificial Neural Network (ANN) simulates the bio- logical nervous system in having the ability to discover the correlation among inputs and outputs [9–11]. The analytical profile of ISX revealed its susceptibility to photothermal degradation. The degradation process was monitored on TLC plates illuminated with UV light [12,13], it was found that the products of degradation varied according to the exposure interval, and the authors were able to identify the degradation products, namely; P- Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy 219 (2019) 444–449 ⁎ Corresponding author at: Analytical Chemistry Department, Faculty of Pharmacy, Cairo University, El-Kasr El-Aini Street, ET-11562 Cairo, Egypt. E-mail address: ahmedss_pharm@yahoo.com (A.S. Saad). https://doi.org/10.1016/j.saa.2019.04.064 1386-1425/© 2019 Elsevier B.V. All rights reserved. Contents lists available at ScienceDirect Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy journal homepage: www.elsevier.com/locate/saa