ABSTRACT
Objective:To evaluate the clinical significance of commonly used clinical inflammatory indicators in children with infectious diseases.Methods:A total of 354 children diagnosed with infectious diseases in our hospital from December 2018 to October 2020 were selected and divided into viral infection group(83 cases), sepsis group (65 cases), atypical pathogen infection group(23 cases), fungal infection group (11 cases), and bacterial infection group(172 cases). The data of serum amyloid A(SAA), procalcitonin(PCT), C-reactive protein(CRP), SAA/CRP, and interleukin (IL) in each group were collected.The fever peak, duration of fever, and fever subsidence time after admission were recorded.The receiver operating characteristic (ROC) curve was plotted, and the area under the curve(AUC), cut-off value, sensitivity and specificity were recorded.The correlation between fever and inflammatory indicators was analyzed.Results:The duration of fever in the atypical pathogen infection group was significantly higher than that in the other groups.Compared with the sepsis group, the differences regarding the levels of SAA, CRP, PCT, and IL-6 were statistically significant compared with those in the bacterial infection group, the atypical pathogen infection group, and the viral infection group (all P<0.05). SAA/CRP was the highest in the viral infection group, and its mean value was nearly twice compared with that in the sepsis group ( P<0.05). IL-10 was significantly different between bacterial infection group and viral infection group( P<0.05). Compared with the fungal infection group, the difference of interferon-γ was statistically significant compared with that in the bacterial infection group, viral infection group and sepsis group (all P<0.05). The ROC curves suggested that the AUC of SAA/CRP and IL-10 was the largest and the same in the viral infection group.The AUC of PCT in the sepsis group was the largest of 0.877, and the specificity was the highest at 91.7% when the PCT was 1.055 ng/mL.Correlation analysis found that SAA and CRP detected for the first time at admission were positively correlated with the time to heat remission. Conclusion:SAA/CRP has significant significance in differentiating sepsis and virus infection, and significantly increased PCT is an important sign of sepsis.
ABSTRACT
The extraction of neuroimaging features of migraine patients and the design of identification models are of great significance for the auxiliary diagnosis of related diseases. Compared with the commonly used image features, this study directly uses time-series signals to characterize the functional state of the brain in migraine patients and healthy controls, which can effectively utilize the temporal information and reduce the computational effort of classification model training. Firstly, Group Independent Component Analysis and Dictionary Learning were used to segment different brain areas for small-sample groups and then the regional average time-series signals were extracted. Next, the extracted time series were divided equally into multiple subseries to expand the model input sample. Finally, the time series were modeled using a bi-directional long-short term memory network to learn the pre-and-post temporal information within each time series to characterize the periodic brain state changes to improve the diagnostic accuracy of migraine. The results showed that the classification accuracy of migraine patients and healthy controls was 96.94%, the area under the curve was 0.98, and the computation time was relatively shorter. The experiments indicate that the method in this paper has strong applicability, and the combination of time-series feature extraction and bi-directional long-short term memory network model can be better used for the classification and diagnosis of migraine. This work provides a new idea for the lightweight diagnostic model based on small-sample neuroimaging data, and contributes to the exploration of the neural discrimination mechanism of related diseases.