Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 6 de 6
Filter
Add more filters










Publication year range
1.
Preprint in English | medRxiv | ID: ppmedrxiv-21264121

ABSTRACT

BackgroundPredicting outcomes of COVID-19 patients at an early stage is critical for optimized clinical care and resource management, especially during a pandemic. Although multiple machine learning models have been proposed to address this issue, based on the need for extensive data pre-processing and feature engineering, these models have not been validated or implemented outside of the original study site. MethodsIn this study, we propose CovRNN, recurrent neural network (RNN)-based models to predict COVID-19 patients outcomes, using their available electronic health record (EHR) data on admission, without the need for specific feature selection or missing data imputation. CovRNN is designed to predict three outcomes: in-hospital mortality, need for mechanical ventilation, and long length of stay (LOS >7 days). Predictions are made for time-to-event risk scores (survival prediction) and all-time risk scores (binary prediction). Our models were trained and validated using heterogeneous and de-identified data of 247,960 COVID-19 patients from 87 healthcare systems, derived from the Cerner(R) Real-World Dataset (CRWD). External validation was performed using three test sets (approximately 53,000 patients). Further, the transferability of CovRNN was validated using 36,140 de-identified patients data derived from the Optum(R) de-identified COVID-19 Electronic Health Record v. 1015 dataset (2007-2020). FindingsCovRNN shows higher performance than do traditional models. It achieved an area under the receiving operating characteristic (AUROC) of 93% for mortality and mechanical ventilation predictions on the CRWD test set (vs. 91{middle dot}5% and 90% for light gradient boost machine (LGBM) and logistic regression (LR), respectively) and 86.5% for prediction of LOS > 7 days (vs. 81{middle dot}7% and 80% for LGBM and LR, respectively). For survival prediction, CovRNN achieved a C-index of 86% for mortality and 92{middle dot}6% for mechanical ventilation. External validation confirmed AUROCs in similar ranges. InterpretationTrained on a large heterogeneous real-world dataset, our CovRNN model showed high prediction accuracy, good calibration, and transferability through consistently good performance on multiple external datasets. Our results demonstrate the feasibility of a COVID-19 predictive model that delivers high accuracy without the need for complex feature engineering.

2.
Article in English | WPRIM (Western Pacific) | ID: wpr-922091

ABSTRACT

Development of thoracolumbar vertebra (TLV) and rib primordium (RP) is a common evolutionary feature across vertebrates, although whole-organism analysis of the expression dynamics of TLV- and RP-related genes has been lacking. Here, we investigated the single-cell transcriptome landscape of thoracic vertebra (TV), lumbar vertebra (LV), and RP cells from a pig embryo at 27 days post-fertilization (dpf) and identified six cell types with distinct gene expression signatures. In-depth dissection of the gene expression dynamics and RNA velocity revealed a coupled process of osteogenesis and angiogenesis during TLV and RP development. Further analysis of cell type-specific and strand-specific expression uncovered the extremely high level of HOXA10 3'-UTR sequence specific to osteoblasts of LV cells, which may function as anti-HOXA10-antisense by counteracting the HOXA10-antisense effect to determine TLV transition. Thus, this work provides a valuable resource for understanding embryonic osteogenesis and angiogenesis underlying vertebrate TLV and RP development at the cell type-specific resolution, which serves as a comprehensive view on the transcriptional profile of animal embryo development.

3.
Article in Chinese | WPRIM (Western Pacific) | ID: wpr-612768

ABSTRACT

[Objective] To expound the diagnosis and treatment of chronic heart failure by tranditional Chinese and western medicine, to make the syndrome differentiation and treatment more accurate and the efficacy better. [Method] The progression of chronic heart failure can be divided into four stages, to combine the tranditional Chinese and western medicine to use the traditional Chinese theory to treat the four stages. [Result] Pre-heart failure and pre-clinical heart failure most belong to Qi deficiency of heart and lung syndrome, deficiencies of Qi and Yin syndrome; Clinical heart failure belongs to Qi deficiency and blood stasis syndrome, turbid-phlegm and water-rheum collecting internally syndrome; refractory end-stage heart failure belongs to heart-kidney Yang deficiency and water flooding syndrome, spleen-kidney Yang deficiency and endogenous turbid-phlegm syndrome, even depletion of Yin and Yang syndrome.[Conclusion] The pattern of diagnosis and treatment of combind tranditional Chinese and western medicine is the result of the development of modern medicine which contributes to the diagnosis of tradition Chinese medicine. This paper expounds the syndrome differentiation and treatment based on the western medical staging to make the syndrome differentiation and treatment accuracy and the curative effect better.

4.
Tianjin Medical Journal ; (12): 1093-1096, 2015.
Article in Chinese | WPRIM (Western Pacific) | ID: wpr-478701

ABSTRACT

Objective To explore the effect of astragalus extracts on adherence, migration, cell viability, microvascular formation, and eNOS expression in bone marrow-derived endothelial progenitor cells (EPCs) of rats. Methods EPCs were cultured, isolated and identified in vitro and divided into four groups: low titer group (10-4 g/L of astragalus extracts), middle titer group (10-3 g/L of astragalus extracts), high titer group (10-2 g/L of astragalus extracts) and control group. The effects of astragalus extract on adhesion, migration or microvascular formation were observed under the inverted microscope and com?pared between all groups;Cell viability was detected by MTT assay;mRNA transcription and protein expression levels of en?dothelial nitric oxide synthase (eNOS) in EPCs were detected by reverse transcription PCR (RT-PCR) and Western blot re?spectively. Results Compared with the control group, cell adhesion, migration and microvascular formation of EPCs all en?hanced with addition of astragalus extracts in a dose dependent manner (F=15.256, 13.633, 97.549 respectively, and P <0.05 in all cases); Cell vitality of EPCs increased with administration of astragalus extracts in a time and dose dependant manner. (F=9.755 for time and F=10.18 for dose). mRNA transcription and protein expression of eNOS in EPCs were up-reg?ulated with addition of astragalus extracts in a dose dependent manner (F=56.356 and 77.125 respectively, and P<0.05 in both cases). Conclusion Astragalus extracts play important role in angiogenesis in EPCs probably through up-regulating expressions of eNOS.

5.
Chinese Pharmacological Bulletin ; (12): 1259-1263,1264, 2015.
Article in Chinese | WPRIM (Western Pacific) | ID: wpr-602791

ABSTRACT

Aim To explore the effect of protein kinase D1 (PKD1 )on adherence,migration,proliferation, microvascular formation,and eNOS expression in bone marrow-derived endothelial progenitor cells(EPCs)of rats.Method The EPCs were isolated from bone marrow of rats,cultured and detected,the effects of PKD1 and its specific blocking agent CID755673 on adhesion,migration,proliferation,or microvascular formation were observed,as well as mRNA and protein expression of endothelial nitric oxide synthase (eNOS ) in EPCs.Results PKD1 significantly promoted adhe-sion,migration,proliferation and microvascular forma-tion of EPCs,and upregulated the mRNA and protein expression of eNOS in EPCs,according to the cell cul-ture experiments of EPCs in vitro.Conclusion PKD1 has the role of angiogenesis through regulation of EPCs,which might be dependent on eNOS.

6.
Chinese Journal of Pathophysiology ; (12): 1490-1494,1499, 2015.
Article in Chinese | WPRIM (Western Pacific) | ID: wpr-602398

ABSTRACT

AIM:Todeterminetheeffectofsalviaextractonangiogenesisofthemyocardiumintheratswith myocardial infarction (MI) and to analyze its possible mechanism .METHODS: Left coronary artery of Sprague-Dawley rats was ligated to establish a MI model .The rats were randomly divided into MI model group , 3 different dose groups of salvia (10, 20 and 40 mg? kg-1? d-1), and sham operation group.Each group consisted of 8 rats.The rats in all treat-ment groups were orally administered with the salvia extract , and the rats in MI group and sham operation group were fed with the same volume of saline .The rats were sacrificed 4 weeks later .The hemodynamic changes of the rats were deter-mined , and the segmental heart samples were used for morphological observation by hematoxylin and eosin staining , Masson staining, or electron microscopic analysis.The expression of vascular endothelial growth factor (VEGF) and cluster of dif-ferentiation 34 ( CD34 ) was analyzed according to immunohistochemistry .RESULTS: Compared with sham operation group, the morphological changes of the myocardium in MI group were disordered , part of myocardial cell outline disap-peared , and obvious fibrosis in the necrosis myocardial tissue and fuzzy or disappearing microvascular ultrastructure were al -so observed .Compared with MI group , the number of new microvessels in all the treatment groups increased obviously , and the morphological changes of the endothelial cells were relatively complete according to electron microscopy .Compared with sham operation group , the protein expression of VEGF and CD 34 in the cytoplasm of the myocardial tissues in MI group in-creased only a little .Compared with MI group , the protein expression of VEGF and CD 34 in the cytoplasm of the myocardi-al tissues in all treatment groups increased significantly ( P<0.01 ) .CONCLUSION: Salvia extract obviously promotes angiogenesis of the myocardial tissues in the rats after myocardial infarction .

SELECTION OF CITATIONS
SEARCH DETAIL
...