Risk prediction of encephalitis in hand, foot and mouth disease: a nomogram model based on platelet indices for resource-limited settings

This study aimed to assess differences in peripheral blood platelet indices including platelet count (PLT), mean platelet volume (MPV), platelet distribution width (PDW), and the platelet-to-lymphocyte ratio (PLR) between children with hand, foot and mouth disease (HFMD) complicated by encephalitis and those with uncomplicated HFMD. A further objective was to develop a robust predictive model for HFMD complicated by encephalitis, specifically designed for resource-limited clinical settings. This retrospective study enrolled children with HFMD who were hospitalized at the Children’s Hospital of Soochow University between January 2015 and December 2020. The participants were categorized into two groups: an encephalitis group (HFMD complicated by encephalitis) and a control group (those with uncomplicated HFMD). The baseline data, clinical features and platelet indices of the children in the two groups were then compared. Binary logistic regression analysis was used to identify the risk factors for HFMD complicated by encephalitis, and a nomogram prediction model for HFMD complicated by encephalitis was developed based on these risk factors. The risk factors in children with HFMD complicated by encephalitis included fever for more than 3 days, listlessness, headache, limb myoclonus, positive neck resistance and/or pathological signs, and certain PLT, PDW, and PLR values. These risk factors were used to construct a simple and practical nomogram prediction model for HFMD complicated by encephalitis, which demonstrated strong predictive performance with an area under the curve (AUC) of 0.902, along with satisfactory calibration and stability upon validation. The nomogram prediction model of platelet indices (PLT, PDW and PLR) combined with clinical risk factors demonstrated a robust predictive capacity for HFMD complicated by encephalitis. Not applicable.