Time-dependent prognostic score matching for recurrent event analysis to evaluate a treatment assigned during follow-up

Abstract Background When dealing with recurrent events in observational studies it is common to include subjects who became at risk before follow-up. This phenomenon is known as left censoring, and simply ignoring these prior episodes can lead to biased and inefficient estimates. We aimed to propose a statistical method that performs well in this setting. Methods Our proposal was based on the use of models with specific baseline hazards. In this, the number of prior episodes were imputed when unknown and stratified according to whether the subject had been at risk of presenting the event before t = 0. A frailty term was also used. Two formulations were used for this “Specific Hazard Frailty Model Imputed” based on the “counting process” and “gap time.” Performance was then examined in different scenarios through a comprehensive simulation study. Results The proposed method performed well even when the percentage of subjects at risk before follow-up was very high. Biases were often below 10% and coverages were around 95%, being somewhat conservative. The gap time approach performed better with constant baseline hazards, whereas the counting process performed better with non-constant baseline hazards. Conclusions The use of common baseline methods is not advised when knowledge of prior episodes experienced by a participant is lacking. The approach in this study performed acceptably in most scenarios in which it was evaluated and should be considered an alternative in this context. It has been made freely available to interested researchers as R package miRecSurv.

Download Full-text

Additive rates model for recurrent event data with intermittently observed time-dependent covariates

Statistical Methods in Medical Research ◽

10.1177/09622802211027593 ◽

2021 ◽

Vol 30 (10) ◽

pp. 2239-2255

Author(s):

Tianmeng Lyu ◽

Xianghua Luo ◽

Chiung-Yu Huang ◽

Yifei Sun

Keyword(s):

Recurrent Events ◽

Epidemiologic Study ◽

Recurrent Event ◽

Time Dependent ◽

Occurrence Rate ◽

Absolute Difference ◽

Event Data ◽

Recurrent Event Data ◽

Time Dependent Covariates

Various regression methods have been proposed for analyzing recurrent event data. Among them, the semiparametric additive rates model is particularly appealing because the regression coefficients quantify the absolute difference in the occurrence rate of the recurrent events between different groups. Estimation of the additive rates model requires the values of time-dependent covariates being observed throughout the entire follow-up period. In practice, however, the time-dependent covariates are usually only measured at intermittent follow-up visits. In this paper, we propose to kernel smooth functions involving time-dependent covariates across subjects in the estimating function, as opposed to imputing individual covariate trajectories. Simulation studies show that the proposed method outperforms simple imputation methods. The proposed method is illustrated with data from an epidemiologic study of the effect of streptococcal infections on recurrent pharyngitis episodes.

Download Full-text

The impact of statin therapy after surgical or endovascular treatment of cerebral aneurysms

Journal of Neurosurgery ◽

10.3171/2019.3.jns183500 ◽

2020 ◽

Vol 133 (1) ◽

pp. 182-189

Author(s):

Tae-Jin Song ◽

Seung-Hun Oh ◽

Jinkwon Kim

Keyword(s):

Statin Therapy ◽

Coil Embolization ◽

Primary Outcome ◽

Cox Regression ◽

Cerebral Aneurysms ◽

Time Dependent ◽

Lipid Lowering ◽

Surgical Clipping ◽

The Impact

OBJECTIVECerebral aneurysms represent the most common cause of spontaneous subarachnoid hemorrhage. Statins are lipid-lowering agents that may expert multiple pleiotropic vascular protective effects. The authors hypothesized that statin therapy after coil embolization or surgical clipping of cerebral aneurysms might improve clinical outcomes.METHODSThis was a retrospective cohort study using the National Health Insurance Service–National Sample Cohort Database in Korea. Patients who underwent coil embolization or surgical clipping for cerebral aneurysm between 2002 and 2013 were included. Based on prescription claims, the authors calculated the proportion of days covered (PDC) by statins during follow-up as a marker of statin therapy. The primary outcome was a composite of the development of stroke, myocardial infarction, and all-cause death. Multivariate time-dependent Cox regression analyses were performed.RESULTSA total of 1381 patients who underwent coil embolization (n = 542) or surgical clipping (n = 839) of cerebral aneurysms were included in this study. During the mean (± SD) follow-up period of 3.83 ± 3.35 years, 335 (24.3%) patients experienced the primary outcome. Adjustments were performed for sex, age (as a continuous variable), treatment modality, aneurysm rupture status (ruptured or unruptured aneurysm), hypertension, diabetes mellitus, household income level, and prior history of ischemic stroke or intracerebral hemorrhage as time-independent variables and statin therapy during follow-up as a time-dependent variable. Consistent statin therapy (PDC > 80%) was significantly associated with a lower risk of the primary outcome (adjusted hazard ratio 0.34, 95% CI 0.14–0.85).CONCLUSIONSConsistent statin therapy was significantly associated with better prognosis after coil embolization or surgical clipping of cerebral aneurysms.

Download Full-text

Rituximab-Containing Risk-Adapted Treatment Strategy in Nodular Lymphocyte Predominant Hodgkin Lymphoma: 7-Years Follow-Up

Cancers ◽

10.3390/cancers13081760 ◽

2021 ◽

Vol 13 (8) ◽

pp. 1760

Author(s):

Novella Pugliese ◽

Marco Picardi ◽

Roberta Della Pepa ◽

Claudia Giordano ◽

Francesco Muriano ◽

...

Keyword(s):

Side Effects ◽

Hodgkin Lymphoma ◽

Prognostic Score ◽

Single Agent ◽

Response To Therapy ◽

Baseline Risk ◽

Historical Cohort ◽

Treatment Groups

Background: Nodular lymphocyte predominant Hodgkin lymphoma (NLPHL) is a rare variant of HL that accounts for 5% of all HL cases. The expression of CD20 on neoplastic lymphocytes provides a suitable target for novel treatments based on Rituximab. Due to its rarity, consolidated and widely accepted treatment guidelines are still lacking for this disease. Methods: Between 1 December 2007 and 28 February 2018, sixteen consecutive newly diagnosed adult patients with NLPHL received Rituximab (induction ± maintenance)-based therapy, according to the baseline risk of German Hodgkin Study Group prognostic score system. The treatment efficacy and safety of the Rituximab-group were compared to those of a historical cohort of 12 patients with NLPHL who received Doxorubicin, Bleomycin, Vinblastine, Dacarbazine (ABVD) chemotherapy followed by radiotherapy (RT), if needed, according to a similar baseline risk. The primary outcome was progression-free survival (PFS) and secondary outcomes were overall survival (OS) and side-effects (according to the Common Terminology Criteria for Adverse Events, v4.03). Results: After a 7-year follow-up (range, 1–11 years), PFS was 100% for patients treated with the Rituximab-containing regimen versus 66% for patients of the historical cohort (p = 0.036). Four patients in the latter group showed insufficient response to therapy. The PFS for early favorable and early unfavorable NLPHLs was similar between treatment groups, while a better PFS was recorded for advanced-stages treated with the Rituximab-containing regimen. The OS was similar for the two treatment groups. Short- and long-term side-effects were more frequently observed in the historical cohort. Grade ≥3 neutropenia was more frequent in the historical cohort compared with the Rituximab-group (58.3% vs. 18.7%, respectively; p = 0.03). Long-term non-hematological toxicities were observed more frequently in the historical cohort. Conclusion: Our results confirm the value of Rituximab in NLPHL therapy and show that Rituximab (single-agent) induction and maintenance in a limited-stage, or Rituximab with ABVD only in the presence of risk factors, give excellent results while sparing cytotoxic agent- and/or RT-related damage. Furthermore, Rituximab inclusion in advanced-stage therapeutic strategy seems to improve PFS compared to conventional chemo-radiotherapy.

Download Full-text

Improved risk estimation of locoregional recurrence, secondary contralateral tumors and distant metastases in early breast cancer: the INFLUENCE 2.0 model

Breast Cancer Research and Treatment ◽

10.1007/s10549-021-06335-z ◽

2021 ◽

Author(s):

Vinzenz Völkel ◽

Tom A. Hueting ◽

Teresa Draeger ◽

Marissa C. van Maaren ◽

Linda de Munck ◽

...

Keyword(s):

Breast Cancer ◽

Locoregional Recurrence ◽

Clinical Decision Making ◽

Metastatic Breast ◽

Distant Metastases ◽

Time Dependent ◽

Individual Risk ◽

Primary Tumors ◽

Statistical Approaches

Abstract Purpose To extend the functionality of the existing INFLUENCE nomogram for locoregional recurrence (LRR) of breast cancer toward the prediction of secondary primary tumors (SP) and distant metastases (DM) using updated follow-up data and the best suitable statistical approaches. Methods Data on women diagnosed with non-metastatic invasive breast cancer were derived from the Netherlands Cancer Registry (n = 13,494). To provide flexible time-dependent individual risk predictions for LRR, SP, and DM, three statistical approaches were assessed; a Cox proportional hazard approach (COX), a parametric spline approach (PAR), and a random survival forest (RSF). These approaches were evaluated on their discrimination using the Area Under the Curve (AUC) statistic and on calibration using the Integrated Calibration Index (ICI). To correct for optimism, the performance measures were assessed by drawing 200 bootstrap samples. Results Age, tumor grade, pT, pN, multifocality, type of surgery, hormonal receptor status, HER2-status, and adjuvant therapy were included as predictors. While all three approaches showed adequate calibration, the RSF approach offers the best optimism-corrected 5-year AUC for LRR (0.75, 95%CI: 0.74–0.76) and SP (0.67, 95%CI: 0.65–0.68). For the prediction of DM, all three approaches showed equivalent discrimination (5-year AUC: 0.77–0.78), while COX seems to have an advantage concerning calibration (ICI < 0.01). Finally, an online calculator of INFLUENCE 2.0 was created. Conclusions INFLUENCE 2.0 is a flexible model to predict time-dependent individual risks of LRR, SP and DM at a 5-year scale; it can support clinical decision-making regarding personalized follow-up strategies for curatively treated non-metastatic breast cancer patients.

Download Full-text

Risk Factors for Prostate Cancer Detection After a Negative Biopsy: A Novel Multivariable Longitudinal Approach

Journal of Clinical Oncology ◽

10.1200/jco.2008.20.3422 ◽

2010 ◽

Vol 28 (10) ◽

pp. 1714-1720 ◽

Cited By ~ 50

Author(s):

Peter H. Gann ◽

Angela Fought ◽

Ryan Deaton ◽

William J. Catalona ◽

Edward Vonesh

Keyword(s):

Prostate Cancer ◽

Risk Factors ◽

Specific Antigen ◽

Time Dependent ◽

Negative Biopsy ◽

Gland Volume ◽

Piecewise Exponential ◽

Over Time ◽

Negative Biopsies

Purpose To introduce a novel approach for the time-dependent quantification of risk factors for prostate cancer (PCa) detection after an initial negative biopsy. Patients and Methods Data for 1,871 men with initial negative biopsies and at least one follow-up biopsy were available. Piecewise exponential regression models were developed to quantify hazard ratios (HRs) and define cumulative incidence curves for PCa detection for subgroups with specific patterns of risk factors over time. Factors evaluated included age, race, serum prostate-specific antigen (PSA) concentration, PSA slope, digital rectal examination, dysplastic glands or prostatitis on biopsy, ultrasound gland volume, urinary symptoms, and number of negative biopsies. Results Four hundred sixty-five men had PCa detected, after a mean follow-up time of 2.8 years. All of the factors were independent predictors of PCa detection except for PSA slope, as a result of its correlation with time-dependent PSA level, and race. PSA (HR = 3.90 for > 10 v 2.5 to 3.9 ng/mL), high-grade prostatic intraepithelial neoplasia/atypical glands (HR = 2.97), gland volume (HR = 0.39 for > 50 v < 25 mL), and number of repeat biopsies (HR = 0.36 for two v zero repeat biopsies) were the strongest predictors. Men with high-risk versus low-risk event histories had a 20-fold difference in PCa detection over 5 years. Conclusion Piecewise exponential models provide an approach to longitudinal analysis of PCa risk that allows clinicians to see the interplay of risk factors as they unfold over time for individual patients. With these models, it is possible to identify distinct subpopulations with dramatically different needs for monitoring and repeat biopsy.

Download Full-text

Conservative Management of Medication-Related Osteonecrosis of the Jaws (MRONJ): A Retrospective Cohort Study

Antibiotics ◽

10.3390/antibiotics10020195 ◽

2021 ◽

Vol 10 (2) ◽

pp. 195

Author(s):

Elena M. Varoni ◽

Niccolò Lombardi ◽

Giulio Villa ◽

Alberto Pispero ◽

Andrea Sardella ◽

...

Keyword(s):

Conservative Management ◽

Prognostic Score ◽

Clinical History ◽

Osteonecrosis Of The Jaw ◽

Pharmacological Therapy ◽

Complete Healing ◽

High Rate ◽

Secondary Outcome ◽

Severe Side Effect

Background: Medication-related osteonecrosis of the jaw (MRONJ) is a severe side effect of bisphosphonates and anti-resorptive drugs prescribed for treatment of severe osteoporosis, Paget’s disease, and bone malignancies. The aim of this study was to evaluate the clinical outcome of a combined pharmacological and surgical management strategy on patients affected by MRONJ. Materials and methods: Medical records of patients with MRONJ were retrospectively examined to collect clinical history data. Conservative management included an initial pharmacological phase with antibiotics and antiseptic agents, followed by surgical intervention to remove bone sequestrum. Primary outcomes were healing from MRONJ at short term (1 month after surgery) and at longer term (3 months after surgery). Secondary outcome was assessment of recurrences at longer-term follow-up. Results: Thirty-five patients were included in the study with mean follow-up of 23.86 ± 18.14 months. Seven cases showed spontaneous exfoliation of necrotic bone during pharmacological therapy, which in one case did not require any further intervention. At 1-month posttreatment, 31 out of 35 (88.5%) patients showed complete healing. The 25 patients who were followed for at least 3 months revealed a healing rate of 92% (23/25). Recurrences occurred in 7 patients out 23 who showed the long-term healing, after a mean period of 7.29 ± 3.45 months. The prognostic score (University of Connecticut Osteonecrosis Numerical Scale—UCONNS) was significantly higher (p = 0.01) in patients with poor healing as compared to complete healing, both at 1 and 3 months posttreatment. Conclusions: A MRONJ treatment approach based on a combined pharmacological and surgical treatment strategy showed a high rate of healing and few recurrences.

Download Full-text

Comparison of Statistical Models For Estimating Intervention Effects Based On Time-To-Recurrent-Event In Stepped Wedge Cluster Randomized Trial Using Open Cohort Design

10.21203/rs.3.rs-999906/v1 ◽

2021 ◽

Author(s):

Shunsuke Oyamada ◽

Shih-Wei Chiu ◽

Takuhiro Yamaguchi

Keyword(s):

Monte Carlo ◽

Monte Carlo Simulations ◽

Statistical Models ◽

Randomised Trial ◽

Recurrent Event ◽

Cluster Randomised Trial ◽

Stepped Wedge ◽

Intervention Effects ◽

Cohort Design

Abstract Background: There are currently no methodological studies on the performance of the statistical models for estimating intervention effects based on the time-to-recurrent-event (TTRE) in stepped wedge cluster randomised trial (SWCRT) using an open cohort design. This study aims to address this by evaluating the performance of these statistical models using an open cohort design with the Monte Carlo simulation in various settings and their application using an actual example.Methods: Using Monte Carlo simulations, we evaluated the performance of the existing extended Cox proportional hazard models, i.e., the Andersen-Gill (AG), Prentice-Williams-Peterson Total-Time (PWP-TT), and Prentice-Williams-Peterson Gap-time (PWP-GT) models, using the settings of several event generation models and true intervention effects, with and without stratification by clusters. Unidirectional switching in SWCRT was represented using time-dependent covariates.Results: Using Monte Carlo simulations with the various described settings, the PWP-GT model with stratification by clusters showed the best performance in most settings and reasonable performance in the others. The only situation in which the performance of the PWP-TT model with stratification by clusters was not inferior to that of the PWP-GT model with stratification by clusters was when there was a certain amount of follow-up period, and the timing of the trial entry was random within the trial period, including the follow-up period. The AG model performed well only in a specific setting. By analysing actual examples, it was found that almost all the statistical models suggested that the risk of events during the intervention condition may be somewhat higher than in the control, although the difference was not statistically significant.Conclusions: The PWP-GT model with stratification by clusters had the most reasonable performance when estimating intervention effects based on the TTRE in SWCRT in various settings using an open cohort design.

Download Full-text

NISAR-F SCORE: a simple risk stratification tool for patients implanted with cardiac resynchronization therapy

EP Europace ◽

10.1093/europace/euab116.457 ◽

2021 ◽

Vol 23 (Supplement_3) ◽

Author(s):

J Correia ◽

L Goncalves ◽

I Pires ◽

J Santos ◽

V Neto ◽

...

Keyword(s):

Ejection Fraction ◽

Cardiac Resynchronization Therapy ◽

Cox Regression ◽

Nyha Class ◽

Prognostic Score ◽

Roc Curves ◽

Cardiac Resynchronization ◽

Class Iii ◽

Resynchronization Therapy

Abstract Funding Acknowledgements Type of funding sources: None. Introduction Individualized estimation of prognosis after cardiac resynchronization therapy (CRT) remains challenging. Outcomes in this group of patients are influenced by multiple factors and a comprehensive and customized approach to estimate prognosis after CRT is lacking Aims To develop and validate a simple prognostic score for patients implanted with CRT (NISAR-F score), based on readily available clinical and echocardiographic variables to predict the combined endpoints of death or hospitalization in 24 months. Methods A single-centre retrospective study was conducted with inclusion of all consecutive patients who underwent CRT implantation between 2012 and 2019. Follow-up started after CRT implantation and ended upon death, hospitalization or 24 months after study entry. Survival analysis was performed using a multivariate Cox regression model, in order to analyze the effect on survival /hospitalization in 24 months of the following factors: age, gender, NYHA Class III-IV, ischemic heart failure, type 2 diabetes, arterial hypertension, dyslipidemia and ejection fraction < 21%. According to the analysis, points were attributed to each factor. Afterwards, the NISAR-F score was calculated for each patient, summing the points of each variable. The authors finally created ROC curves for the NISAR-F score to predict the occurrence of the combined endpoint in 2 groups of patients: CRT responders (ejection fraction increase of at least 10% after CRT implantation) and CRT non-responders. The statistical analysis was performed in SPSS. Results 102 patients were included in the study (75.4% male, mean age 68 ± 10.46 years). 10(9.8%) of the patients were re-hospitalized and 8 (7.8%) died during the 24-month follow-up. After calculating NISAR-F score for each patient, area under ROC curves were obtained. The analysis of the ROC curves allows us to confirm the good performance of the score created [responders group (AUC 0.812) vs non-responders (AUC 0.721)]. Conclusion The NISAR-F score is a useful tool to predict the combined endpoint (mortality and hospitalization in 24 months) after CRT implantation, in both responders and non-responders, revealing good performance of this new and simple score based only on clinical and echocardiographic variables.

Download Full-text

The Glasgow Prognostic Score Determined During Concurrent Chemoradiotherapy Is an Independent Predictor of Survival for Cervical Cancer

International Journal of Gynecological Cancer ◽

10.1097/igc.0000000000000485 ◽

2015 ◽

Vol 25 (7) ◽

pp. 1306-1314 ◽

Cited By ~ 10

Author(s):

Takeshi Nishida ◽

Keiichiro Nakamura ◽

Junko Haraga ◽

Chikako Ogawa ◽

Tomoyuki Kusumoto ◽

...

Keyword(s):

Cervical Cancer ◽

Concurrent Chemoradiotherapy ◽

Multivariate Analyses ◽

Prognostic Score ◽

Glasgow Prognostic Score ◽

Disease Free Survival ◽

Kaplan Meier ◽

The Glasgow Prognostic Score ◽

Prediction Of Prognosis

ObjectiveThe Glasgow prognostic score (GPS) determined at pretreatment is important in the prediction of prognosis in various cancers. We investigated if the GPS used both at pretreatment and during concurrent chemoradiotherapy (CCRT) could predict the prognosis of patients with cervical cancer.MethodsWe collected GPS and clinicopathological data from the medical records of 91 patients who underwent CCRT for cervical cancer; their GPSs at pretreatment and during CCRT were retrospectively analyzed for correlations with recurrence and survival. Statistical analyses were performed using the Mann-WhitneyUtest. Disease-free survival (DFS) and overall survival (OS) were analyzed using the Kaplan-Meier method. Cox’s proportional hazard regression was used for univariate and multivariate analyses.ResultsThe median follow-up for all patients who were alive at the time of last follow-up was 38.0 months (range, 1–108 months). The DFS and OS rates of patients with a high GPS during CCRT (GPS 1 + 2; 55 patients; 60.4%) were significantly shorter than those for patients with a low GPS (GPS 0; 36 patients; 39.6%) (DFS,P< 0.001; OS,P< 0.001). Furthermore, multivariate analyses showed that high GPS during CCRT was an independent prognostic factor of survival for OS (P= 0.008).ConclusionsDuring CCRT, a high GPS was revealed to be an important predictor of survival for cervical cancer.

Download Full-text