Objective To propose a method for predicting weaning outcomes based on machine learning and electrical impedance tomography(EIT).Methods Firstly,EIT image features were extracted from a total of 84 samples from 30 patients,and the important features screened with the extreme gradient boosting(XGBoost)algorithm were used as inputs to the model.Secondly,the prediction model was built with six machine learning methods,namely random forest(RF),support vector machines(SVM),XGBoost,gradient boosting decision tree(GBDT),logistic regression(LR)and decision tree(tree).Then the prediction model had its prediction performance evaluated by AUC,accuracy,sensitivity and specificity under imbalanced dataset,over-sampling balanced dataset and random under-sampling balanced dataset.Results In terms of AUC,accuracy and specificity,the model under the over-sampling balanced dataset and the random under-sampling balanced dataset behaved better than that under the imbalanced dataset(P＜0.05);in terms of sensitivity,the difference in model performance between the over-sampling balanced dataset and the imbalanced dataset was not statistically significant(P＞0.05),and the model performance under the random under-sampling balanced dataset decreased when compared with that under the imbalanced dataset(P＜0.05).There were no significant differences between the model performance under the over-sampling balanced dataset and that under the random under-sampling balanced dataset(P＞0.05).The model based on XGBoost behaved the best under the over-sampling balanced dataset,with an AUC of 0.769,an accuracy of 0.808,a sensitivity of 0.938 and a specificity of 0.600.Conclusion The method based on machine learning and EIT predicts weaning outcomes of patients with prolonged mechanical ventilation,and thus can be used for auxiliary decision support for clinicians to determine the appropriate timing of weaning.[Chinese Medical Equipment Journal,2023,44(10):1-6]

ObjectiveTo explore the guidance value of “treatment of disease in accordance with three conditions” theory in the prevention and treatment of corona virus disease 2019（COVID-19） based on the differences of syndromes and traditional Chinese medicine（TCM） treatments in COVID-19 patients from Xingtai Hospital of Chinese Medicine of Hebei province and Ruili Hospital of Chinese Medicine and Dai Medicine of Yunnan province and discuss its significance in the prevention and treatment of the unexpected acute infectious diseases. MethodDemographics data and clinical characteristics of COVID-19 patients from the two hospitals were collected retrospectively and analyzed by SPSS 18.0. The information on formulas was obtained from the hospital information system （HIS） of the two hospitals and analyzed by the big data intelligent processing and knowledge service system of Guangdong Hospital of Chinese Medicine for frequency statistics and association rules analysis. Heat map-hierarchical clustering analysis was used to explore the correlation between clinical characteristics and formulas. ResultA total of 175 patients with COVID-19 were included in this study. The 70 patients in Xingtai，dominated by young and middle-aged males，had clinical symptoms of fever， abnormal sweating，and fatigue. The main pathogenesis is stagnant cold-dampness in the exterior and impaired yin by depressed heat， with manifest cold， dampness， and deficiency syndromes. The therapeutic methods highlight relieving exterior syndrome and resolving dampness， accompanied by draining depressed heat. The core Chinese medicines used are Poria，Armeniacae Semen Amarum，Gypsum Fibrosum，Citri Reticulatae Pericarpium，and Pogostemonis Herba. By contrast，the 105 patients in Ruili， dominated by young females， had atypical clinical symptoms， and most of them were asymptomatic patients or mild cases. The main pathogenesis is dampness obstructing the lung and the stomach， with obvious dampness and heat syndromes. The therapeutic methods are mainly invigorating the spleen， resolving dampness， and dispersing Qi with light drugs. The core Chinese medicines used are Poria，Atractylodis Macrocephalae Rhizoma，Glycyrrhizae Radix et Rhizoma，Coicis Semen，Platycodonis Radix，Lonicerae Japonicae Flos， and Pogostemonis Herba. ConclusionThe differences in clinical characteristics， TCM syndromes， and medication of COVID-19 patients from the two places may result from different regions，population characteristics， and the time point of the COVID-19 outbreak. The “treatment of disease in accordance with three conditions” theory can help to understand the internal correlation and guide the treatments.