Mycoplasma pneumoniae is a significant cause of respiratory infections in both children and adults. In recent years, the global spread of infection and increasing resistance to macrolide antibiotics have increased the risk of Mycoplasma pneumoniae pneumonia (MPP) progressing to severe or refractory forms, thereby posing a serious threat to human health. These cases are often accompanied by severe complications, such as plastic bronchitis, pleural effusion, pulmonary embolism, and extrapulmonary complications, including myocardial damage, liver dysfunction, kidney injury, anemia, and encephalitis. Patients with severe MPP are particularly vulnerable to life-threatening conditions, like diffuse alveolar hemorrhage, pulmonary embolism, and acute respiratory distress syndrome, resulting in lower survival rates. Without timely treatment, long-term sequelae or even fatal outcomes are possible, presenting a significant challenge to clinical care and leading to substantial consumption of medical resources. Therefore, identifying independent risk factors for delayed recovery from MPP and developing accurate predictive models are crucial for early intervention and management.

The study cohort included MPP patients admitted to three medical centers from July 2023 to October 2023. Patients were divided into two groups based on clinical and imaging outcomes at two weeks post-treatment: recovery and delayed recovery. Image segmentation, feature extraction, and selection were performed using the uAI Research Portal V1.1. A logistic regression model was constructed. A total of 1904 radiomics features were automatically extracted from the raw images using the Pyradiomics V3.0 tool built into the uAI Research Portal V1.1. Feature selection was performed with Z-score normalization, Spearman correlation analysis, and least absolute shrinkage and selection operator methods. Clinical-imaging, radiomics, and integrated (clinical + imaging + radiomics features) models were constructed. Model performance was assessed by calculating the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. Decision curve analysis was used to evaluate the net benefit