Assessing cure status prediction from survival data using receiver operating characteristic curves

Amico, Maïlis; Keilegom, Ingrid Van; Han, Botang

doi:10.1093/biomet/asaa080

Cited by 6 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ROC curve is the “receiver operating characteristic” curve. ROC curve analysis can test the actual positive and negative abilities [9] . AUC (Area Under Curve) is the area under the ROC curve, which is between 0.1 and 1.…”

Section: Resultsmentioning

confidence: 99%

Status Quo and Influencing Factors of Family Doctors Performance in Dongguan City

Wang

Xiao

et al. 2021

Preprint

View full text Add to dashboard Cite

Background The low-performance rate of family doctors is the most important problem in the implementation of the contract service system of family doctors in China, and improving the performance rate of family doctors has become a topic of common concern. We investigated the performance behavior of family doctors in Dongguan, Guangdong Province, to understand the current situation of family doctors performance in Dongguan, and to explore the influencing factors of their performance. Objectives To understand the status quo of family doctors performance in Dongguan City, Guangdong Province, and to explore the influencing factors of family doctors agreement fulfillment rate. Methods The multi-stage sampling method was used to randomly select family doctors in Dongguan City, Guangdong Province, to investigate the status quo of family doctors performance in community health service institutions in Dongguan City. Logistic regression analysis was used to investigate the influencing factors of family doctors performance, and decision trees and associations were used to further identify the influencing factors of family doctors performance. Results 100 family doctors participated in the survey, and 75% of them were generally able to perform their duties. Logistic regression analysis shows that whether a family doctor signs a contract with a resident is the influencing factor of family doctor performance behavior, and the higher the family doctor signing rate, the higher the family doctor performance rate. The results of decision tree analysis showed that the biggest influence factor of family doctors performance behavior is whether the family doctors are contracted residents or not. ROC curve was 0.860, and pAUC was 0.073 respectively. The most influential factor in decreasing the average Gini index of random forest is whether the family doctor signed a contract or not. The results of association rules showed that there was a correlation between whether the family doctor signed a contract or not and the performance of the family doctor. Conclusions The performance rate of family doctors in Dongguan City, Guangdong Province is relatively high. Whether family doctors sign contracts with residents is the influencing factor of family doctors performance. Improving the contract rate of family doctors is the key to improve the performance rate of family doctors.

show abstract

Section: Resultsmentioning

confidence: 99%

Status Quo and Influencing Factors of Family Doctors Performance in Dongguan City

Wang

Xiao

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In this regard, Amico et al proposed estimators of ROC and AUC based on the mixture cure model. 32 However, their formulation heavily depends on the assumption of existence of a known "cured time" beyond which all censored observations are considered as cured. We propose a completely different approach to compute the ROC curves which is independent of such assumption and is more practical.…”

Section: Application To Leukemia Datamentioning

confidence: 99%

“…For this purpose, we compute the AUC values based on the ROC curves. In this regard, Amico et al proposed estimators of ROC and AUC based on the mixture cure model 32 . However, their formulation heavily depends on the assumption of existence of a known “cured time" beyond which all censored observations are considered as cured.…”

Section: Application To Leukemia Datamentioning

confidence: 99%

On the integration of decision trees with mixture cure model

Aselisewine,

Pal

2023

Statistics in Medicine

View full text Add to dashboard Cite

The mixture cure model is widely used to analyze survival data in the presence of a cured subgroup. Standard logistic regression‐based approaches to model the incidence may lead to poor predictive accuracy of cure, specifically when the covariate effect is non‐linear. Supervised machine learning techniques can be used as a better classifier than the logistic regression due to their ability to capture non‐linear patterns in the data. However, the problem of interpret‐ability hangs in the balance due to the trade‐off between interpret‐ability and predictive accuracy. We propose a new mixture cure model where the incidence part is modeled using a decision tree‐based classifier and the proportional hazards structure for the latency part is preserved. The proposed model is very easy to interpret, closely mimics the human decision‐making process, and provides flexibility to gauge both linear and non‐linear covariate effects. For the estimation of model parameters, we develop an expectation maximization algorithm. A detailed simulation study shows that the proposed model outperforms the logistic regression‐based and spline regression‐based mixture cure models, both in terms of model fitting and evaluating predictive accuracy. An illustrative example with data from a leukemia study is presented to further support our conclusion.

show abstract

“…Note that the proposed multiple imputation technique does not rely on naive assumptions such as the existence of a known threshold time beyond which all censored observations can be considered cured. 53 The steps of multiple imputation are as follows: For a pre-defined integer N * and n * = 1 , 2 , … , N *, generate falsefalse{ J i false( n * false) : i = 1 , … , n falsefalse}, where J i false( n * false) is a Bernoulli random variable with success probability p i false( n * false). The discussion on deriving p i false( n * false) is provided in Section 2.5. For the imputed data falsefalse{ J i false( n * false) : i = 1 , … , n falsefalse}, obtain π false^ false( n * false) false( z i false) as the estimate of π false( z i false) by employing the SVM f...…”

Section: Svm-based Mixture Cure Rate Model With Interval Censoringmentioning

confidence: 99%

A support vector machine-based cure rate model for interval censored data

Pal,

Peng,

Aselisewine

et al. 2023

Stat Methods Med Res

View full text Add to dashboard Cite

The mixture cure rate model is the most commonly used cure rate model in the literature. In the context of mixture cure rate model, the standard approach to model the effect of covariates on the cured or uncured probability is to use a logistic function. This readily implies that the boundary classifying the cured and uncured subjects is linear. In this article, we propose a new mixture cure rate model based on interval censored data that uses the support vector machine to model the effect of covariates on the uncured or the cured probability (i.e. on the incidence part of the model). Our proposed model inherits the features of the support vector machine and provides flexibility to capture classification boundaries that are nonlinear and more complex. The latency part is modeled by a proportional hazards structure with an unspecified baseline hazard function. We develop an estimation procedure based on the expectation maximization algorithm to estimate the cured/uncured probability and the latency model parameters. Our simulation study results show that the proposed model performs better in capturing complex classification boundaries when compared to both logistic regression-based and spline regression-based mixture cure rate models. We also show that our model’s ability to capture complex classification boundaries improve the estimation results corresponding to the latency part of the model. For illustrative purpose, we present our analysis by applying the proposed methodology to the NASA’s Hypobaric Decompression Sickness Database.

show abstract

Assessing cure status prediction from survival data using receiver operating characteristic curves

Cited by 6 publications

References 27 publications

Status Quo and Influencing Factors of Family Doctors Performance in Dongguan City

Status Quo and Influencing Factors of Family Doctors Performance in Dongguan City

On the integration of decision trees with mixture cure model

A support vector machine-based cure rate model for interval censored data

Contact Info

Product

Resources

About