The historical development of endogenous wind （内风） is traced with time as the thread， based on the progression of factors such as syndromes， causes of disease， and pathogenesis. It is believed that the concept of wind syndrome originated in The Inner Canon of Yellow Emperor （《黄帝内经》）， encompassing both exogenous wind （外风） and endogenous wind syndrome. Over time， exogenous wind syndrome gradually evolved into mild syndromes and severe syndromes， while endogenous wind syndrome emerged from severe syndromes of exogenous wind. Endogenous wind syndrome has both syndrome and pathogenic attributes， and its theoretical system has gradually become more refined. Based on the theories of ancient and modern medical practitioners， and combining the holistic perspectives with Xiang （象） thinking， it is proposed that endogenous wind has both physiological and pathological distinctions. The physiological endogenous wind refers to the liver's moderate dispersing and regulating function， which helps to distribute qi （气）， blood， and body fluids， while pathological endogenous wind arises from abnormal liver dispersal. Therefore， in clinical practice， different treatment methods， such as tonifying， unblocking， and warming， can be applied according to the differentiation of deficiency and excess in the pathogenesis.

Objective To predict the risk of in-hospital death in patients with chronic heart failure(CHF)complicated by lung infections using interpretable machine learning.Methods The clinical data of 1415 patients diagnosed with CHF complicated by lung infections were obtained from the MIMIC-IV database.According to the pathogen type,the patients were categorized into bacterial pneumonia and non-bacterial pneumonia groups,and their risks of in-hospital death were compared using Kaplan-Meier survival curves.Univariate analysis and LASSO regression were used to select the features for constructing LR,AdaBoost,XGBoost,and LightGBM models,and their performance was compared in terms of accuracy,precision,F1 value,and AUC.External validation of the models was performed using the data from eICU-CRD database.SHAP algorithm was applied for interpretive analysis of XGBoost model.Results Among the 4 constructed models,the XGBoost model showed the highest accuracy and F1 value for predicting the risk of in-hospital death in CHF patients with lung infections in the training set.In the external test set,the XGBoost model had an AUC of 0.691(95%CI:0.654-0.720)in bacterial pneumonia group and an AUC of 0.725(95%CI:0.577-0.782)in non-bacterial pneumonia group,and showed better predictive ability and stability than the other models.Conclusion The overall performance of the XGBoost model is superior to the other 3 models for predicting the risk of in-hospital death in CHF patients with lung infections.The SHAP algorithm provides a clear interpretation of the model to facilitate decision-making in clinical settings.

Objective To predict the risk of in-hospital death in patients with chronic heart failure(CHF)complicated by lung infections using interpretable machine learning.Methods The clinical data of 1415 patients diagnosed with CHF complicated by lung infections were obtained from the MIMIC-IV database.According to the pathogen type,the patients were categorized into bacterial pneumonia and non-bacterial pneumonia groups,and their risks of in-hospital death were compared using Kaplan-Meier survival curves.Univariate analysis and LASSO regression were used to select the features for constructing LR,AdaBoost,XGBoost,and LightGBM models,and their performance was compared in terms of accuracy,precision,F1 value,and AUC.External validation of the models was performed using the data from eICU-CRD database.SHAP algorithm was applied for interpretive analysis of XGBoost model.Results Among the 4 constructed models,the XGBoost model showed the highest accuracy and F1 value for predicting the risk of in-hospital death in CHF patients with lung infections in the training set.In the external test set,the XGBoost model had an AUC of 0.691(95%CI:0.654-0.720)in bacterial pneumonia group and an AUC of 0.725(95%CI:0.577-0.782)in non-bacterial pneumonia group,and showed better predictive ability and stability than the other models.Conclusion The overall performance of the XGBoost model is superior to the other 3 models for predicting the risk of in-hospital death in CHF patients with lung infections.The SHAP algorithm provides a clear interpretation of the model to facilitate decision-making in clinical settings.