Development and Validation of a Nomogram for Predicting Severe Respiratory Illness in Children with Isolated Human Metapneumovirus Infection

Background/Objectives: Human metapneumovirus (hMPV) is a leading cause of acute respiratory tract infections in children, but comorbidities and mixed infections have confounded most previous studies. This study aimed to develop an early prediction model for severe respiratory illness in children with isolated hMPV infection. Methods: This retrospective study enrolled 540 children with isolated hMPV infection (without comorbidities or mixed infections) hospitalised between February 2022 and January 2024. Severe respiratory illness was defined according to British Thoracic Society guidelines. Multivariable logistic regression analysis was performed to identify predictors and develop a nomogram, with model performance evaluated by AUC, Hosmer–Lemeshow test, and bootstrap validation. Results: Six independent predictors were identified: male sex (protective factor, OR = 0.500), elevated neutrophil count (OR = 1.114), decreased lymphocyte count (OR = 0.829), decreased prealbumin level (OR = 0.992), crackles (OR = 1.858), and wheezes (OR = 3.734). The nomogram achieved an AUC of 0.743 (95% CI: 0.690–0.796) and demonstrated good calibration performance (Hosmer–Lemeshow p = 0.139, Brier score = 0.136). Risk stratification classified patients into low-risk (<10%), intermediate-risk (10–30%), and high-risk (>30%) groups, with severe illness rates of 5.1%, 16.7%, and 46.0%, respectively (p < 0.001). Conclusions: The nomogram incorporating six early-admission indicators may serve as a practical tool for early risk stratification in hospitalised children with isolated hMPV infection.