Influenza prediction and monitoring early warning method

• Main Authors: SON SEUNG-WOOK, YANG GAOCHAO, LI XIN, HOU YONGSHENG
• Format: Patent
• Language: Chinese; English
• Published: 21.06.2024
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; PHYSICS

The invention particularly relates to an influenza predicting and monitoring early warning method. According to the influenza predicting and monitoring early warning method, time granularity is defined, and based on ILI% of a previous time granularity, weather conditions and network search data, an SARIMA time sequence model and an XGBoost multiple regression analysis algorithm are used to predict ILI% of a future time granularity; and a risk adjustment CUSUM control chart model is combined to monitor the flu and perform early warning on flu outbreak. The influenza prediction and monitoring early warning method improves the prediction precision of the influenza sample case percentage (ILI%), and can timely and accurately perform early warning prompt on large-scale influenza outbreak so as to take prevention measures before an influenza threat comes, provide a data basis for a public health department to make a decision, help a medical institution prepare resources in advance, and improve the safety of the med