Objective To construct the differential diagnosis model of viral pneumonia and bacterial pneumonia based on lung ultrasonography (LUS) characteristics. Methods A total of 248 patients with pneumonia who completed LUS in our hospital from January 2021 to March 2024 were retrospectively included, and were divided into a viral group (140 cases) and a bacterial group (108 cases) according to the final etiological diagnosis. Predictors in differential diagnosis between viral pneumonia and bacterial pneumonia were analyzed by univariate and multivariate methods. The differential diagnosis model of viral pneumonia and bacterial pneumonia and the prediction efficiency were evaluated. Results Univariate and multivariate logistic analysis showed that the presence or absence of lung consolidation, pleural effusion, B-line range of both lungs and pulmonary ultrasound score were independent predictors of the differential diagnosis of viral pneumonia and bacterial pneumonia (P<0.05). Using the logistic regression model of lung consolidation, pleural effusion, bilateral B-line range, and pulmonary ultrasound score, including the P-values of three variables (lung consolidation, pleural effusion, and bilateral B-line range), and the P-values of four variables (lung consolidation, pleural effusion, bilateral B-line range, and pulmonary ultrasound score), the receiver operating characteristic curve was used to predict the diagnosis of patient. The areas under the curve were 0.863, 0.612, 0.669, 0.684, 0.904, and 0.920, respectively. Conclusion Lung consolidation, pleural effusion, B-line range of both lungs and pulmonary ultrasound score detected by LUS have good diagnostic efficacy in the differential diagnosis of viral pneumonia and bacterial pneumonia, suggesting that LUS technology may be used in the differential diagnosis of viral pneumonia and bacterial pneumonia.
Myocardial infarction (MI) has the characteristics of high mortality rate, strong suddenness and invisibility. There are problems such as the delayed diagnosis, misdiagnosis and missed diagnosis in clinical practice. Electrocardiogram (ECG) examination is the simplest and fastest way to diagnose MI. The research on MI intelligent auxiliary diagnosis based on ECG is of great significance. On the basis of the pathophysiological mechanism of MI and characteristic changes in ECG, feature point extraction and morphology recognition of ECG, along with intelligent auxiliary diagnosis method of MI based on machine learning and deep learning are all summarized. The models, datasets, the number of ECG, the number of leads, input modes, evaluation methods and effects of different methods are compared. Finally, future research directions and development trends are pointed out, including data enhancement of MI, feature points and dynamic features extraction of ECG, the generalization and clinical interpretability of models, which are expected to provide references for researchers in related fields of MI intelligent auxiliary diagnosis.