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.

[Effect of Tanshinone IIA in Preventing and Treating Oxaliplatin Induced Peripheral Neuropathy].

OBJECTIVE: To observe preventive and therapeutic effects of Tanshinone IIA (T II A) on oxaliplatin induced peripheral neuropathy (OlPN) and to explore its effects on the expression of calcitonin gene related peptide (CGRP) and never growth factor (NGF). METHODS: Totally 36 phase II - III patients with malignant tumor of digestive tract undergoing chemotherapy program with oxaliplatin, were equally assigned to the T II A group (using THA at 80 mg/day 1 day before oxaliplatin chemotherapy for 3 successive days) and the control group (using chemotherapy program with oxaliplatin alone) by segmented randomization. After 4 cycles of chemotherapy, the incidence degree and incidence of OlPN were evaluated. Sensory nerve conduction velocity (SNCV) and motor nerve conduction velocity ( MNCV) were tested by EMG evoked potential device. Serum levels of CGRP and NGF were also detected in the two groups before and after chemotherapy. The correlation of serum levels of CGRP and NGF to OIPN was assessed using linear correlation analysis. RESULTS: After chemotherapy the OlPN incidence was 27.8% (5/18 cases) in the T II A group, obviously lower than that in the control group (55.6%, 10/18 cases; P < 0.05). Compared with before treatment in the same group, SNCV and MNCV of common peroneal nerve were slowed down, serum NGF levels decreased, and serum CGRP levels obviously increased in the two groups (all P < 0.05). Compared with the control group after treatment, SNCV and MNCV of common peroneal nerve were obviously accelerated, serum NGF levels increased, and serum CGRP levels obviously decreased in the THA group (all P < 0.05). Results of linear correlation analysis indicated serum NGF level was negatively correlated with peripheral neuropathy (PN), serum CGRP expression was positively correlated with neurotoxicity (P < 0.05). CONCLUSION: T II A could reduce the incidence of OlPN, which might be associated with inhibiting the expression of CGRP and up-regulating NGF activities.

Baicalin Blocks Colon Cancer Cell Cycle and Inhibits Cell Proliferation through miR-139-3p Upregulation by Targeting CDK16.

Baicalin was reported to facilitate the apoptosis of colon cells and inhibit tumor growth in vivo. This study aimed to explore the specific mechanism and function of baicalin on colon cells. Relative mRNA levels were tested via qPCR. Cell proliferation, viability, and cell cycle phases were evaluated using MTT, colony formation, and flow cytometry assays, respectively. The interaction between miR-139-3p and cyclin-dependent kinase 16 (CDK16) was measured via a dual-luciferase reporter assay. Immunohistochemistry was used to count the positivity cells in tumor tissues collected from treated xenografted tumor mice. The results showed that baicalin increased miR-139-3p expression while also decreasing CDK16 levels, blocking the cell cycle, and inhibiting cell proliferation in colon cancer cells. miR-139-3p silencing or CDK16 overexpression abolished the inhibitory effects of baicalin on colon cancer proliferation. miR-139-3p directly targeted and interacted with CDK16 at the cellular level. The protective functions of miR-139-3p knockdown on tumor cells were abrogated by silencing CDK16. The combination of baicalin treatment and CDK16 knockdown further inhibited tumor growth of xenografted tumor mice compared with the groups injected with only sh-CDK16 or baicalin in vivo. In conclusion, baicalin inhibited colon cancer growth by modulating the miR-139-3p/CDK16 axis.

Multicenter clinical study for evaluation of efficacy and safety of transdermal fentanyl matrix patch in treatment of moderate to severe cancer pain in 474 chinese cancer patients.

OBJECTIVE: Although a new matrix formulation fentanyl has been used throughout the world for cancer pain management, few data about its efficacy and clinical outcomes associated with its use in Chinese patients have been obtained. This study aimed to assess the efficacy and safety of the new system in Chinese patients with moderate to severe cancer pain. METHODS: A total of 474 patients with moderate to severe cancer pain were enrolled in this study and were treated with the new transdermal fentanyl matrix patch (TDF) up to 2 weeks. All the patients were asked to record pain intensity, side effects, quality of life (QOL), adherence and global satisfaction. The initial dose of fentanyl was 25 µg/h titrated with opioid or according to National Comprehensive Cancer Network (NCCN) guidelines. Transdermal fentanyl was changed every three days. RESULTS: After 2 weeks. The mean pain intensity of the 459 evaluated patients decreased significantly from 5.63±1.26 to 2.03±1.46 (P<0.0001). The total remission rate was 91.29%, of which moderate remission rate 53.16%, obvious remission rate 25.49% and complete remission rate 12.64%. The rate of adverse events was 33.75%, 18.78% of which were moderate and 3.80% were severe. The most frequent adverse events were constipation and nausea. No fatal events were observed. The quality of life was remarkably improved after the treatment (P<0.0001). CONCLUSION: The new TDF is effective and safe in treating patients with moderate to severe cancer pain, and can significantly improve the quality of life.

[Experimental study on effect of epimedium flavonoids in protecting telomere length of senescence cells HU].

OBJECTIVE: To investigate the mechanism of senescence delay of human diploid fibroblast (2BS) and protecting telomere length by epimedium flavonoids (EF). METHODS: The drug sera of EF were used to treat the 2BS. The population doublings of 2BS cells were observed, the mRNA expression of p16 gene were determined by fluorescence real-time quantitative RT-PCR, the telomerase activation of 2BS cells were determined by TRAP-Hyb, the total retinoblastoma (Rb) and phosphorated Rb protein content were detected by ELISA, the telomere length of 2BS cells were determined by telomere restriction fragment (TRF) Southern blot assay. RESULTS: EF could significantly extend the population doublings of 2BS cells, the expression of p16 mRNA was decreased and the content of phosphorated Rb protein were increased by EF. The telomere lengthening of 2BS cells were improved by EF, but the telomerase was not activated. CONCLUSION: In senescence human fibroblasts 2BS cells, p16 gene mRNA expression increased, content of phosphorated Rb protein decreased and the telomere length of 2BS shortened, EF might delay the aging of cells through inhibiting the p16 gene expression, promoting the production of phosphorated Rb protein and to protect the length of telomere, but not activating the telomerase.