Abstract: AIM: To evaluate the bioequivalence of two candesartan cilexetil tablet formulations in healthy Chinese subjects after administration of a single dose, and an artificial neural network model was established to predict the candesartan plasma concentration, and provide a basis for clinical rational use of drugs.  METHODS: Thirty-two healthy Chinese subjects were enrolled for oral administration of a single 8 mg dose of candesartan cilexetil tablet (test or reference product) under fasting or fed conditions to conduct a bioequivalence study. The bioequivalence results were used to build a back-propagation artificial neural network model by MATLAB software, and the model was internally and externally verified to predict the plasma concentration. RESULTS: Under both fasting and fed conditions, the Cmax, AUC0-t, and AUC0-∞ of the test product were all fall within 80.00%-125.00% of the reference product, indicating the two formulations were bioequivalent. The candesartan plasma concentration prediction model was constructed by MATLAB software. The performance verification result of MSE is 0.000 781, the gradient amplitude is 0.000 432, the number of verification checks is 0. Good correlation coefficients are showed in the training group, the verification group, and the prediction group (r>0.99). CONCLUSION: The test and the reference product of candesartan cilexetil are bioequivalent under fasting and fed conditions. The established prediction model can accurately predict the candesartan plasma concentration in humans after oral administration. It may provide a basis for clinical rational use of drugs.

Key words: candesartan cilexetil tablet, bioequivalence, artificial neural network, plasma concentration, precision medicine