Machine learning–optimized ultrasound processing of mealworm-enriched apple vinegar

Machine learning–based modelling and multi-objective optimization were applied to evaluate the effects of ultrasound-assisted processing on mealworm flour-enriched apple vinegar. The influences of mealworm flour concentration, ultrasound amplitude, and treatment time on total phenolic content (TPC) and antioxidant activity (DPPH) were investigated using regression-based machine learning algorithms and Pareto-based optimization approaches. Among the evaluated models, the Poly2-ElasticNet model showed the best LOOCV performance and the lowest prediction error within the investigated dataset. Multi-objective optimization identified the most balanced operating conditions for maximizing both TPC and DPPH responses. Under optimized conditions, the combined mealworm flour fortification and ultrasound treatment resulted in higher bioactive values than the untreated and thermally pasteurized unfortified samples. The optimized ultrasound-treated mealworm-enriched vinegar exhibited the highest TPC (121.73 mg GAE/100 mL), DPPH radical-scavenging activity (61.69%), and total flavonoid content (32.16 mg CE/100 mL). HPLC-DAD analysis revealed that procyanidin B2, epicatechin, andchlorogenic acid were among the predominant phenolic compounds in AV-OPT-MW-US, and their concentrations were significantly higher than in AV-PAS. SPME-GC–MS analysis showed that several esters and alcohols were numerically higher in AV-OPT-MW-US than in AV-PAS, although they remained below the levels in AV-CON. In addition, LC–MS/MS analysis showed increased levels of amino acids, including glutamic acid, alanine, leucine, valine, and lysine, reflecting the amino acids supplied by mealworm flour fortification. Overall, mealworm flour fortification combined with optimized ultrasound processing yielded apple vinegar with higher measured amino acid concentrations and chemical antioxidant responses than the unfortified controls. Further studies are needed to determine the nutritional relevance, sensory acceptance, storage stability, and scalability of the resulting formulation. The findings highlight the potential of edible insect fortification and advanced optimization technologies for the development of sustainable functional fermented foods.

Authors

Institutions

Publication Details

Journal
Frontiers in Nutrition
Published
2026-11-18
DOI
https://doi.org/10.3389/fnut.2026.2006029
Primary Topic
Phytochemicals and Antioxidant Activities
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Machine learning–optimized ultrasound processing of mealworm-enriched apple vinegar

Okan Levent, Dilek DÜLGER ALTINER, Filiz Aksu, Remzi Gürfidan et al.
2 links
Frontiers in Nutrition
Phytochemicals and Antioxidant Activities
article

Machine learning–optimized ultrasound processing of mealworm-enriched apple vinegar

Okan Levent, Dilek DÜLGER ALTINER, Filiz Aksu, Remzi Gürfidan, Seydi Yıkmış, Enes Açıkgözoğlu, Nazan Tokatlı Demirok, Marwa Ezz El-Din Ibrahim, Sema Sandıkçı Altunatmaz, Deniz Aktaran Bala, Melikenur Türkol Gündüz
article en

Abstract

Machine learning–based modelling and multi-objective optimization were applied to evaluate the effects of ultrasound-assisted processing on mealworm flour-enriched apple vinegar. The influences of mealworm flour concentration, ultrasound amplitude, and treatment time on total phenolic content (TPC) and antioxidant activity (DPPH) were investigated using regression-based machine learning algorithms and Pareto-based optimization approaches. Among the evaluated models, the Poly2-ElasticNet model showed the best LOOCV performance and the lowest prediction error within the investigated dataset. Multi-objective optimization identified the most balanced operating conditions for maximizing both TPC and DPPH responses. Under optimized conditions, the combined mealworm flour fortification and ultrasound treatment resulted in higher bioactive values than the untreated and thermally pasteurized unfortified samples. The optimized ultrasound-treated mealworm-enriched vinegar exhibited the highest TPC (121.73 mg GAE/100 mL), DPPH radical-scavenging activity (61.69%), and total flavonoid content (32.16 mg CE/100 mL). HPLC-DAD analysis revealed that procyanidin B2, epicatechin, andchlorogenic acid were among the predominant phenolic compounds in AV-OPT-MW-US, and their concentrations were significantly higher than in AV-PAS. SPME-GC–MS analysis showed that several esters and alcohols were numerically higher in AV-OPT-MW-US than in AV-PAS, although they remained below the levels in AV-CON. In addition, LC–MS/MS analysis showed increased levels of amino acids, including glutamic acid, alanine, leucine, valine, and lysine, reflecting the amino acids supplied by mealworm flour fortification. Overall, mealworm flour fortification combined with optimized ultrasound processing yielded apple vinegar with higher measured amino acid concentrations and chemical antioxidant responses than the unfortified controls. Further studies are needed to determine the nutritional relevance, sensory acceptance, storage stability, and scalability of the resulting formulation. The findings highlight the potential of edible insect fortification and advanced optimization technologies for the development of sustainable functional fermented foods.

Frontiers in NutritionVol. 13
Tekirdağ Namık Kemal University (TR), Inonu University (TR), Istanbul University-Cerrahpaşa (TR), Isparta University of Applied Sciences (TR), King Faisal University (SA), Kocaeli Üniversitesi (TR), Istanbul University (TR)
Zero hunger
Phytochemicals and Antioxidant Activities
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon