AI verification for spirulina’s antimicrobial power in total coliform and Staphylococcus aureus isolated from tilapia fillet

Abstract

Seafood products, including fresh tilapia fillets, are highly susceptible to rapid quality deterioration due to microbial contamination, posing a significant concern for food safety and public health. This study investigated, both experimentally and through artificial intelligence modeling, the antimicrobial activity of Spirulina platensis (SP) extracts against two common foodborne pathogens: total coliforms and Staphylococcus aureus (S. aureus). SP extracts were obtained using the freeze-thaw method at concentrations of 0.5%, 1%, and 5% (w/v), labeled as EA, EB, and EC, respectively. Microbial analysis was conducted on 25 fresh Nile tilapia fillets. Each fish was divided into four quarters: one served as the control, while the remaining three were treated with the different SP extract concentrations. Bacterial counts were recorded before treatment and at 1, 24, and 48 h post-treatment, with samples stored at 4 °C throughout. The antimicrobial activity of the SP extracts was modeled using Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) models. The results indicated that SP extracts effectively reduced total coliform and S. aureus counts in the treated fish fillets. Both ANN and ANFIS models accurately predicted the reduction in microbial counts, validating the experimental results. Among the treatments, EC (5% concentration) exhibited the highest antimicrobial activity, outperforming EB and EA. These findings suggest that SP extracts hold promise as a natural preservative for seafood and other food products, contributing to food safety and public health protection. Future research should focus on identifying and characterizing the bioactive compounds in SP extracts across different food matrices, with potential applications in the development of functional foods and novel therapeutics.