Epidemiology & Biostatistics
Permanent URI for this communityhttp://hdl.handle.net/1903/7125
Browse
7 results
Search Results
Item A method for analyzing censored survival phenotype with gene expression data(Springer Nature, 2008-10-06) Wu, Tongtong; Sun, Wei; Yuan, Shinsheng; Chen, Chun-Houh; Li, Ker-ChauSurvival time is an important clinical trait for many disease studies. Previous works have shown certain relationship between patients' gene expression profiles and survival time. However, due to the censoring effects of survival time and the high dimensionality of gene expression data, effective and unbiased selection of a gene expression signature to predict survival probabilities requires further study. We propose a method for an integrated study of survival time and gene expression. This method can be summarized as a two-step procedure: in the first step, a moderate number of genes are pre-selected using correlation or liquid association (LA). Imputation and transformation methods are employed for the correlation/LA calculation. In the second step, the dimension of the predictors is further reduced using the modified sliced inverse regression for censored data (censorSIR). The new method is tested via both simulated and real data. For the real data application, we employed a set of 295 breast cancer patients and found a linear combination of 22 gene expression profiles that are significantly correlated with patients' survival rate. By an appropriate combination of feature selection and dimension reduction, we find a method of identifying gene expression signatures which is effective for survival prediction.Item Hepatitis B vaccinations among Koreans: Results from 2005 Korea National Cancer Screening Survey(Springer Nature, 2009-11-25) Juon, Hee-Soon; Choi, Kui Son; Park, Eun-Cheol; Kwak, Min-Son; Lee, SunminLiver cancer is one of most commonly diagnosed cancers among Koreans. Chronic hepatitis B virus (HBV) infection is a major risk factor for liver cancer. HBV infection can be prevented by effective screening and vaccination programs. The purpose of this study is to examine the status of HBV infection and the predictors associated with HBV vaccination. The study population was derived from the 2005 Korea National Cancer Screening Survey (KNCSS). The KNCSS is an annual cross-sectional survey that uses a nationally-representative random sampling to investigate cancer screening rates. A total of 1,786 Koreans over 40 years of age participated in this study. Of all the participants, 5.9% reported HBV positive (HBsAg+, HBsAb-), 41.8% were HBV negative but protected (HBsAg-, HBsAb+), and 52.3% were unprotected (HBsAg-, HBsAb-). Among unprotected individuals (n = 934), 23.1% reported to have received the vaccination. About half of those who had vaccinations completed the 3-shot vaccine series. In multiple analyses, education, having private cancer insurance, alcohol use, having regular check-up, and doing regular exercise were associated with completed HBV vaccination. This study result suggests that we need a liver cancer education program to increase HBV awareness and to increase the liver cancer prevention message among low educated populations.Item Identification of Factors That Relate to Gestational Age in Term and Preterm Babies Using 2002 National Birth Data(2009) Hammad, Hoda Tarek; Zhang, Guangyu; Public and Community Health; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Infant mortality and other subsequent handicaps have been found to be correlated with preterm births. The purpose of this study is to investigate which factors relate to gestational age in term and preterm babies using the 2002 Public-Use Natality data file. Using this data, an exploratory data analysis of both the important discrete and continuous variables will be conducted to obtain a general idea of the data set. This will be followed by the use of regression models to determine which explanatory variables best relate to gestational age. The results can be used to establish guidelines for monitoring and treatment plans for expectant mothers who are most susceptible to preterm labor.Item Effects of birthplace, language and length of time in the U.S. on receipt of asthma management plans among U.S. adults with current asthma(2009) Williams, Sonja; Carter-Pokras, Olivia; Public and Community Health; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Approximately 7% of the adult population in the United States suffers from asthma and only 32% of those adults have an asthma management plan, which is an important component in asthma management. Racial/ethnic minorities have higher rates of asthma and lower rates of good asthma management. There is a lack of research in examining how foreign birth and other proxy measures of acculturation may affect long term management of asthma. Using data from both the 2002 and 2003 National Health Interview Survey, this secondary data analysis examined the relationship between the receipt of asthma management plans among 18-64 year old adult asthmatics by birthplace, length of time in the U.S., and language of interview. Hispanic/Latino participants who spoke English during the interview had a 3.43 times greater odds of having an asthma management plan when compared to those who spoke Spanish (95% CI: 1.97-5.98).Item Missing Data Analysis: A Case Study of a Randomized Controlled Trial(2009) Patzer, Shaleah Mary Murphy; Zhang, Guangyu; Public and Community Health; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Missing data is a pervasive problem in the analysis of many clinical trials. In order for the analysis of a study to produce unbiased estimators, the missing data problem must be addressed. First, the missing data pattern must be established; second, the missingness mechanism must be determined; and third, the most appropriate imputation method for imputing the missing values must be found. The purpose of this paper is to explore the imputation methods best suited for the missing data from the Diet and Exercise for Elevated Risk Trial (DEER) in a secondary analysis of the data. The missingness pattern in the data set is arbitrary and the missingness mechanism is MAR. A simulation study suggests that the two best methods for imputation are subject-specific mean imputation and multiple imputation. I conclude that mean imputation is the best method for handling missing data in the DEER data set.Item Emergency Preparedness: Knowledge and Perceptions of Latin American Immigrants(1999) Carter-Pokras, Olivia; Zambrana, Ruth E.; Mora, Sonia E.; Aaby, Katherine A.This paper describes the level of public emergency knowledge and perceptions of risks among Latin American immigrants, and their preferred and actual sources of emergency preparedness information (including warning signals). Five Latino community member focus groups, and one focus group of community health workers, were conducted in a suburban county of Washington D.C. (N51). Participants came from 13 Latin American countries, and 64.7% immigrated during the previous five years. Participants had difficulty defining emergency and reported a wide range of perceived personal emergency risks: immigration problems; crime, personal insecurity, gangs; home/traffic accidents; home fires; environmental problems; and snipers. As in previous studies, few participants had received information on emergency preparedness, and most did not have an emergency plan. Findings regarding key messages and motivating factors can be used to develop clear, prioritized messages for communication regarding emergencies and emergency preparedness for Latin American immigrant communities in the U.S.Item Assessing Health Concerns and Barriers in a Heterogeneous Latino Community(The Johns Hopkins University Press, 2006) Martinez, Iveris L.; Carter-Pokras, OliviaIntroduction. Major health issues and barriers to health services for Latino immigrants were identified through community-based participatory research in Baltimore city. Methods. In collaboration with community partners, five focus groups were conducted among Latino adults from 10 countries and health service providers. Findings. Priorities across groups included chronic diseases, HIV/AIDS and STDs, mental health, and the need for ancillary services. Community members and providers did not always agree on what health matters were of primary concern. Participants expected to receive health information at the point of service. Barriers to receiving health services and information span linguistic, financial, logistical, legal, and cultural matters. Conclusions. This formative research illustrates the complexity and interrelatedness of health priorities and barriers created by social issues such as employment, legal status, and related stressors.