The aim of this study is to evaluate the relationship of leading causes of death with gradients o... more The aim of this study is to evaluate the relationship of leading causes of death with gradients of cognitive impairment and multimorbidity. This is a population-based study using data from the linked 1992-2010 Health and Retirement Study and National Death Index ( n = 9,691). Multimorbidity is defined as a combination of chronic conditions, functional limitations, and geriatric syndromes. Regression trees and Random Forest identified which combinations of multimorbidity associated with causes of death. Multimorbidity is common in the study population. Heart disease is the leading cause in all groups, but with a larger percentage of deaths in the mild and moderate/severe cognitively impaired groups than among the noncognitively impaired. The different "paths" down the regression trees show that the distribution of causes of death changes with different combinations of multimorbidity. Understanding the considerable heterogeneity in chronic conditions, functional limitations,...
Introduction: The Department of Health and Human Services’ 2010 Strategic Framework on Multiple C... more Introduction: The Department of Health and Human Services’ 2010 Strategic Framework on Multiple Chronic Conditions called for the identification of common constellations of conditions in older adults. Objectives: To analyze patterns of conditions constituting multimorbidity (CCMM) and expenditures in a US representative sample of midlife and older adults (50–64 and ≥65 years of age, respectively). Design: A cross-sectional study of the 2010 Health and Retirement Study (HRS; n=17,912). The following measures were used: (1) count and combinations of CCMM, including (i) chronic conditions (hypertension, arthritis, heart disease, lung disease, stroke, diabetes, cancer, and psychiatric conditions), (ii) functional limitations (upper body limitations, lower body limitations, strength limitations, limitations in activities of daily living, and limitations in instrumental activities of daily living), and (iii) geriatric syndromes (cognitive impairment, depressive symptoms, incontinence, vis...
Accelerated weathering exposures were performed on poly(ethylene-terephthalate) (PET) films. Long... more Accelerated weathering exposures were performed on poly(ethylene-terephthalate) (PET) films. Longitudinal multi-level predictive models as a function of PET grades and exposure types were developed for the change in yellowness index (YI) and haze (%). Exposures with similar change in YI were modeled using a linear fixed-effects modeling approach. Due to the complex nature of haze formation, measurement uncertainty, and the differences in the samples' responses, the change in haze (%) depended on individual samples' responses and a linear mixed-effects modeling approach was used. When compared to fixed-effects models, the addition of random effects in the haze formation models significantly increased the variance explained. For both modeling approaches, diagnostic plots confirmed independence and homogeneity with normally distributed residual errors. Predictive R2 values for true prediction error and predictive power of the models demonstrated that the models were not subject...
Large sequences of images (or movies) can now be obtained on an unprecedented scale, which poses ... more Large sequences of images (or movies) can now be obtained on an unprecedented scale, which poses fundamental challenges to the existing image analysis techniques. The challenges include heterogeneity, (automatic) alignment, multiple comparisons, potential artifacts, and hidden noises. This paper introduces our MATLAB package, Longitudinal Image Sequence Analysis (LISA), as a one-stop ensemble of image processing and analysis tool for comparing a general class of images from either different times, sessions, or subjects. Given two contrasting sequences of images, the image processing in LISA starts with selecting a region of interest in two representative images, followed by automatic or manual segmentation and registration. Automatic segmentation de-noises an image using a mixture of Gaussian distributions of the pixel intensity values, while manual segmentation applies a user-chosen intensity cut-off value to filter out noises. Automatic registration aligns the contrasting images b...
Feature selection from a large number of covariates (aka features) in a regression analysis remai... more Feature selection from a large number of covariates (aka features) in a regression analysis remains a challenge in data science, especially in terms of its potential of scaling to ever-enlarging data and finding a group of scientifically meaningful features. For example, to develop new, responsive drug targets for ovarian cancer, the actual false discovery rate (FDR) of a practical feature selection procedure must also match the target FDR. The popular approach to feature selection, when true features are sparse, is to use a penalized likelihood or a shrinkage estimation, such as a LASSO, SCAD, Elastic Net, or MCP procedure (call them benchmark procedures). We present a different approach using a new subsampling method, called the Subsampling Winner algorithm (SWA). The central idea of SWA is analogous to that used for the selection of US national merit scholars. SWA uses a "base procedure" to analyze each of the subsamples, computes the scores of all features according to...
... GQ Zhang1, Gongqin Shen1, Josh Staiger1, Adam Troy1, and Jiayang Sun2 1 Department of Electri... more ... GQ Zhang1, Gongqin Shen1, Josh Staiger1, Adam Troy1, and Jiayang Sun2 1 Department of Electrical Engineering and Computer Science 2 Department of Statistics Case Western Reserve University, Cleveland, Ohio, USA gqz@eecs.case.edu, http://newton.case.edu ...
The aim of this study is to evaluate the relationship of leading causes of death with gradients o... more The aim of this study is to evaluate the relationship of leading causes of death with gradients of cognitive impairment and multimorbidity. This is a population-based study using data from the linked 1992-2010 Health and Retirement Study and National Death Index ( n = 9,691). Multimorbidity is defined as a combination of chronic conditions, functional limitations, and geriatric syndromes. Regression trees and Random Forest identified which combinations of multimorbidity associated with causes of death. Multimorbidity is common in the study population. Heart disease is the leading cause in all groups, but with a larger percentage of deaths in the mild and moderate/severe cognitively impaired groups than among the noncognitively impaired. The different "paths" down the regression trees show that the distribution of causes of death changes with different combinations of multimorbidity. Understanding the considerable heterogeneity in chronic conditions, functional limitations,...
Introduction: The Department of Health and Human Services’ 2010 Strategic Framework on Multiple C... more Introduction: The Department of Health and Human Services’ 2010 Strategic Framework on Multiple Chronic Conditions called for the identification of common constellations of conditions in older adults. Objectives: To analyze patterns of conditions constituting multimorbidity (CCMM) and expenditures in a US representative sample of midlife and older adults (50–64 and ≥65 years of age, respectively). Design: A cross-sectional study of the 2010 Health and Retirement Study (HRS; n=17,912). The following measures were used: (1) count and combinations of CCMM, including (i) chronic conditions (hypertension, arthritis, heart disease, lung disease, stroke, diabetes, cancer, and psychiatric conditions), (ii) functional limitations (upper body limitations, lower body limitations, strength limitations, limitations in activities of daily living, and limitations in instrumental activities of daily living), and (iii) geriatric syndromes (cognitive impairment, depressive symptoms, incontinence, vis...
Accelerated weathering exposures were performed on poly(ethylene-terephthalate) (PET) films. Long... more Accelerated weathering exposures were performed on poly(ethylene-terephthalate) (PET) films. Longitudinal multi-level predictive models as a function of PET grades and exposure types were developed for the change in yellowness index (YI) and haze (%). Exposures with similar change in YI were modeled using a linear fixed-effects modeling approach. Due to the complex nature of haze formation, measurement uncertainty, and the differences in the samples' responses, the change in haze (%) depended on individual samples' responses and a linear mixed-effects modeling approach was used. When compared to fixed-effects models, the addition of random effects in the haze formation models significantly increased the variance explained. For both modeling approaches, diagnostic plots confirmed independence and homogeneity with normally distributed residual errors. Predictive R2 values for true prediction error and predictive power of the models demonstrated that the models were not subject...
Large sequences of images (or movies) can now be obtained on an unprecedented scale, which poses ... more Large sequences of images (or movies) can now be obtained on an unprecedented scale, which poses fundamental challenges to the existing image analysis techniques. The challenges include heterogeneity, (automatic) alignment, multiple comparisons, potential artifacts, and hidden noises. This paper introduces our MATLAB package, Longitudinal Image Sequence Analysis (LISA), as a one-stop ensemble of image processing and analysis tool for comparing a general class of images from either different times, sessions, or subjects. Given two contrasting sequences of images, the image processing in LISA starts with selecting a region of interest in two representative images, followed by automatic or manual segmentation and registration. Automatic segmentation de-noises an image using a mixture of Gaussian distributions of the pixel intensity values, while manual segmentation applies a user-chosen intensity cut-off value to filter out noises. Automatic registration aligns the contrasting images b...
Feature selection from a large number of covariates (aka features) in a regression analysis remai... more Feature selection from a large number of covariates (aka features) in a regression analysis remains a challenge in data science, especially in terms of its potential of scaling to ever-enlarging data and finding a group of scientifically meaningful features. For example, to develop new, responsive drug targets for ovarian cancer, the actual false discovery rate (FDR) of a practical feature selection procedure must also match the target FDR. The popular approach to feature selection, when true features are sparse, is to use a penalized likelihood or a shrinkage estimation, such as a LASSO, SCAD, Elastic Net, or MCP procedure (call them benchmark procedures). We present a different approach using a new subsampling method, called the Subsampling Winner algorithm (SWA). The central idea of SWA is analogous to that used for the selection of US national merit scholars. SWA uses a "base procedure" to analyze each of the subsamples, computes the scores of all features according to...
... GQ Zhang1, Gongqin Shen1, Josh Staiger1, Adam Troy1, and Jiayang Sun2 1 Department of Electri... more ... GQ Zhang1, Gongqin Shen1, Josh Staiger1, Adam Troy1, and Jiayang Sun2 1 Department of Electrical Engineering and Computer Science 2 Department of Statistics Case Western Reserve University, Cleveland, Ohio, USA gqz@eecs.case.edu, http://newton.case.edu ...
Uploads
Papers by Jiayang Sun