In vitro and in vivo comparison of the anti-staphylococcal efficacy of generic products and the innovator of oxacillin

Abstract

Background: Oxacillin continues to be an important agent in the treatment of staphylococcal infections; many generic products are available and the only requirement for their approval is demonstration of pharmaceutical equivalence. We tested the assumption that pharmaceutical equivalence predicts therapeutic equivalence by comparing 11 generics with the innovator product in terms of concentration of the active pharmaceutical ingredient (API), minimal inhibitory (MIC) and bactericidal concentrations (MBC), and antibacterial efficacy in the neutropenic mouse thigh infection model.

Methods: The API in each product was measured by a validated microbiological assay and compared by slope (potency) and intercept (concentration) analysis of linear regressions. MIC and MBC were determined by broth microdilution according to Clinical and Laboratory Standard Institute (CLSI) guidelines. For in vivo efficacy, neutropenic ICR mice were inoculated with a clinical strain of Staphylococcus aureus. The animals had 4.14 +/- 0.18 log10 CFU/thigh when treatment started. Groups of 10 mice per product received a total dose ranging from 2.93 to 750 mg/kg per day administered q1h. Sigmoidal dose-response curves were generated by nonlinear regression fitted to Hill equation to compute maximum effect (Emax), slope (N), and the effective dose reaching 50% of the Emax (ED50). Based on these results, bacteriostatic dose (BD) and dose needed to kill the first log of bacteria (1LKD) were also determined.

Results: 4 generic products failed pharmaceutical equivalence due to significant differences in potency; however, all products were undistinguishable from the innovator in terms of MIC and MBC. Independently of their status with respect to pharmaceutical equivalence or in vitro activity, all generics failed therapeutic equivalence in vivo, displaying significantly lower Emax and requiring greater BD and 1LKD, or fitting to a non-sigmoidal model.

Conclusions: Pharmaceutical or in vitro equivalence did not entail therapeutic equivalence for oxacillin generic products, indicating that criteria for approval deserve review to include evaluation of in vivo efficacy.

Figure 1

Concentration-response relationship of innovator and generic products of oxacillin in the microbiological assay. A. The slopes and intercepts of OXA-BLA, OXA-COL, OXA-OPH, OXA-PEN, and OXA-SCA were not statistically different from those of OXA-BMS (innovator), thus confirming their pharmaceutical equivalence (P = 0.1165). The standard curves of all products are better described by a single linear regression, shown here with the 95% confidence interval. B. The slopes and intercepts of OXA-CAR, OXA-EXP, OXA-MEM and OXA-VIT were significantly different to the innovator's (P < 0.03458), thus failing pharmaceutical equivalence. As generic products belong to populations different to that of the innovator, each is described by an independent linear regression with their respective coefficient of determination (r²).

Figure 2

Dose-response relationship of innovator oxacillin (OXA-BMS) in 4 independent experiments in the neutropenic mouse thigh infection model, fitted to Hill's model by NLR. The four experiments (gray lines) were indistinguishable by curve fitting analysis (CFA), thus a single regression (red curve) described them better than 4 individual regressions.

Figure 3

Dose-response relationship of the innovator and 9 generic products of oxacillin in the neutropenic mouse thigh infection model. OXA-BMS (innovator, black curve) and 8 generics fitted to Hill's sigmoid model, while generic product OXA-SER fitted to the Gaussian U-shaped model (red curve). Regardless of pharmaceutical equivalence and in vitro activity, all generics displayed significantly inferior bactericidal efficacy (P < 0.0001) or different pharmacodynamic behavior (Gaussian instead of sigmoid) compared with the innovator, thus lacking therapeutic equivalence.