Predictive models for the effect of environmental factors on the abundance of Vibrio parahaemolyticus in oyster farms in Taiwan using extreme gradient boosting

Machine learning to predict the relationship between Vibrio spp. concentrations in seawater and oysters and prevalent environmental conditions

Vibrio parahaemolyticus and Vibrio vulnificus are bacteria with a significant public health impact. Identifying factors impacting their presence and concentrations in food sources could enable the identification of significant risk factors and prevent incidences of foodborne illness. In recent years, machine learning has shown promise in modeling microbial presence based on prevalent external and internal variables, such as environmental variables and gene presence/absence, respectively, particularly with the generation and availability of large amounts and diverse sources of data. Such analyses can prove useful in predicting microbial behavior in food systems, particularly under the influence of the constant changes in environmental variables. In this study, we tested the efficacy of six machine learning regression models (random forest, support vector machine, elastic net, neural network, k-nearest neighbors, and extreme gradient boosting) in predicting the relationship between environmental variables and total and pathogenic V. parahaemolyticus and V. vulnificus concentrations in seawater and oysters. In general, environmental variables were found to be reliable predictors of total and pathogenic V. parahaemolyticus and V. vulnificus concentrations in seawater, and pathogenic V. parahaemolyticus in oysters (Acceptable Prediction Zone >70 %) when analyzed using our machine learning models. SHapley Additive exPlanations, which was used to identify variables influencing Vibrio concentrations, identified chlorophyll a content, seawater salinity, seawater temperature, and turbidity as influential variables. It is important to note that different strains were differentially impacted by the same environmental variable, indicating the need for further research to study the causes and potential mechanisms of these variations. In conclusion, environmental variables could be important predictors of Vibrio growth and behavior in seafood. Moreover, the models developed in this study could prove invaluable in assessing and managing the risks associated with V. parahaemolyticus and V. vulnificus, particularly in the face of a changing environment.

Advancements in Predictive Microbiology: Integrating New Technologies for Efficient Food Safety Models

Predictive microbiology is a rapidly evolving field that has gained significant interest over the years due to its diverse application in food safety. Predictive models are widely used in food microbiology to estimate the growth of microorganisms in food products. These models represent the dynamic interactions between intrinsic and extrinsic food factors as mathematical equations and then apply these data to predict shelf life, spoilage, and microbial risk assessment. Due to their ability to predict the microbial risk, these tools are also integrated into hazard analysis critical control point (HACCP) protocols. However, like most new technologies, several limitations have been linked to their use. Predictive models have been found incapable of modeling the intricate microbial interactions in food colonized by different bacteria populations under dynamic environmental conditions. To address this issue, researchers are integrating several new technologies into predictive models to improve efficiency and accuracy. Increasingly, newer technologies such as whole genome sequencing (WGS), metagenomics, artificial intelligence, and machine learning are being rapidly adopted into newer-generation models. This has facilitated the development of devices based on robotics, the Internet of Things, and time-temperature indicators that are being incorporated into food processing both domestically and industrially globally. This study reviewed current research on predictive models, limitations, challenges, and newer technologies being integrated into developing more efficient models. Machine learning algorithms commonly employed in predictive modeling are discussed with emphasis on their application in research and industry and their advantages over traditional models.

Characterization of a Vibrio parahaemolyticus-targeting lytic bacteriophage SSJ01 and its application in artificial seawater

Vibrio parahaemolyticus is a major foodborne pathogen causing serious illnesses. In this study, a new lytic bacteriophage SSJ01 that infects V. parahaemolyticus was isolated and characterized. It had a short non-contractile tail and belonged to the Caudoviricetes class. It rapidly adsorbed onto host cells, exhibited a short latent period, and has a large burst size. It showed lytic activities under a broad range of temperature (- 18 to 60 °C), pH (5 to 11), and salinity (0 to 6%). It contained 35 open reading frames with a G + C content of 49.16% without toxic or lysogen-forming genes. The MOI of 105 phage-treated group in vitro reduced the target cells up to 3.49-log CFU/mL at 6 °C and 3.47-log CFU/mL at 25 °C, respectively. In aquatic environments (6 and 25 °C), bactericidal activities showed a significant decrease within 2 h. Therefore, the bacteriophage SSJ01 has potential as a biocontrol agent to control V. parahaemolyticus in marine culture.

Modeling naturally-occurring Vibrio parahaemolyticus in post-harvest raw shrimps

There is little known about the growth and survival of naturally-occurring Vibrio parahaemolyticus in harvested raw shrimps. In this study, the fate of naturally-occurring V. parahaemolyticus in post-harvest raw shrimps was investigated from 4℃ to 30℃ using real-time PCR combined with propidium monoazide (PMA-qPCR). The Baranyi-model was used to fit the growth and survival data. A square root model and non-linear Arrhenius model was then used to quantify the parameters derived from the Baranyi-model. The results showed that naturally-occurring V. parahaemolyticus were slowly inactivated at 4℃ and 7℃ with deactivation rates of 0.019 Log CFU/g/h and 0.025 Log CFU/g/h. Conversely, at 15, 20, 25, and 30 °C, the average maximum growth rates (μmax) of naturally-occurring V. parahaemolyticus were determined to be 0.044, 0.105, 0.179 and 0.336 Log CFU/g/h, accompanied by the average lag phases (λ) of 15.5 h, 7.3 h, 4.4 h and 3.7 h. The validation metrics, Af and Bf, for both the square root model and non-linear, indicating that the model had a good ability to predict the growth behavior of naturally-occurring V. parahaemolyticus in post-harvest raw shrimps. Furthermore, a comparative exploration between the growth of artificially contaminated V. parahaemolyticus in cooked shrimps and naturally-occurring V. parahaemolyticus in post-harvest raw shrimps revealed intriguing insights. While no substantial distinction in deactivation rates emerged at 4 °C and 7 °C (P > 0.05), a discernible disparity in growth rates was observable at 15 °C, 20 °C, 25 °C, and 30 °C, with the former surpassing the latter. Which indicated the risk of V. parahaemolyticus using models derived from cooked shrimps may be biased. Our study also unveiled a discernible seasonal effect. The μmax and λ of V. parahaemolyticus in shrimps harvested in summer were similar to those harvested in autumn, while the initial and maximum bacterial concentration harvested in summer were higher than those harvested in autumn. This predictive microbiology model of naturally-occurring V. parahaemolyticus in raw shrimps provides relevance to modelling growth in situ.

Artificial Intelligence in Food Safety: A Decade Review and Bibliometric Analysis

Artificial Intelligence (AI) technologies have been powerful solutions used to improve food yield, quality, and nutrition, increase safety and traceability while decreasing resource consumption, and eliminate food waste. Compared with several qualitative reviews on AI in food safety, we conducted an in-depth quantitative and systematic review based on the Core Collection database of WoS (Web of Science). To discover the historical trajectory and identify future trends, we analysed the literature concerning AI technologies in food safety from 2012 to 2022 by CiteSpace. In this review, we used bibliometric methods to describe the development of AI in food safety, including performance analysis, science mapping, and network analysis by CiteSpace. Among the 1855 selected articles, China and the United States contributed the most literature, and the Chinese Academy of Sciences released the largest number of relevant articles. Among all the journals in this field, PLoS ONE and Computers and Electronics in Agriculture ranked first and second in terms of annual publications and co-citation frequency. The present character, hot spots, and future research trends of AI technologies in food safety research were determined. Furthermore, based on our analyses, we provide researchers, practitioners, and policymakers with the big picture of research on AI in food safety across the whole process, from precision agriculture to precision nutrition, through 28 enlightening articles.

Microbiological Quality of Oysters and Mussels Along Its Market Supply Chain

Oysters and mussels are known vectors of foodborne pathogens because of their immobile and filter-feeding nature leading to the accumulation of biological particles in their tissues. Accumulated bacteria which comes from the culture environment and unsanitary handling can cause food poisoning if these shellfish are consumed raw or partially processed. This study determined the incidence of bacterial pathogen contamination along the different channels of the oyster and mussel supply chain through a time-distribution simulation analysis. First, the route of the fresh bivalve products from a local farm to its market was established through interviews. From the data gathered, a simulation experiment was conducted following the observed time-temperature conditions and the actual bulk packaging material used by the traders. The presence of target pathogens Escherichia coli, Salmonella spp., Vibrio parahaemolyticus, and Vibrio cholerae were detected using standard conventional culture techniques. Initial E. coli counts in both mussels and oysters were higher than the safety limit of 330 MPN in 100 g tissue. Interestingly, E. coli counts in mussels decreased after 6 h and maintained low numbers after more than 24 h postharvest. Counts in oysters however increased to 1000 MPN in 100 g tissue. V. parahaemolyticus in mussels and oysters showed a gradual increase in counts with increasing holding time albeit in numbers that are lower than the safety limit of 1000 cfu g^-1 tissue. Qualitative detection of Salmonella and V. cholerae showed the presence of both pathogens in all the sampling points. All four pathogens were also detected in the culture waters and in the sediment. Results of the study showed that the culture environment and the handling practices contribute greatly to the pathogen contamination in oysters and mussels.

Artificial Intelligence Models for Zoonotic Pathogens: A Survey

Zoonotic diseases or zoonoses are infections due to the natural transmission of pathogens between species (animals and humans). More than 70% of emerging infectious diseases are attributed to animal origin. Artificial Intelligence (AI) models have been used for studying zoonotic pathogens and the factors that contribute to their spread. The aim of this literature survey is to synthesize and analyze machine learning, and deep learning approaches applied to study zoonotic diseases to understand predictive models to help researchers identify the risk factors, and develop mitigation strategies. Based on our survey findings, machine learning and deep learning are commonly used for the prediction of both foodborne and zoonotic pathogens as well as the factors associated with the presence of the pathogens.

Depuration of live oysters to reduce Vibrio parahaemolyticus and Vibrio vulnificus: A review of ecology and processing parameters

Consumption of raw oysters, whether wild-caught or aquacultured, may increase health risks for humans. Vibrio vulnificus and Vibrio parahaemolyticus are two potentially pathogenic bacteria that can be concentrated in oysters during filter feeding. As Vibrio abundance increases in coastal waters worldwide, ingesting raw oysters contaminated with V. vulnificus and V. parahaemolyticus can possibly result in human illness and death in susceptible individuals. Depuration is a postharvest processing method that maintains oyster viability while they filter clean salt water that either continuously flows through a holding tank or is recirculated and replenished periodically. This process can reduce endogenous bacteria, including coliforms, thus providing a safer, live oyster product for human consumption; however, depuration of Vibrios has presented challenges. When considering the difficulty of removing endogenous Vibrios in oysters, a more standardized framework of effective depuration parameters is needed. Understanding Vibrio ecology and its relation to certain depuration parameters could help optimize the process for the reduction of Vibrio. In the past, researchers have manipulated key depuration parameters like depuration processing time, water salinity, water temperature, and water flow rate and explored the use of processing additives to enhance disinfection in oysters. In summation, depuration processing from 4 to 6 days, low temperature, high salinity, and flowing water effectively reduced V. vulnificus and V. parahaemolyticus in live oysters. This review aims to emphasize trends among the results of these past works and provide suggestions for future oyster depuration studies.

Nested Spatial and Temporal Modeling of Environmental Conditions Associated With Genetic Markers of Vibrio parahaemolyticus in Washington State Pacific Oysters

The Pacific Northwest (PNW) is one of the largest commercial harvesting areas for Pacific oysters (Crassostrea gigas) in the United States. Vibrio parahaemolyticus, a bacterium naturally present in estuarine waters accumulates in shellfish and is a major cause of seafood-borne illness. Growers, consumers, and public-health officials have raised concerns about rising vibriosis cases in the region. Vibrio parahaemolyticus genetic markers (tlh, tdh, and trh) were estimated using an most-probable-number (MPN)-PCR technique in Washington State Pacific oysters regularly sampled between May and October from 2005 to 2019 (N = 2,836); environmental conditions were also measured at each sampling event. Multilevel mixed-effects regression models were used to assess relationships between environmental measures and genetic markers as well as genetic marker ratios (trh:tlh, tdh:tlh, and tdh:trh), accounting for variation across space and time. Spatial and temporal dependence were also accounted for in the model structure. Model fit improved when including environmental measures from previous weeks (1-week lag for air temperature, 3-week lag for salinity). Positive associations were found between tlh and surface water temp, specifically between 15 and 26°C, and between trh and surface water temperature up to 26°C. tlh and trh were negatively associated with 3-week lagged salinity in the most saline waters (> 27 ppt). There was also a positive relationship between tissue temperature and tdh, but only above 20°C. The tdh:tlh ratio displayed analogous inverted non-linear relationships as tlh. The non-linear associations found between the genetic targets and environmental measures demonstrate the complex habitat suitability of V. parahaemolyticus. Additional associations with both spatial and temporal variables also suggest there are influential unmeasured environmental conditions that could further explain bacterium variability. Overall, these findings confirm previous ecological risk factors for vibriosis in Washington State, while also identifying new associations between lagged temporal effects and pathogenic markers of V. parahaemolyticus.