http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Flexible Modeling Approach for Current Status Survival Data via Pseudo-Observations
Han, Seungbong,Andrei, Adin-Cristian,Tsui, Kam-Wah The Korean Statistical Society 2012 응용통계연구 Vol.25 No.6
When modeling event times in biomedical studies, the outcome might be incompletely observed. In this paper, we assume that the outcome is recorded as current status failure time data. Despite well-developed literature the routine practical use of many current status data modeling methods remains infrequent due to the lack of specialized statistical software, the difficulty to assess model goodness-of-fit, as well as the possible loss of information caused by covariate grouping or discretization. We propose a model based on pseudo-observations that is convenient to implement and that allows for flexibility in the choice of the outcome. Parameter estimates are obtained based on generalized estimating equations. Examples from studies in bile duct hyperplasia and breast cancer in conjunction with simulated data illustrate the practical advantages of this model.
Multiple imputation for competing risks survival data via pseudo-observations
Han, Seungbong,Andrei, Adin-Cristian,Tsui, Kam-Wah The Korean Statistical Society 2018 Communications for statistical applications and me Vol.25 No.4
Competing risks are commonly encountered in biomedical research. Regression models for competing risks data can be developed based on data routinely collected in hospitals or general practices. However, these data sets usually contain the covariate missing values. To overcome this problem, multiple imputation is often used to fit regression models under a MAR assumption. Here, we introduce a multivariate imputation in a chained equations algorithm to deal with competing risks survival data. Using pseudo-observations, we make use of the available outcome information by accommodating the competing risk structure. Lastly, we illustrate the practical advantages of our approach using simulations and two data examples from a coronary artery disease data and hepatocellular carcinoma data.
Han, Seungbong,Lee, JungBok The Korean Statistical Society 2016 Communications for statistical applications and me Vol.23 No.4
In doubly-censored data, an originating event time and a terminating event time are interval-censored. In certain analyses of such data, a researcher might be interested in the elapsed time between the originating and terminating events as well as regression modeling with risk factors. Therefore, in this study, we introduce a model evaluation method to measure the predictive ability of a model based on negative predictive values. We use a semiparametric estimate of the predictive accuracy to provide a simple and flexible method for model evaluation of doubly-censored survival outcomes. Additionally, we used simulation studies and tested data from a prostate cancer trial to illustrate the practical advantages of our approach. We believe that this method could be widely used to build prediction models or nomograms.
( Jonggi Choi ),( Seungbong Han ),( Gi-ae Kim ),( Young-suk Lim ) 대한간학회 2018 춘·추계 학술대회 (KASL) Vol.2018 No.1
Aims: HBeAg seroclearance is one of surrogate markers by current guidelines to predict the long-term outcomes in patients with chronic hepatitis B (CHB). However, whether HBeAg seroclearance in HBeAg-positive CHB patients under antiviral treatment can reflect the long-term outcomes remains unanswered in the era of high potency antiviral agents. Methods: A historical cohort of 2,829 treatment-naïve HBeAg-positive CHB patients who initiated treatment with entecavir or tenofovir disoproxil fumarate at a tertiary referral hospital in Korea from 2007 through 2016 were included. The risk of HCC was analyzed by multivariable Cox proportional hazards model and time-dependent Cox model. Results: The mean age was 45.0 years and 1,832 (64.8%) were male. Cirrhosis was present in 1,077 (38.1%) of patients. With the median follow-up of 56.8 months, HBeAg seroclearance was observed in 905 (32.0%) patients. HBeAg seroconversion and virologic response (HBV-DNA <60 IU/mL) were achieved in 694 (24.5%) and 2249 (79.5%) patients, respectively. During 13,526 person-years of follow-up, 238 patients developed HCC, with an annual incidence rate of 1.75/100PYs. The unadjusted cumulative incidence of HCC of patients experiencing HBeAg seroclearance during the first 2-year of antiviral treatment was not significantly different compared with that of patients who persisted HBeAg-positivity (P=0.15), regardless of presence of cirrhosis. By time-dependent Cox model, HBeAg seroclearance during overall treatment period was not a significant factor for predicting HCC development (adjusted hazard ratio: 0.92, 95% confidence interval: 0.58-1.44, P=0.70). In multivariable analysis, older age, male sex, lower ALT level, lower albumin, lower platelet count, and cirrhosis at baseline were independent predictive factors for HCC development. Conclusions: In a large historical cohort of HBeAg-positive CHB patients, HBeAg seroclearance during antiviral treatment was not a significant surrogate marker for predicting HCC.
Je, Hyoung Uk,Han, Seungbong,Kim, Young Seok,Nam, Joo-Hyun,Kim, Hak Jae,Kim, Jae Weon,Park, Won,Bae, Duk-Soo,Kim, Jin Hee,Shin, So Jin,Kim, Juree,Lee, Ki-Heon,Yoon, Mee Sun,Kim, Seok Mo,Kim, Ji-Yoon,Y Elsevier 2014 Radiotherapy and oncology Vol.111 No.3
<P><B>Abstract</B></P> <P><B>Purpose</B></P> <P>To develop a nomogram predicting the risks of distant metastasis following postoperative adjuvant radiation therapy for early stage cervical cancer.</P> <P><B>Materials and methods</B></P> <P>We reviewed the medical records of 1069 patients from ten participating institutions. Patients were divided into two cohorts: a training set (<I>n</I> =748) and a validation set (<I>n</I> =321). The demographic, clinical, and pathological variables were included in the univariate Cox proportional hazards analysis. Clinically established and statistically significant prognostic variables were utilized to develop a nomogram.</P> <P><B>Results</B></P> <P>The model was constructed using four variables: histologic type, pelvic lymph node involvement, depth of stromal invasion, and parametrial invasion. This model demonstrated good calibration and discrimination, with an internally validated concordance index of 0.71 and an externally validated c-index of 0.65. Compared to FIGO staging, which showed a broad range in terms of distant metastasis, the developed nomogram can accurately predict individualized risks based on individual risk factors.</P> <P><B>Conclusions</B></P> <P>The devised model offers a significantly accurate level of prediction and discrimination. In clinical practice it could be useful for counseling patients and selecting the patient group who could benefit from more intensive/further chemotherapy, once validated in a prospective patient cohort.</P>