Interpretable machine-learning model for Predicting the Convalescent COVID-19 patients with pulmonary diffusing capacity impairment.

INTRODUCTION: The COVID-19 patients in the convalescent stage noticeably have pulmonary diffusing capacity impairment (PDCI). The pulmonary diffusing capacity is a frequently-used indicator of the COVID-19 survivors' prognosis of pulmonary function, but the current studies focusing on prediction of the pulmonary diffusing capacity of these people are limited. The aim of this study was to develop and validate a machine learning (ML) model for predicting PDCI in the COVID-19 patients using routinely available clinical data, thus assisting the clinical diagnosis. METHODS: Collected from a follow-up study from August to September 2021 of 221 hospitalized survivors of COVID-19 18 months after discharge from Wuhan, including the demographic characteristics and clinical examination, the data in this study were randomly separated into a training (80%) data set and a validation (20%) data set. Six popular machine learning models were developed to predict the pulmonary diffusing capacity of patients infected with COVID-19 in the recovery stage. The performance indicators of the model included area under the curve (AUC), Accuracy, Recall, Precision, Positive Predictive Value(PPV), Negative Predictive Value (NPV) and F1. The model with the optimum performance was defined as the optimal model, which was further employed in the interpretability analysis. The MAHAKIL method was utilized to balance the data and optimize the balance of sample distribution, while the RFECV method for feature selection was utilized to select combined features more favorable to machine learning. RESULTS: A total of 221 COVID-19 survivors were recruited in this study after discharge from hospitals in Wuhan. Of these participants, 117 (52.94%) were female, with a median age of 58.2 years (standard deviation (SD) = 12). After feature selection, 31 of the 37 clinical factors were finally selected for use in constructing the model. Among the six tested ML models, the best performance was accomplished in the XGBoost model, with an AUC of 0.755 and an accuracy of 78.01% after experimental verification. The SHAPELY Additive explanations (SHAP) summary analysis exhibited that hemoglobin (Hb), maximal voluntary ventilation (MVV), severity of illness, platelet (PLT), Uric Acid (UA) and blood urea nitrogen (BUN) were the top six most important factors affecting the XGBoost model decision-making. CONCLUSION: The XGBoost model reported here showed a good prognostic prediction ability for PDCI of COVID-19 survivors during the recovery period. Among the interpretation methods based on the importance of SHAP values, Hb and MVV contributed the most to the prediction of PDCI outcomes of COVID-19 survivors in the recovery period.

Electro-acupuncture regulates glucose metabolism in chronic stress model rats.

Studies have shown that acupuncture is very effective in treating chronic stress depression. However, little is known about the therapeutic mechanism of electro-acupuncture. Metabolomics, on the other hand, is a technology that determines the metabolic changes of organisms caused by various interventions as a whole and is related to the overall effect of electro-acupuncture (EA). 1HNMR, serum sample analysis, and histopathology and molecular biology analysis were used to evaluate the effects of EA. The results show that electro-acupuncture points can regulate the heat pain threshold of chronic stress model rats and change the morphology of adrenal cortex cells Structure, and regulate the contents of corticotropin-releasing hormone, Corticosterone (CORT), glucose, alanine and valine in the samples. These findings help to clarify the therapeutic mechanism of electro-acupuncture on heterologous chronic stress model rats. The effect of electro-acupuncture on improving chronic stress is likely to be achieved by regulating glucose metabolism, which can provide a reference for clinical acupuncture treatment of chronic stress depression.

Comparative metabolomics study on therapeutic mechanism of electro-acupuncture and moxibustion on rats with chronic atrophic gastritis (CAG).

Some studies have proved that both acupuncture and moxibustion are very effective for the treatment of CAG. However, little is known about therapeutic mechanism of electro-acupuncture and moxibustion on CAG as well as the difference between them. On the other hand, metabolomics is a 'top-down' approach to understand metabolic changes of organisms caused by disease or interventions in holistic context, which consists with the holistic thinking of electro-acupuncture and moxibustion treatment. In this study, the difference of therapeutic mechanism between electro-acupuncture and moxibustion on CAG rats was investigated by a 1H NMR-based metabolomics analysis of multiple biological samples (serum, stomach, cerebral cortex and medulla) coupled with pathological examination and molecular biological assay. For all sample types, both electro-acupuncture and moxibustion intervention showed beneficial effects by restoring many CAG-induced metabolic changes involved in membrane metabolism, energy metabolism and function of neurotransmitters. Notably, the moxibustion played an important role in CAG treatment mainly by regulating energy metabolism in serum, while main acting site of electro-acupuncture treatment was nervous system in stomach and brain. These findings are helpful to facilitate the therapeutic mechanism elucidating of electro-acupuncture and moxibustion on CAG rats. Metabolomics is promising in mechanisms study for traditional Chinese medicine (TCM).

MOXIBUSTION ALLEVIATES GASTRIC PRECANCEROUS LESIONS IN RATS BY PROMOTING CELL APOPTOSIS AND INHIBITING PROLIFERATION-RELATED ONCOGENES.

BACKGROUND: It is well known that gastric mucosa dysplasia and intestinal metaplasia are gastric precancerous lesions (GPL). Moxibustion treatment of Liangmen (ST21) and Zusanli (ST36) alleviated the inflammatory response and dysplasia of gastric mucosa in our previous study. The purpose of this study was to further examine the underlying mechanism of moxibustion treatment of ST21 and ST36 on GPL. MATERIALS AND METHODS: Sixty SD rats were divided into five groups and rats with GPL were treated with either moxibustion (ST), moxibustion (Sham), or vitacoenzyme. B-cell lymphoma 2 (bcl-2), tumor protein p53 (P53) and cellular Myc (C-MYC), which are related to cell apoptosis, proliferating cell nuclear antigen (PCNA), vascular endothelial growth factor (VEGF), argyrophilic nucleolar organizer region proteins (Ag-NORs), which are associated with cell proliferation, and cell signaling proteins, nuclear factor kappa B (NF-κB), epidermal growth factor receptor (EGFR) and phosphorylated extracellular signal regulated kinase (p-ERK), were measured after moxibustion treatment. RESULTS: Compared with Control group, gastric mucosa in GPL group showed abnormal mucosal proliferation and pathological mitotic figure, the mRNA expression of bcl-2, P53 and C-MYC increased significantly (P < 0.01), the protein expression of PCNA, VEGF, Ag-NORs and the activity of NF-κß as well as EGFR/ERK signaling proteins also increased significantly (P < 0.01). Moxibustion treatment decreased gastric mucosal proliferation and pathological mitotic figure, down-regulated the mRNA expression of bcl-2, P53, C-MYC (P < 0.01), decreased the protein expression of PCNA, VEGF, Ag-NORs and the activity of NF-κß as well as EGFR/ERK signaling proteins significantly (P < 0.01). But moxibustion treatment of Sham didn't show the same effect on GPL. CONCLUSION: Moxibustion treatment inhibited cell apoptosis and reduced gastric mucosa dysplasia by inhibiting the expression of bcl-2, P53, C-MYC and decreased the activity of NF-κß as well as EGFR/ERK signaling proteins.