A review of the use of time‐varying covariates in the Fine‐Gray subdistribution hazard competing risk regression model

Austin, Peter C.; Latouche, Aurélien; Fine, Jason P.

doi:10.1002/sim.8399

Cited by 92 publications

(74 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…waist circumference, education, smoking status (including level of smoking intensity) and level of alcohol consumption. Finally, to account for the potential influence of competing risk of death ( N = 23,774), we calculated the cumulative incidence adjusted for mortality and evaluated the discrimination of the reduced model based on Fine-Gray subdistribution hazard regression [ 39 ] in both the derivation and validation samples.…”

Section: Methodsmentioning

confidence: 99%

Development and validation of a lifestyle-based model for colorectal cancer risk prediction: the LiFeCRC score

Aleksandrova

Reichmann

Kaaks

et al. 2021

BMC Med

View full text Add to dashboard Cite

Background Nutrition and lifestyle have been long established as risk factors for colorectal cancer (CRC). Modifiable lifestyle behaviours bear potential to minimize long-term CRC risk; however, translation of lifestyle information into individualized CRC risk assessment has not been implemented. Lifestyle-based risk models may aid the identification of high-risk individuals, guide referral to screening and motivate behaviour change. We therefore developed and validated a lifestyle-based CRC risk prediction algorithm in an asymptomatic European population. Methods The model was based on data from 255,482 participants in the European Prospective Investigation into Cancer and Nutrition (EPIC) study aged 19 to 70 years who were free of cancer at study baseline (1992–2000) and were followed up to 31 September 2010. The model was validated in a sample comprising 74,403 participants selected among five EPIC centres. Over a median follow-up time of 15 years, there were 3645 and 981 colorectal cancer cases in the derivation and validation samples, respectively. Variable selection algorithms in Cox proportional hazard regression and random survival forest (RSF) were used to identify the best predictors among plausible predictor variables. Measures of discrimination and calibration were calculated in derivation and validation samples. To facilitate model communication, a nomogram and a web-based application were developed. Results The final selection model included age, waist circumference, height, smoking, alcohol consumption, physical activity, vegetables, dairy products, processed meat, and sugar and confectionary. The risk score demonstrated good discrimination overall and in sex-specific models. Harrell’s C-index was 0.710 in the derivation cohort and 0.714 in the validation cohort. The model was well calibrated and showed strong agreement between predicted and observed risk. Random survival forest analysis suggested high model robustness. Beyond age, lifestyle data led to improved model performance overall (continuous net reclassification improvement = 0.307 (95% CI 0.264–0.352)), and especially for young individuals below 45 years (continuous net reclassification improvement = 0.364 (95% CI 0.084–0.575)). Conclusions LiFeCRC score based on age and lifestyle data accurately identifies individuals at risk for incident colorectal cancer in European populations and could contribute to improved prevention through motivating lifestyle change at an individual level.

show abstract

Section: Methodsmentioning

confidence: 99%

Development and validation of a lifestyle-based model for colorectal cancer risk prediction: the LiFeCRC score

Aleksandrova

Reichmann

Kaaks

et al. 2021

BMC Med

View full text Add to dashboard Cite

show abstract

“…However, the official Stata command to implement the regression does allow for the variables to be specified as time varying, and it is not uncommon to see time-varying covariates appear in such estimates. Austin et al (2020) advise caution against including time varying covariates in such regressions, due to difficulty in estimating their effects on the CIF (similar interpretability issues also arise when applying Cox regressions…”

Section: Estimationmentioning

confidence: 99%

Time To Go? Head Coach Quits and Dismissals in Professional Football

Bryson¹,

Buraimo

Farnell

et al. 2020

De Economist

View full text Add to dashboard Cite

That football Head Coaches will be dismissed for poor performance and will quit when they have better outside options seems obvious. But owners may find it hard to distinguish poor performance from bad luck and may find it difficult to identify and attract talented Head Coaches from other clubs even if their current Head Coach is performing below expectations. Equally, Head Coaches may have few options to move to better clubs even when they are performing well. Using rich data on Head Coach characteristics we identify determinants of quits and dismissals across four professional football leagues over the period 2002–2015. We find that Head Coaches’ probabilities of dismissal are significantly lower when the team is performing above expectations, with the effect strongest for recent games. However, in contrast to earlier studies, we find that performing above expectations also reduces the probability of Head Coach quits. Head Coach success in the past, as well as Head Coach experience, reduce the probability of being dismissed, even when conditioning on team performance, suggesting Head Coach human capital has some ‘protective’ effect in managerial careers. Past experience has little effect on quit probabilities—with the exception of tenure at the current employer, which is associated with lower quit rates. We test the robustness of our results by confining estimates to first exits, within-season departures and by dealing with unobserved Head Coach heterogeneity.

show abstract

“…mortality), including time-varying variables may lead to unclear inferences and bias. 58 Finally, since the introduction of DAA therapy in BC is relatively new, the BC-HTC has not yet accrued enough follow-up time to assess the impact of DAA therapy on cancer development. However, it should be noted that the main objective of the current study was to assess the association between mono and co/triple-viral infections on cancer risk, irrespective of treatment status.…”

Section: Discussion/conclusionmentioning

confidence: 99%

Elevated risk of colorectal, liver, and pancreatic cancers among HCV, HBV and/or HIV (co)infected individuals in a population based cohort in Canada

et al. 2021

View full text Add to dashboard Cite

Introduction: Studies of the impact of hepatitis C virus (HCV), hepatitis B virus (HBV) and HIV mono and co-infections on the risk of cancer, particularly extra-hepatic cancer, have been limited and inconsistent in their findings. Methods: In the British Columbia Hepatitis Testers Cohort, we assessed the risk of colorectal, liver, and pancreatic cancers in association with HCV, HBV and HIV infection status. Using Fine and Gray adjusted proportional subdistribution hazards models, we assessed the impact of infection status on each cancer, accounting for competing mortality risk. Cancer occurrence was ascertained from the BC Cancer Registry. Results: Among 658,697 individuals tested for the occurrence of all three infections, 1407 colorectal, 1294 liver, and 489 pancreatic cancers were identified. Compared to uninfected individuals, the risk of colorectal cancer was significantly elevated among those with HCV (Hazard ration [HR] 2.99; 95% confidence interval [CI] 2.55–3.51), HBV (HR 2.47; 95% CI 1.85–3.28), and HIV mono-infection (HR 2.30; 95% CI 1.47–3.59), and HCV/HIV co-infection. The risk of liver cancer was significantly elevated among HCV and HBV mono-infected and all co-infected individuals. The risk of pancreatic cancer was significantly elevated among individuals with HCV (HR 2.79; 95% CI 2.01–3.70) and HIV mono-infection (HR 2.82; 95% CI 1.39–5.71), and HCV/HBV co-infection. Discussion/Conclusion: Compared to uninfected individuals, the risk of colorectal, pancreatic and liver cancers was elevated among those with HCV, HBV and/or HIV infection. These findings highlight the need for targeted cancer prevention and diligent clinical monitoring for hepatic and extrahepatic cancers in infected populations.

show abstract

A review of the use of time‐varying covariates in the Fine‐Gray subdistribution hazard competing risk regression model

Cited by 92 publications

References 29 publications

Development and validation of a lifestyle-based model for colorectal cancer risk prediction: the LiFeCRC score

Development and validation of a lifestyle-based model for colorectal cancer risk prediction: the LiFeCRC score

Time To Go? Head Coach Quits and Dismissals in Professional Football

Elevated risk of colorectal, liver, and pancreatic cancers among HCV, HBV and/or HIV (co)infected individuals in a population based cohort in Canada

Contact Info

Product

Resources

About