Bayesian proportional hazards model with latent variables

2017 ◽  
Vol 28 (4) ◽  
pp. 986-1002 ◽  
Author(s):  
Deng Pan ◽  
Kai Kang ◽  
Chunjie Wang ◽  
Xinyuan Song
Keyword(s):  
Risk Factors ◽  
Factor Analysis ◽  
Exploratory Factor Analysis ◽  
Latent Variables ◽  
Proportional Hazards ◽  
Proportional Hazards Model ◽  
Failure Time ◽  
Analysis Model ◽  
Factor Analysis Model ◽  
Hazards Model

We consider a joint modeling approach that incorporates latent variables into a proportional hazards model to examine the observed and latent risk factors of the failure time of interest. An exploratory factor analysis model is used to characterize the latent risk factors through multiple observed variables. In commonly used confirmatory factor analysis, the number of latent variables and their observed indicators are specified prior to analysis. By contrast, the exploratory factor analysis model allows such information to be fully determined by the data. A Bayesian approach coupled with efficient sampling methods is developed to conduct statistical inference, and the performance of the proposed methodology is confirmed through simulations. The model is applied to a study on the risk factors of chronic kidney disease for patients with type 2 diabetes.

A unified approach to variable selection for Cox’s proportional hazards model with interval-censored failure time data

2021 ◽  
pp. 096228022110092
Author(s):  
Mingyue Du ◽  
Hui Zhao ◽  
Jianguo Sun
Keyword(s):  
Variable Selection ◽  
Proportional Hazards ◽  
Proportional Hazards Model ◽  
Failure Time ◽  
Significant Feature ◽  
Failure Time Data ◽  
Time Data ◽  
Hazards Model ◽  
Interval Censored ◽  
Cox's Proportional Hazards Model

Cox’s proportional hazards model is the most commonly used model for regression analysis of failure time data and some methods have been developed for its variable selection under different situations. In this paper, we consider a general type of failure time data, case K interval-censored data, that include all of other types discussed as special cases, and propose a unified penalized variable selection procedure. In addition to its generality, another significant feature of the proposed approach is that unlike all of the existing variable selection methods for failure time data, the proposed approach allows dependent censoring, which can occur quite often and could lead to biased or misleading conclusions if not taken into account. For the implementation, a coordinate descent algorithm is developed and the oracle property of the proposed method is established. The numerical studies indicate that the proposed approach works well for practical situations and it is applied to a set of real data arising from Alzheimer’s Disease Neuroimaging Initiative study that motivated this study.

Risk factors for disease progression in low-teens normal-tension glaucoma

2019 ◽  
Vol 104 (1) ◽  
pp. 81-86 ◽  
Author(s):  
Sung Uk Baek ◽  
Ahnul Ha ◽  
Dai Woo Kim ◽  
Jin Wook Jeoung ◽  
Ki Ho Park ◽  
...  
Keyword(s):  
Risk Factors ◽  
Disease Progression ◽  
Proportional Hazards ◽  
Proportional Hazards Model ◽  
Normal Tension Glaucoma ◽  
Cox Proportional Hazards ◽  
Cox Proportional Hazards Model ◽  
Hazards Model ◽  
Diurnal Iop

Background/AimsTo investigate the risk factors for disease progression of normal-tension glaucoma (NTG) with pretreatment intraocular pressure (IOP) in the low-teens.MethodsOne-hundred and two (102) eyes of 102 patients with NTG with pretreatment IOP≤12 mm Hg who had been followed up for more than 60 months were retrospectively enrolled. Patients were divided into progressor and non-progressor groups according to visual field (VF) progression as correlated with change of optic disc or retinal nerve fibre layer defect. Baseline demographic and clinical characteristics including diurnal IOP and 24 hours blood pressure (BP) were compared between the two groups. The Cox proportional hazards model was used to identify the risk factors for disease progression.ResultsThirty-six patients (35.3%) were classified as progressors and 66 (64.7%) as non-progressors. Between the two groups, no significant differences were found in the follow-up periods (8.7±3.4 vs 7.7±3.2 years; p=0.138), baseline VF mean deviation (−4.50±5.65 vs −3.56±4.30 dB; p=0.348) or pretreatment IOP (11.34±1.21 vs 11.17±1.06 mm Hg; p=0.121). The multivariate Cox proportional hazards model indicated that greater diurnal IOP at baseline (HR=1.609; p=0.004), greater fluctuation of diastolic BP (DBP; HR=1.058; p=0.002) and presence of optic disc haemorrhage during follow-up (DH; HR=3.664; p=0.001) were risk factors for glaucoma progression.ConclusionIn the low-teens NTG eyes, 35.3% showed glaucoma progression during the average 8.7 years of follow-up. Fluctuation of DBP and diurnal IOP as well as DH were significantly associated with greater probability of disease progression.

Psychometrics of the Gratitude Questionnaire-6 in African-Americans at Risk for Cardiovascular Disease

2020 ◽  
Vol 42 (12) ◽  
pp. 1148-1154
Author(s):  
Lakeshia Cousin ◽  
Laura Redwine ◽  
Christina Bricker ◽  
Kevin Kip ◽  
Harleah Buck
Keyword(s):  
At Risk ◽  
Factor Analysis ◽  
Confirmatory Factor Analysis ◽  
Exploratory Factor Analysis ◽  
Factor Structure ◽  
Well Being ◽  
Divergent Validity ◽  
Analysis Model ◽  
Factor Analysis Model ◽  
Confirmatory Factor

Psychometrics of the Gratitude Questionnaire-6, which measures dispositional gratitude, was originally estimated in healthy college students. The purpose of this study was to examine the scales’ factor structure, convergent/divergent validity, and reliability among 298 AA adults at risk for CVD in the community. Analyses were performed using bivariate correlations, exploratory factor analysis, and confirmatory factor analysis. The scale demonstrated acceptable estimates for internal consistency (Cronbach’s α = 0.729). Our exploratory factor analysis results yielded a one-factor structure consistent with the original instrument, and the confirmatory factor analysis model was a good fit. Convergent/divergent validity was supported by the association with positive affect (coefficient = 0.482, 95% CI = [0.379, 0.573], spiritual well-being (coefficient = 0.608, 95% CI = [0.519, 0.685], and depressive symptoms (coefficient = −0.378, 95% CI = [−0.475, −0.277]. Findings supported the scale’s reliability and convergent/divergent validity among AAs at risk for CVD.

scholarly journals Incidence and Survival Changes in Patients with Esophageal Adenocarcinoma during 1984–2013

2019 ◽  
Vol 2019 ◽  
pp. 1-11 ◽  
Author(s):  
Zhang Haiyu ◽  
Pei Xiaofeng ◽  
Mo Xiangqiong ◽  
Qiu Junlan ◽  
Zheng Xiaobin ◽  
...  
Keyword(s):  
United States ◽  
Risk Factors ◽  
Esophageal Adenocarcinoma ◽  
Proportional Hazards ◽  
Proportional Hazards Model ◽  
The United States ◽  
Cox Proportional Hazards ◽  
Cox Proportional Hazards Model ◽  
Hazards Model ◽  
Potential Risk Factors

Purpose. The morbidity of esophageal adenocarcinoma (EAC) has significantly increased in Western countries. We aimed to identify trends in incidence and survival in patients with EAC in the recent 30 years and then analyzed potential risk factors, including race, sex, age, and socioeconomic status (SES). Methods. All data were collected from the Surveillance, Epidemiology, and End Results or SEER database. Kaplan–Meier analysis and the Cox proportional hazards model were conducted to compare the differences in survival between variables, including sex, race, age, and SES, as well as to evaluate the association of these factors with prognosis. Results. A total of 16,474 patients with EAC were identified from 1984 to 2013 in the United States. Overall incidence increased every 10 years from 1.8 to 3.1 to 3.9 per 100. Overall survival gradually improved (p<0.0001), which was evident in male patients ((hazard ratio (HR) = 1.111; 95% confidence interval (CI) (1.07, 1.15)); however, the 5-year survival rate remained low (20.1%). The Cox proportional hazards model identified old age, black ethnicity, and medium/high poverty as risk factors for EAC (HR = 1.018; 95% CI (1.017, 1.019; HR = 1.240, 95% CI (1.151,1.336), HR = 1.000, 95% CI (1.000, 1.000); respectively). Conclusions. The incidence of EAC in the United States increased over time. Survival advantage was observed in white patients and patients in the low-poverty group. Sex was an independent prognostic factor for EAC, but this finding has to be confirmed by further research.

scholarly journals An exploratory factor analysis model for slum severity index in Mexico City

Urban Studies ◽  
2019 ◽  
Vol 57 (4) ◽  
pp. 789-805 ◽  
Author(s):  
Debraj Roy ◽  
David Bernal ◽  
Michael Lees
Keyword(s):  
Factor Analysis ◽  
International Development ◽  
Mexico City ◽  
Exploratory Factor Analysis ◽  
Urban Areas ◽  
Informal Settlements ◽  
Severity Index ◽  
Development Planning ◽  
Analysis Model ◽  
Factor Analysis Model

Today, over half of the world’s population lives in urban areas and it is projected that, by 2050, two out of three people will live in a city. This increased rural–urban migration, coupled with housing poverty, has led to the growth and formation of informal settlements, commonly known as slums. In Mexico, 25% of the urban population now live in informal settlements with varying degrees of deprivation. Although some informal neighbourhoods have contributed to the upward mobility of the inhabitants, the majority still lack basic services. Mexico City and the conurbation around it form a mega city of 21million people that has been growing in a manner qualified as ‘highly unproductive, (that) deepens inequality, raises pollution levels’ (available at:   https://www.smartcitiesdive.com/ex/sustainablecitiescollective/making-way-urban-reform-mexico/176466/ ) and contains the largest slum in the world: Neza-Chalco-Izta. Urban reforms are now aiming to improve the conditions in these slums and therefore it is very important to have reliable tools to measure the changes that are underway. In this paper, we use exploratory factor analysis to define an index of shelter deprivation in Mexico City, namely the Slum Severity Index (SSI), based on the UN-HABITAT’s definition of slum. We apply this novel approach to the Census survey of Mexico and measure the shelter deprivation levels of households from 1990 to 2010. The analysis highlights high variability in housing conditions within Mexico City. We find that the SSI decreased significantly between 1990 and 2000 as a result of several policy reforms but increased between 2000 and 2010. We also show correlations of the SSI with other social factors such as education, health and fertility. We present a validation of the SSI using Grey Level Co-occurrence Matrix (GLCM) features extracted from Very-High Resolution (VHR) remote-sensed satellite images. Finally, we show that the SSI can present a cardinally meaningful assessment of the extent of deprivation compared with a similar index defined by Connolly (Connolly P (2009) Observing the evolution of irregular settlements: Mexico city’s colonias populares, 1990 to 2005. International Development Planning Review 31: 1–35) that studies shelter deprivation in Mexico.

scholarly journals Risk Factors for Mortality in Chinese Patients on Continuous Ambulatory Peritoneal Dialysis

2015 ◽  
Vol 35 (2) ◽  
pp. 199-205 ◽  
Author(s):  
Fan Zhang ◽  
Hong Liu ◽  
Xiaoli Gong ◽  
Fuyou Liu ◽  
Youming Peng ◽  
...  
Keyword(s):  
Risk Factors ◽  
Peritoneal Dialysis ◽  
Continuous Ambulatory Peritoneal Dialysis ◽  
Proportional Hazards ◽  
Proportional Hazards Model ◽  
Patient Survival ◽  
Cox Proportional Hazards ◽  
Cox Proportional Hazards Model ◽  
Hazards Model ◽  
Kaplan Meier

ObjectiveThe intent of this study was to evaluate the clinical outcome and risk factors affecting mortality of the continuous ambulatory peritoneal dialysis (CAPD) patients in a single peritoneal dialysis (PD) center over a period of 10 years.Patients and methodsWe retrospectively analyzed patients on PD from June 2001 to June 2011. The clinical and biochemical data were collected from the medical records. Clinical variables included gender, age at the start of PD, smoking status, body mass index (BMI), cause of end-stage renal disease (ESRD), presence of diabetes mellitus and blood pressure. Biochemical variables included hemoglobin, urine volume, residual renal function (RRF), serum albumin, blood urea nitrogen (BUN), creatinine, total cholesterol, triglyceride, comorbidities, and outcomes. Survival curves were made by the Kaplan-Meier method. Univariate and multivariate analyses to identify mortality risk factors were performed using the Cox proportional hazard regression model.ResultsA total of 421 patients were enrolled, 269 of whom were male (63.9%). The mean age at the start of PD was 57.9 ± 14.8 years. Chronic glomerulonephritis was the most common cause of ESRD (39.4%). Estimation of patient survival by Kaplan-Meier was 92.5%, 80.2%, 74.4%, and 55.7% at 1, 3, 5, and 10 years, respectively. Patient survival was associated with age (hazard ratio [HR]: 1.641 [1.027 – 2.622], p = 0.038), cardiovascular disease (HR: 1.731 [1.08 – 2.774], p = 0.023), hypertriglyceridemia (HR: 1.782 [1.11 – 2.858], p = 0.017) in the Cox proportional hazards model analysis. Estimation of technique survival by Kaplan-Meier was 86.7%, 68.8%, 55.7%, and 37.4% at 1, 3, 5, and 10 years, respectively. In the Cox proportional hazards model analysis, age (HR: 1.672 [1.176 – 2.377], p = 0.004) and hypertriglyceridemia (HR: 1.511 [1.050 – 2.174], p = 0.026) predicted technique failure.ConclusionThe PD patients in our center exhibited comparable or even superior patient survival and technical survival rates, compared with reports from other centers in China and other countries.

Frailty Approach for the Analysis of Clustered Failure Time Observations in Dental Research

2005 ◽  
Vol 84 (1) ◽  
pp. 54-58 ◽  
Author(s):  
S.K. Chuang ◽  
T. Cai ◽  
C.W. Douglass ◽  
L.J. Wei ◽  
T.B. Dodson
Keyword(s):  
Proportional Hazards ◽  
Proportional Hazards Model ◽  
Failure Time ◽  
Cox Proportional Hazards ◽  
Cox Proportional Hazards Model ◽  
Implant Failure ◽  
Failure Patterns ◽  
Hazards Model ◽  
Within Subjects ◽  
Immediate Implant

Because dental implant failure patterns tend to cluster within subjects, we hypothesized that the risk of implant failure varies among subjects. To address this hypothesis in the setting of clustered, correlated observations, we considered a retrospective cohort study where we identified a cohort having at least one implant placed. The cohort was composed of 677 patients who had 2349 implants placed. To test the hypothesis, we applied an innovative analytic method, i.e., the Cox proportional hazards model with frailty, to account for correlation within subjects and the heterogeneity of risk, i.e., frailty, among subjects for implant failure. Consistent with our hypothesis, risk for implant failure among subjects varied to a statistically significantly degree (p = 0.041). In addition, the risk for implant failure is significantly associated with several factors, including tobacco use, implant length, immediate implant placement, staging, well size, and proximity of adjacent implants or teeth.

scholarly journals An Inference-based Prognostic Framework for Health Management of Automotive Systems

2020 ◽  
Vol 7 (2) ◽  
Author(s):  
Chaitanya Sankavaram ◽  
Anuradha Kodali ◽  
Krishna Pattipati ◽  
Satnam Singh ◽  
Yilu Zhang ◽  
...  
Keyword(s):  
Proportional Hazards ◽  
Proportional Hazards Model ◽  
Failure Time ◽  
Remaining Useful Life ◽  
Survival Functions ◽  
Time Data ◽  
Automotive Systems ◽  
Multiple Fault Diagnosis ◽  
Hazards Model ◽  
Useful Life

This paper presents a unified data-driven prognostic framework that combines failure time data, static parameter data and dynamic time-series data. The framework employs proportional hazards model and a soft dynamic multiple fault diagnosis algorithm for inferring the degraded state trajectories of components and to estimate their remaining useful life times. The framework takes into account the cross-subsystem fault propagation, a case prevalent in any networked and embedded system. The key idea is to use Cox proportional hazards model to estimate the survival functions of error codes and symptoms (probabilistic test outcomes/prognostic indicators) from failure time data and static parameter data, and use them to infer the survival functions of components via soft dynamic multiple fault diagnosis algorithm. The average remaining useful life and its higher-order central moments (e.g., variance, skewness, kurtosis) can be estimated from these component survival functions. The framework is demonstrated on datasets derived from two automotive systems, namely hybrid electric vehicle regenerative braking system, and an electronic throttle control subsystem simulator. Although the proposed framework is validated on automotive systems, it has the potential to be applicable to a wide variety of systems, ranging from aerospace systems to buildings to power grids.

Sign in / Sign up

Export Citation Format

Share Document