# Forecasting Foodborne Disease Risk Caused by Vibrio parahaemolyticus Using a SARIMAX Model Incorporating Sea Surface Environmental and Climate Factors: Implications for Seafood Safety in Zhejiang, China

## TL;DR

This study uses a SARIMAX model to predict Vibrio parahaemolyticus foodborne disease risk in Zhejiang, China, based on environmental and climate factors.

## Contribution

A novel SARIMAX model incorporating marine and climate factors for forecasting Vibrio parahaemolyticus detection rates.

## Key findings

- Vibrio parahaemolyticus detection rates peak in summer and follow cyclical patterns.
- The SARIMAX model accurately forecasts detection rates with a mean absolute error of 0.047.
- Meteorological and marine factors have specific lag effects on Vibrio parahaemolyticus detection.

## Abstract

Vibrio parahaemolyticus is a prevalent pathogen responsible for foodborne diseases in coastal regions. Understanding its dynamic relationship with various meteorological and marine factors is crucial for predicting outbreaks of bacterial foodborne illnesses. This study analyzes the occurrence of V. parahaemolyticus-induced foodborne illness in Zhejiang Province, China, from 2014 to 2018, using an 8-day time unit based on the temporal characteristics of marine products. The detection rate of V. parahaemolyticus exhibited a distinct cyclical pattern, peaking during the summer months. Meteorological and marine factors showed varying lag effects on the detection of V. parahaemolyticus, with specific lag periods as follows: sunshine duration (3 weeks), air temperature (3 weeks), total precipitation (8 weeks), relative humidity (7 weeks), sea surface temperature (1 week), and sea surface salinity (8 weeks). The SARIMAX model, which incorporates both marine and climatic factors, was developed to facilitate short-term forecasts of V. parahaemolyticus detection rates in coastal cities. The model’s performance was evaluated, and the actual values consistently fell within the 95% confidence interval of the predicted values, with a mean absolute error (MAE) of 0.047, indicating high accuracy. This framework provides both theoretical and practical insights for predicting and preventing future foodborne disease outbreaks. These findings can support food industry stakeholders—such as seafood suppliers, restaurants, regulatory agencies, and healthcare institutions—in anticipating high-risk periods and implementing targeted measures. These include enhancing cold chain management, conducting timely seafood inspections, strengthening cross-contamination controls during seafood processing, dynamically adjusting market surveillance intensity, and improving hygiene practices. In addition, hospitals and local health departments can use the model’s forecasts to allocate medical resources such as beds, medications, and staff in advance to better prepare for seasonal surges in foodborne illness.