Optimization of microwave-assisted polyphenol extraction and antioxidant activity from papaya peel using response surface methodology and artificial neural network

The objective of the present study is to determine the optimal conditions of microwave-assisted extraction (MAE) such as microwave power (MWP), irradiation time (I-time), ethanol concentration (EtOH%), and solvent-to-solid ratio (S/S) for maximizing total polyphenol content (TPC) and 2,2-diphenyl-1-picrylhydrazyl (DPPH) radical scavenging activity from papaya peel. Box-Behnken design (BBD) was used considering MWP 300–600 W, I-time 60-120 s, EtOH% 30-70%, and S/S 30-70 mL/g. Additionally, response surface methodology (RSM) and artificial neural networks (ANN) were employed for modelling, with cross-validation to enhance reliability. These models were combined with the desirability function (DF) and/or genetic algorithm (GA) optimization approaches. Maximizing TPC and DPPH activity while maintaining MWP, I-time, EtOH%, and S/S within their respective ranges using hybrid optimization approaches (RSM-DF: TPC = 1058 mgGAE/100g, and DPPH = 83%, RSM-GA: TPC = 1064 mgGAE/100g and DPPH = 79%, and ANN-GA: TPC = 1086 mgGAE/100g, and DPPH = 83%,) yielded consistent optimal results. An additional optimization approach (RSM-DF: TPC = 955 mgGAE/100g, and DPPH = 90%), aimed at minimizing MWP, I-time, EtOH%, and S/S while maximizing TPC and DPPH activity, showed a significant reduction of approximately 3 L in ethanol consumption for each 100 g of dry samples. The maximized TPC and DPPH activity in all four approaches showed a significant ( p < 0.05) alignment with their corresponding validation tests, demonstrating the better performance of these modelling and optimization processes. In terms of assessing the effectiveness of microwave assistance, conventional solvent extraction was also performed, maintaining a 70 mL/g S/S ratio of 55% ethanol at 60°C for 2 h. This method resulted in lower values of TPC (857 ± 23 g GAE/100g) yield and DPPH activity (72 ± 5%) compared to the optimized condition of MAE.