Application of Parametric Models to a Survival Analysis of Hemodialysis Patients

Montaseri, Maryam; Charati, Jamshid Yazdani; Espahbodi, Fateme

doi:10.5812/numonthly.28738

Cited by 9 publications

(15 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…According to the results of this study, parametric survival model to analyze these data is suitable due to several reasons: according to the hazard function, the use of parametric models is suitable. Parametric models may provide complementary data for physicians and authors to be alert about how risks change in the future [42]. Also, comparing standard error coefficients in parametric models and Cox regression, standard error coefficients of parametric models are smaller than Cox model.…”

Section: Discussionmentioning

confidence: 99%

Modeling the Factors Affecting the First Birth in the Family's' Fertility in Hamedan Province

Soltanian

Davar

Akhgar

et al. 2019

JPRI

View full text Add to dashboard Cite

Background: The role of fertility as the most important determinant of demographic fluctuations has given more importance to its studies compared with other demographic phenomena. In this context, different indexes are used to measure fertility patterns where the index of the first birth after marriage has received much attention. Materials and Methods: This was a cross-sectional (descriptive-analytic) study in which the fertility data of women are converted into a fictitious cohort and investigated. In this study, married woman in the age group of 15 to 49 years in 500 families in Hamedan were selected. In this study, a researcher-made questionnaire was used that included information related to the number of live births (fertility) and factors related to it (i.e. date of marriage, age, the first pregnancy, number of unwanted pregnancies, average interval between children, and the use of contraceptives). Univariate and multivariate survival analysis was carried out for the interval between marriage and the first birth. In the univariate section, using Kaplan-Meir method and log-rank test, survival functions of the interval between the first births after marriage in different predictive variables were compared. Result: Mean age of mothers at the first birth was 22.04±4.357 years and mean number of live births was 2.18±0.904. The first marriage age of women, parental education, women’s employment, the use of contraceptives, and the number of live births were at a significance level of 5%. Conclusion: It can be concluded that parental education, women’s employment, and use of contraceptives play important roles in population growth.

show abstract

Section: Discussionmentioning

confidence: 99%

Modeling the Factors Affecting the First Birth in the Family's' Fertility in Hamedan Province

Soltanian

Davar

Akhgar

et al. 2019

JPRI

View full text Add to dashboard Cite

show abstract

“…These studies utilized the Log-rank test, the standard Cox PH regression, or parametric models which are suitable techniques for analyzing short-term OS. 2,5,11,12,16,18,37 Moreover, among the various parametric models, the log-normal and Weibull distributions had better performance than Cox regression. 11,12 MSP models are more appropriate than Cox regression in cases with long follow-up and a high censoring rate.…”

Section: Discussionmentioning

confidence: 99%

“…2,5,11,12,16,18,37 Moreover, among the various parametric models, the log-normal and Weibull distributions had better performance than Cox regression. 11,12 MSP models are more appropriate than Cox regression in cases with long follow-up and a high censoring rate. 29,34 In our dataset, the estimated NPKM plot leveled off around 0.55 and a long plateau (almost 8.5 years) was observed over time.…”

Section: Discussionmentioning

confidence: 99%

“…9,10 In the Iranian population, the mortality rate of HD patients is about 30-50% and their five-year OS rate is almost 18-23%. 11,12 Several studies have been conducted to investigate the associated determinants of the short-term OS of patients under HD. 5,[12][13][14][15][16][17][18][19][20][21] Epidemiological studies have demonstrated that several covariates affect HD patients' OS rate including sex, body mass index (BMI), comorbid illnesses, and blood cell indices (including mean corpuscular hemoglobin concentration [MCHC], hemoglobin, red blood cell [RBC], white blood cell [WBC], albumin, cholesterol, high-density lipoprotein [HDL], and uric acid).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prognosis and Long-Term Overall Survival in Hypertensive Patients Undergoing Chronic Hemodialysis: A Multicenter Parametric Mixture Split-Population Analysis

et al. 2021

View full text Add to dashboard Cite

Background: Hemodialysis (HD) patients face long-term complications which require ongoing dialysis and follow-up. The management of hypertension among HD populations has often been neglected. This study aimed at identifying the determinants of death in hypertensive HD (HTN-HD) patients. Methods: In a multicenter retrospective cohort study (conducted from 2005 to 2018 in thirty-four HD centers affiliated with Shiraz University of Medical Sciences), the data of 725 HTN-HD patients who had at least 3 months of regular dialysis and follow-up were analyzed. Accelerated failure time mixture split-population (AFTMSP) regression was utilized to identify the factors with significant effects on long- and short-term overall survival (OS) separately. Results: Among the different AFTMSP models, the extended generalized gamma (EGG) model outperformed the others. Sex (male: event time ratio [ETR]=1.30), initial vascular access type (arteriovenous fistula: ETR=1.50), and the type of membrane flux used for HD (high-flux: ETR=1.27) had important impacts on short-term OS. Moreover, age (OR=1.06), dialysis adequacy (Kt/ Vurea≤1.2: OR=2.30), initial vascular access type (central venous catheter: OR=2.08), serum sodium (OR=0.90) concentration, and potassium (OR=0.66) concentration had significant effects on long-term OS. Conclusion: The split-population analyses were able to demonstrate that the predictors of long-term OS were different from those of short-term OS. Although the superiority of the parametric EGG model was proved in this study, further research with different databases is suggested. Moreover, these findings can be considered by health policy decision-makers to create a new guideline to enhance the long-term OS of HTN-HD patients.

show abstract

“…Los investigadores en ciencias médicas a menudo tienden a preferir el enfoque no paramétrico en lugar del paramétrico debido a que se necesitan suposiciones menores; sin embargo, algunos autores como Efron (5) y Oakes (6) , postulan que, en ciertas circunstancias, los modelos paramétricos realizan un análisis más sólido, ya que teniendo en cuenta algunas suposiciones y la selección de una distribución de probabilidad hipotética para los tiempos de supervivencia, la inferencia estadística es más precisa, lo que hace que las desviaciones estándar se vuelvan más pequeñas que cuando no existen tales suposiciones (7) . A pesar de que este tipo de enfoque involucra un proceso más riguroso, el análisis de supervivencia paramétrico ha sido abordado en diferentes estudios clínicos, en el cual se han evaluado los modelos tradicionales (exponencial, gamma, Weibull, lognormal), encontrando que la distribución Weibull muestra un mejor comportamiento para el conjunto de los datos analizados (8)(9)(10) .…”

Section: Introductionunclassified

Aplicación de modelos paramétricos alternativos para el análisis de supervivencia de pacientes con cáncer

Valencia-Orozco

Parra-Lara

Martínez

et al. 2019

Rev Peru Med Exp Salud Publica

View full text Add to dashboard Cite

En el presente artículo se describe una metodología que permite tener un acercamiento a modelos probabilísticos alternativos para el análisis de supervivencia, con censura por la derecha, distintos a los que usualmente se estudian (distribución: exponencial, gamma, Weibull y log-normal), ya que es posible que los datos no se ajusten siempre con suficiente precisión por las distribuciones existentes. La metodología utilizada permite mayor flexibilidad de modelar observaciones extremas, ubicadas generalmente en la cola derecha de la distribución de los datos, lo cual admite que algunos eventos aún tengan la probabilidad de ocurrir, lo que no sucede con los modelos tradicionales y el estimador de Kaplan-Meier, el cual estima para los tiempos más prolongados, probabilidades de supervivencia aproximadamente iguales a cero. Para mostrar la utilidad de la propuesta metodológica, se consideró una aplicación con datos reales que relaciona tiempos de supervivencia de pacientes con cáncer de colon.

show abstract

Application of Parametric Models to a Survival Analysis of Hemodialysis Patients

Cited by 9 publications

References 16 publications

Modeling the Factors Affecting the First Birth in the Family's' Fertility in Hamedan Province

Modeling the Factors Affecting the First Birth in the Family's' Fertility in Hamedan Province

Prognosis and Long-Term Overall Survival in Hypertensive Patients Undergoing Chronic Hemodialysis: A Multicenter Parametric Mixture Split-Population Analysis

Aplicación de modelos paramétricos alternativos para el análisis de supervivencia de pacientes con cáncer

Contact Info

Product

Resources

About