Browsing by Author "Deng, Y"

Now showing 1 - 7 of 7
  • Thumbnail Image
    ItemOpen Access
    Analysis of main risk factors causing stroke in Shanxi Province based on machine learning models
    (Informatics in Medicine Unlocked, 2021-01-01) Liu, J; Sun, Y; Ma, J; Tu, J; Deng, Y; He, P; Li, R; Hu, F; Huang, H; Zhou, X; Xu, S
    Background: In China, stroke has been the first leading cause of death in recent years. It is a major cause of long-term physical and cognitive impairment, which bring great pressure on the National Public Health System. On the other hand, China is a big country, evaluation of the risk of getting stroke is important for the prevention and treatment of stroke in China. Methods: A data set with 2000 hospitalized stroke patients in 2018 and 27583 residents during the year 2017 to 2020 is analyzed in this study. With the cleaned data, three models on stroke risk levels are built by using machine learning methods. The importance of “8+2” factors from China National Stroke Prevention Project (CSPP) is evaluated via decision tree and random forest models. The importance of more detailed features and their SHAP values are evaluated and ranked via random forest model. Furthermore, a logistic regression model is applied to evaluate the probability of getting stroke for different risk levels. Results: Among all “8+2” risk factors of getting stroke, the decision tree model reveals that top three factors are Hypertension (0.4995), Physical Inactivity (0.08486) and Diabetes Mellitus (0.07889), and the random forest model shows that top three factors are Hypertension (0.3966), Hyperlipidemia (0.1229) and Physical Inactivity (0.1146). In addition to “8+2” factors the importance of features for lifestyle information, demographic information and medical measurement are evaluated via random forest model. It shows that top five features are Systolic Blood Pressure (SBP) (0.3670), Diastolic Blood Pressure (DBP) (0.1541), Physical Inactivity (0.0904), Body Mass Index (BMI) (0.0721) and Fasting Blood Glucose (FBG)(0.0531). SHAP values show that DBP, Physical Inactivity, SBP, BMI, Smoking, FBG, and Triglyceride(TG) are positively correlated to the risk of getting stroke. High-density Lipoprotein (HDL) is negatively correlated to the risk of getting stroke. Combining with the data of 2000 hospitalized stroke patients, the logistic regression model shows that the average probabilities of getting stroke are 7.20%±0.55% for the low-risk level patients, 19.02%±0.94% for the medium-risk level patients and 83.89%±0.97% for the high-risk level patients. Conclusion: Based on the census data from Shanxi Province, we investigate stroke risk factors and their ranking. It shows that Hypertension, Physical Inactivity, and Overweight are ranked as the top three high stroke risk factors in Shanxi. The probability of getting a stroke is also estimated through our interpretable machine learning methods.
  • Thumbnail Image
    ItemOpen Access
    Changes to the North Atlantic subtropical high and its role in the intensification of summer rainfall variability in the southeastern United States
    (Journal of Climate, 2011-03-01) Li, W; Li, L; Fu, R; Deng, Y; Wang, H
    This study investigates the changes of the North Atlantic subtropical high (NASH) and its impact on summer precipitation over the southeastern (SE) United States using the 850-hPa geopotential height field in the National Centers forEnvironmental Prediction (NCEP) reanalysis, the 40-yr European Centre for Medium-Range Weather Forecasts (ECMWF) Re-Analysis (ERA-40), long-term rainfall data, and Intergovernmental Panel on Climate Change (IPCC) Fourth Assessment Report (AR4) model simulations during the past six decades (1948-2007). The results show that the NASH in the last 30 yr has become more intense, and its western ridge has displaced westward with an enhanced meridional movement compared to the previous 30 yr. When the NASH moved closer to the continental United States in the three most recent decades, the effect of the NASH on the interannual variation of SE U.S. precipitation is enhanced through the ridge's north-south movement. The study's attribution analysis suggested that the changes of the NASH are mainly due to anthropogenic warming. In the twenty-first century with an increase of the atmospheric CO2 concentration, the center of the NASH would be intensified and the western ridge of the NASH would shift farther westward. These changes would increase the likelihood of both strong anomalously wet and dry summers over the SEUnited States in the future, as suggested by the IPCC AR4 models. © 2011 American Meteorological Society.
  • Thumbnail Image
    ItemOpen Access
    Dynamical and thermodynamical coupling between the North Atlantic subtropical high and the marine boundary layer clouds in boreal summer
    (Climate Dynamics, 2017-06-10) Wei, W; Li, W; Deng, Y; Yang, S; Jiang, JH; Huang, L; Liu, WT
  • Thumbnail Image
    ItemOpen Access
    Impact of the Interdecadal Pacific Oscillation on Tropical Cyclone Activity in the North Atlantic and Eastern North Pacific.
    (Sci Rep, 2015-07-24) Li, W; Li, L; Deng, Y
    Tropical cyclones (TCs) are among the most devastating weather systems affecting the United States and Central America (USCA). Here we show that the Interdecadal Pacific Oscillation (IPO) strongly modulates TC activity over the North Atlantic (NA) and eastern North Pacific (eNP). During positive IPO phases, less (more) TCs were observed over NA (eNP), likely due to the presence of stronger (weaker) vertical wind shear and the resulting changes in genesis potential. Furthermore, TCs over NA tend to keep their tracks more eastward and recurve at lower latitudes during positive IPO phases. Such variations are largely determined by changes in steering flow instead of changes in genesis locations. Over the eNP, smaller track variations are observed at different IPO phases with stable, westward movements of TCs prevailing. These findings have substantial implications for understanding decadal to inter-decadal fluctuations in the risk of TC landfalls along USCA coasts.
  • Thumbnail Image
    ItemOpen Access
  • Thumbnail Image
    ItemOpen Access
    Mass Footprints of the North Pacific Atmospheric Blocking Highs
    (JOURNAL OF CLIMATE, 2015-06) Park, TW; Deng, Y; Li, W; Yang, S; Cai, M
  • Thumbnail Image
    ItemOpen Access
    Quenching factor measurements of neon nuclei in neon gas
    Balogh, L; Beaufort, C; Brossard, A; Caron, J-F; Chapellier, M; Coquillat, J-M; Corcoran, EC; Crawford, S; Fard, A Dastgheibi; Deng, Y; Dering, K; Durnford, D; Garrah, C; Gerbier, G; Giomataris, I; Giroux, G; Gorel, P; Gros, M; Gros, P; Guillaudin, O; Hoppe, EW; Katsioulas, I; Kelly, F; Knights, P; Kwon, L; Langrock, S; Lautridou, P; Martin, RD; Manthos, I; Matthews, J; Mols, J-P; Muraz, J-F; Neep, T; Nikolopoulos, K; O'Brien, P; Piro, M-C; Samuleev, P; Santos, D; Savvidis, G; Savvidis, I; Fernandez, F Vazquez de Sola; Vidal, M; Ward, R; Zampaolo, M; An, P; Awe, C; Barbeau, P; Hedges, S; Li, L; Runge, J
    The NEWS-G collaboration uses Spherical Proportional Counters (SPCs) to search for weakly interacting massive particles (WIMPs). In this paper, we report the first measurements of the nuclear quenching factor in neon gas at \SI{2}{bar} using an SPC deployed in a neutron beam at the TUNL facility. The energy-dependence of the nuclear quenching factor is modelled using a simple power law: $\alpha$E$_{nr}^{\beta}$; we determine its parameters by simultaneously fitting the data collected with the detector over a range of energies. We measured the following parameters in Ne:CH$_{4}$ at \SI{2}{bar}: $\alpha$ = 0.2801 $\pm$ 0.0050 (fit) $\pm$ 0.0045 (sys) and $\beta$ = 0.0867 $\pm$ 0.020 (fit) $\pm$ 0.006(sys). Our measurements do not agree with expected values from SRIM or Lindhard theory. We demonstrated the feasibility of performing quenching factor measurements at sub-keV energies in gases using SPCs and a neutron beam.