A New Integrated Interpolation Method for High Missing Unstable Disease Surveillance Data — 12 Urban Agglomerations, China, 2009–2020

Abstract

Introduction The prevalence of unstable and incomplete monitoring data significantly complicates syndromic analysis. Many data interpolation methods currently available demonstrate inadequate effectiveness in overcoming this issue. Methods To improve the accuracy of interpolation, we propose the integration of the SHapley Additive exPlanation model (SHAP) with the structural equation model (SEM), forming a combined SHAP-SEM approach. A case study is then performed to assess the enhanced performance of this novel model compared to traditional methods. Results The SHAP-SEM model was utilized to develop an interpolation model employing data from the Chinese respiratory syndrome surveillance database. We executed three distinct experiments to establish the model datasets, comprising a total of 100 replicates. The performance of the model was evaluated using the root mean square error (RMSE), correlation coefficient (r), and F-score. The findings demonstrate that the SHAP-SEM model consistently achieves superior accuracy in data interpolation, which is evident across different seasons and in overall performance. Discussion We conclude that the SHAP-SEM model demonstrates an exceptional capacity for accurately interpolating volatile and incomplete data. This capability is crucial for developing a comprehensive database that is essential for conducting risk assessments related to syndromes.