Simultaneous Determination of Estradiol Cypionate and Medroxyprogesterone Acetate Hormones in Injectable Suspension by UV Spectrophotometry Based on Least-Squares Support Vector Machine and Fuzzy Inference System: Comparison with HPLC.

Background: The combination of estradiol cypionate (ECA) and medroxyprogesterone acetate (MPA) is used to prevent pregnancy in women. The analysis of the ECA and MPA combination reveals a challenge due to the strong overlap of the spectra of these compounds.

Objective: Spectrophotometry techniques along with chemometrics methods are simple, fast, precise, and low-cost for the simultaneous determination of ECA and MPA in a combined pharmaceutical dosage form.

Methods: Two developed approaches, the least-squares support vector machine (LSSVM) and fuzzy inference system (FIS), along with a spectrophotometric method were proposed to solve such a challenging overlap.

Results: Based on the cross-validation method, the regularization parameter (γ) and width of the function (σ) in the LSSVM model were optimized and the root mean square error (RMSE) values were found to be 0.3957 and 0.2839 for ECA and MDA, respectively. The mean recovery values were 99.87 and 99.63% for ECA and MDA, respectively. The FIS coupled with principal component analysis (PCA) showed mean recovery percentages equal to 99.05 and 99.50% for ECA and MDA, respectively. Also, the RMSE of both components was lower than 0.3.

Conclusion: The analysis results of a real sample (injection suspension) using the proposed methods were compared with HPLC by a one-way analysis of variance (ANOVA) test, and no significant differences were found in the results.

Highlights: Intelligent methods were proposed for the simultaneous determination of ECA and MPA. The least-squares support vector machine and fuzzy inference system along with spectrophotometry were used. HPLC as a reference method was performed and compared with chemometrics methods. The benefits of the proposed approaches are that they are rapid, simple, low-cost, and accurate.