Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 3 de 3
Filter
Add more filters










Database
Language
Publication year range
1.
Clin Appl Thromb Hemost ; 27: 10760296211040868, 2021.
Article in English | MEDLINE | ID: mdl-34558325

ABSTRACT

The purpose of this study is to establish a novel pulmonary embolism (PE) risk prediction model based on machine learning (ML) methods and to evaluate the predictive performance of the model and the contribution of variables to the predictive performance. We conducted a retrospective study at the Shanghai Tenth People's Hospital and collected the clinical data of in-patients that received pulmonary computed tomography imaging between January 1, 2014 and December 31, 2018. We trained several ML models, including logistic regression (LR), support vector machine (SVM), random forest (RF), and gradient boosting decision tree (GBDT), compared the models with representative baseline algorithms, and investigated their predictability and feature interpretation. A total of 3619 patients were included in the study. We discovered that the GBDT model demonstrated the best prediction with an area under the curve value of 0.799, whereas those of the RF, LR, and SVM models were 0.791, 0.716, and 0.743, respectively. The sensibilities of the GBDT, LR, RF, and SVM models were 63.9%, 68.1%, 71.5%, and 75%, respectively; the specificities were 81.1%, 66.1, 72.7%, and 65.1%, respectively; and the accuracies were 77.8%, 66.5%, 72.5%, and 67%, respectively. We discovered that the maximum D-dimer level contributed the most to the outcome prediction, followed by the extreme growth rate of the plasma fibrinogen level, in-hospital duration, and extreme growth rate of the D-dimer level. The study demonstrates the superiority of the GBDT model in predicting the risk of PE in hospitalized patients. However, in order to be applied in clinical practice and provide support for clinical decision-making, the predictive performance of the model needs to be prospectively verified.


Subject(s)
Machine Learning/standards , Pulmonary Embolism/epidemiology , Aged , Cross Infection , Female , Hospitalization , Humans , Male , Prognosis , Retrospective Studies
2.
RSC Adv ; 9(25): 14004-14010, 2019 May 07.
Article in English | MEDLINE | ID: mdl-35519349

ABSTRACT

In this work, a series of C-doped BiVO4 (BiVO4-T) with natural leaf structures were synthesized by a dipping-calcination method with the leaf of Chongyang wood seedling as a template under different calcination temperatures. The structures and morphologies of BiVO4-T were observed by FE-SEM observations. The doped carbon in BiVO4-T was formed in situ from the natural leaf during the calcination process and the amount of doping could be regulated from 0.51-1.16 wt% by controlling the calcination temperature. It was found that the sample calcined at 600 °C (BiVO4-600) with a C-doping content of 1.16 wt% showed the best photocatalytic degradation activity. After 120 min visible light irradiation, the photocatalytic decomposition efficiency of RhB for BiVO4-600 is 2.2 times higher than that of no template BiVO4. The enhanced photocatalytic performance is ascribed to the combined action of the unique morphology and doped-carbon. It is considered that the unique structures and carbon doping of BiVO4-600 are in favor of the enhancement of visible light absorption, which was supported by UV-vis DRS. Furthermore, the C-doping can enhance the efficient separation and transfer of the photo-generated electron-hole pairs, as proved by PL measurements. This study provides a simple dipping-calcination method and found the best calcination temperature to fabricate a high-performance BiVO4, which simultaneously achieves morphology and C-doping control in one step.

3.
J Spinal Cord Med ; 41(4): 450-458, 2018 07.
Article in English | MEDLINE | ID: mdl-28880133

ABSTRACT

OBJECTIVE: To describe the characteristics of spinal cord injury (SCI) individuals in Shanghai and examine their treatment and rehabilitation for traumatic and complete SCI individuals. DESIGN: Community-based secondary data analyses. SETTING: Shanghai, China. METHODS: We analyzed gender, age at injury, complications, disturbances of function, treatment, etiology, and severity of injury of SCI individuals that enrolled in "halfway houses", government-supported community co-op centers. Bivariate statistical analyses were conducted to examine the factors associated with complete and traumatic SCI. RESULTS: We analyzed 808 SCI individuals who participated in halfway houses in Shanghai during 2009-2015. The male-to-female ratio was 2.1:1. The proportion of middle or elder age groups at injury (age 46 to 60 and age 61 or over) showed a rising trend from 1970 to 2015. The leading causes of SCIs in Shanghai were traumatic injuries (58%), followed by disease (29.5%). The proportion of traumatic injuries decreased over time, while the proportion of non-traumatic injuries rose significantly. A majority of traumatic injury individuals were aged between 16-45. CONCLUSION: The middle or elder age groups at injury among SCI individuals increased continuously from 1970 to 2015. The principal causes of injury in Shanghai were traumatic injuries and disease-related injuries. Men had a higher prevalence of traumatic SCI in Shanghai. Preventive measures should focus on male and middle-aged adults. As a fast-aging society in Shanghai, more effective prevention, medical care, and rehabilitation schemes should be implemented for aging SCI individuals.


Subject(s)
Rehabilitation Centers/statistics & numerical data , Spinal Cord Injuries/epidemiology , Adolescent , Adult , Aged , Child , Child, Preschool , China , Female , Humans , Independent Living/statistics & numerical data , Infant , Male , Middle Aged , Spinal Cord Injuries/rehabilitation
SELECTION OF CITATIONS
SEARCH DETAIL
...