Smart Analysis and Decision-Making for Emerging Infectious Diseases

This is a multicenter, cluster‐randomized controlled trial (cRCT) with a single‐blinddesign (blinding of statisticians). The study will be conducted across fiveprovinces/municipalities: Guangdong, Zhejiang, Hubei, Sichuan, and Shanghai. At least 36district/county‐level Centers for Disease Control and Prevention (CDCs) will be selectedas study clusters and allocated in an approximately 1:1 ratio to either the interventiongroup or the control group. Three eligible CDC staff members will be enrolled from eachparticipating cluster, including one CDC director or relevant leader responsible forinfectious disease prevention and control and two professional staff members engaged inacute infectious disease surveillance, risk assessment, decision‐making, or emergencyresponse.Randomization Procedure: For the four provinces (Zhejiang, Guangdong, Hubei, andSichuan), participating district/county‐level CDC clusters will be stratified within eachprovince according to socioeconomic level (high, medium, and low), as applicable, andrandomly allocated within strata to the intervention or control group. For Shanghaimunicipality, participating district‐level CDC clusters will be stratified by urbanfunctional zone (central urban vs. new/suburban districts) and randomly allocated withinstrata. Cluster allocation will be maintained in an approximately 1:1 ratio.Intervention: The intervention group will use a multi‐agent integrated toolkit (includingdata‐knowledge agent, assessment agent, decision agent, and evaluation agent) to assistwith epidemic risk perception, situational assessment, and emergency decision‐making, inaddition to routine practices. The control group will follow routine practices only.Follow‐up Plan: The intervention period is 3 months, timed to coincide with peak seasonsfor specific infectious diseases (winter/spring for respiratory infections; summer/autumnfor vector‐borne diseases like dengue). Follow‐up assessments will occur every 3 months,with the endpoint defined as the conclusion of an emerging infectious disease event.Sample Size: Using PASS software (two‐sided α=0.05, Power=80%, ICC=0.05, CV=0.5, standarddeviation=12 hours, and average cluster size m=3), and assuming a 30% reduction inresponse time in the intervention group, a minimum of 32 evaluable clusters,corresponding to 16 clusters per group and 96 evaluable participants, is required.Because only 3 participants will be enrolled from each cluster and an individualattrition rate of approximately 10% is anticipated, at least 36 clusters and at least 108participants will be recruited. The final anticipated enrollment will equal three timesthe actual number of participating clusters.Data Management: Dual independent data entry will be performed. Data will be stored onPeking University's encrypted servers, with backups on the university cloud platform andoffline encrypted hard drives (AES‐256 encryption). All data will be physically destroyedafter the retention period.Missing Data: Analysis will follow the intention‐to‐treat (ITT) principle. Missingprimary outcome data will be handled using the last observation carried forward (LOCF)method.Safety Evaluation: Adverse events include headache and absenteeism, classified using afive‐level attribution scale (definitely, probably, possibly, probably not, definitelynot related), with the first three categories counted as adverse reaction rates. Anyserious adverse event must be reported immediately to the sponsor and/or ethicscommittee.Early Termination: The study may be terminated early under the following conditions: (1)identification of serious safety issues; (2) the toolkit proves ineffective or futile;(3) major protocol flaws or implementation deviations; (4) request by the applicant oradministrative authority.