ABSTRACT Efficient recovery of phenolic compounds is critical for valorizing Crataegus songarica K. Koch for food and nutraceutical applications. Conventional maceration (CM) is often limited by low extraction efficiency and prolonged processing time, whereas energy‐assisted techniques may enhance extraction performance but still lack comprehensive data‐driven assessment. In this study, conventional maceration, ultrasound‐assisted extraction (UAE), microwave‐assisted extraction (MAE), and infrared‐assisted extraction (IRAE) were comparatively evaluated using total identified phenolics and individual flavonoids as response variables. Under the investigated extraction conditions, MAE achieved the highest phenolic recovery (158.82 ± 4.37 mg 100 g − 1 ) following 0.5 min of microwave irradiation combined with a subsequent reflux‐assisted extraction stage, compared with 70.15 ± 2.14 mg 100 g − 1 obtained by CM after 60 min, while IRAE and UAE yielded 129.77 ± 3.18 and 83.32 ± 2.11 mg 100 g − 1 , respectively. Chemometric analyses, including principal component analysis and hierarchical cluster analysis, clearly differentiated extraction modes, primarily according to temperature, solvent concentration, and dry‐matter content. Predictive modeling was performed using Ridge regression, random forest, support vector machine, XGBoost, and multilayer‐perceptron artificial neural network models under nested cross‐validation conditions. Among the tested approaches, XGBoost provided the strongest predictive performance (cross‐validated R 2 ≈ 0.76, RMSE ≈ 27 mg 100 g − 1 , MeanAE ≈ 21 mg 100 g − 1 ) and identified temperature and dry matter as the dominant variables controlling phenolic recovery. The results demonstrate that integrating controlled extraction experiments with interpretable machine learning approaches provides a scalable and potentially resource‐efficient framework for optimizing phenolic extraction from hawthorn and related bioactive plant materials.
Zokirova et al. (2026) studied this question.