[Platelet-to-lymphocyte ratio as a biomarker for predicting coronary artery lesions in Chinese children with Kawasaki disease: a Meta analysis]. / è¡€å°æ¿ä¸Žæ·‹å·´ç»†èƒžæ¯”å€¼å¯¹ä¸­å›½å·å´Žç— æ‚£å„¿å† çŠ¶åŠ¨è„‰ç— å˜é¢„æµ‹ä»·å€¼çš„Meta分析.

OBJECTIVES: To systematically evaluate the value of the platelet-to-lymphocyte ratio (PLR) in predicting coronary artery lesions (CAL) in Chinese children with Kawasaki Disease (KD). METHODS: A comprehensive search was conducted in databases including PubMed, Embase, Cochrane Library, Web of Science, China National Knowledge Infrastructure, Wanfang Data, China Biomedical Literature Database, and China Science and Technology Journal Database from inception to December 2022. The quality of the included literature was assessed using the Newcastle-Ottawa Scale, and a Meta analysis was performed using Stata 15.1. RESULTS: A total of ten published reports, involving 3 664 Chinese children with KD, were included in this Meta analysis, of whom 1 328 developed CAL. The Meta analysis revealed a sensitivity of 0.78 (95%CI: 0.71-0.83), specificity of 0.71 (95%CI: 0.61-0.80), overall diagnostic odds ratio of 8.69 (95%CI: 5.02-15.06), and an area under the curve of the summary receiver operating characteristic of 0.82 (95%CI: 0.78-0.85) for PLR in predicting CAL in the children with KD. The sensitivity, specificity, and area under the curve of summary receiver operating characteristic were lower for PLR alone compared to PLR in combination with other indicators. Sensitivity analysis demonstrated the stability of the Meta analysis results with no significant changes upon excluding individual studies. However, a significant publication bias was observed (P<0.001). CONCLUSIONS: PLR demonstrates certain predictive value for CAL in Chinese children with KD.

Elevated serum HbA1c level, rather than previous history of diabetes, predicts the disease severity and clinical outcomes of acute pancreatitis.

INTRODUCTION: The aim of our study is to explore the value of serum glycosylated hemoglobin A1c (HbA1c) in disease severity and clinical outcomes of acute pancreatitis (AP). RESEARCH DESIGN AND METHODS: Patients with AP were included from January 2013 to December 2020, retrospectively, dividing into normal serum HbA1c level (N-HbA1c) group and high serum HbA1c level (H-HbA1c) group according to the criteria HbA1c <6.5%. We compared patient characteristics, biochemical parameters, disease severity, and clinical outcomes of patients with AP in two groups. Besides, we evaluated the efficacy of serum HbA1c to predict organ failure (OF) in AP patients by receiver operating curve (ROC). RESULTS: We included 441 patients with AP, including 247 patients in N-HbA1c group and 194 patients in H-HbA1c group. Serum HbA1c level was positively correlated with Atlanta classification, systemic inflammatory response syndrome, local complication, and OF (all p<0.05). Ranson, BISAP (bedside index of severity in acute pancreatitis), and CT severity index scores in patients with H-HbA1c were markedly higher than those in patients with N-HbA1c (all p<0.01). ROC showed that the best critical point for predicting the development of OF in AP with serum HbA1c is 7.05% (area under the ROC curve=0.79). Logistic regression analysis showed H-HbA1c was the independent risk factor for the development of OF in AP. Interestingly, in patients with presence history of diabetes and HbA1c <6.5%, the severity of AP was significantly lower than that in H-HbA1c group. Besides, there was no significant difference between with and without history of diabetes in N-HbA1c group. CONCLUSIONS: Generally known, diabetes is closely related to the development of AP, and strict control of blood glucose can improve the related complications. Thus, the level of glycemic control before the onset of AP (HbA1c as an indicator) is the key to poor prognosis of AP, rather than basic history of diabetes. Elevated serum HbA1c level can become the potential indicator for predicting the disease severity of AP.

Prediction of the severity of acute pancreatitis using machine learning models.

BACKGROUND: Acute pancreatitis (AP) is the most common pancreatic disease. Predicting the severity of AP is critical for making preventive decisions. However, the performance of existing scoring systems in predicting AP severity was not satisfactory. The purpose of this study was to develop predictive models for the severity of AP using machine learning (ML) algorithms and explore the important predictors that affected the prediction results. METHODS: The data of 441 patients in the Department of Gastroenterology in our hospital were analyzed retrospectively. The demographic data, blood routine and blood biochemical indexes, and the CTSI score were collected to develop five different ML predictive models to predict the severity of AP. The performance of the models was evaluated by the area under the receiver operating characteristic curve (AUC). The important predictors were determined by ranking the feature importance of the predictive factors. RESULTS: Compared to other ML models, the extreme gradient boosting model (XGBoost) showed better performance in predicting severe AP, with an AUC of 0.906, an accuracy of 0.902, a sensitivity of 0.700, a specificity of 0.961, and a F1 score of 0.764. Further analysis showed that the CTSI score, ALB, LDH, and NEUT were the important predictors of the severity of AP. CONCLUSION: The results showed that the XGBoost algorithm can accurately predict the severity of AP, which can provide an assistance for the clinicians to identify severe AP at an early stage.