06/03/2009 — Identification of Ovarian Cancer Symptoms in Health Insurance Claims Data

Sean Devlin

Women with ovarian cancer have reported abdominal/pelvic pain, bloating, difficulty eating or feeling full quickly, and urinary frequency/urgency prior to diagnosis. While case-control studies have been important in identifying the initial symptoms, this seminar examines how health insurance claims data can further elucidate the association between symptom prevalence and ovarian cancer, and potentially address the need for advocacy at the patient- and/or physician-level. We examine methods to discern the relative prevalence of the four symptoms and describe the association with cancer stage at diagnosis. Lastly, we explore the performance of a hypothetical passive screening tool implemented using insurance claims data.

05/27/2009 — Now you see it, now you don’t: Impact of population screening practice on perceived efficacy of cancer therapies

Maggie Au

Many cancer treatment trials are conducted in unscreened populations. As cancer screening becomes more prevalent the questionable validity of these trial results in the presence of screening is increasingly pertinent. We evaluate the impact of screening on treatment efficacy estimates. We develop expressions for cause-specific cumulative incidence in the presence of screening and use these to simulate results under different settings of lead time, overdiagnosis, treatment efficacy, and other-cause survival. Under screening, we see a reduction in the difference in cumulative incidence of prostate cancer death between the two treatment arms, a corresponding reduction in the power of a study to detect a treatment effect, and an increase in the NNT (number needed to treat). These results clearly indicate that it is important to recognize that, under screening, treatments may not attain the benefits and may cost more than would have been expected based on clinical trials of their effect in the absence of screening. Conversely, treatments shown to be ineffective in trials done in a screened population could turn out to be worthwhile in populations where screening is not performed at the population level. Addressing and taking into account these differences that result from screening is an important next step in developing appropriate clinical practice for a population based on trial results.

05/20/2009 — The Proportional Odds Model in the Sequential Monitoring of Clinical Trials

Ken Wu

In this talk, I will introduce a work in progress regarding the monitoring of clinical trials with the proportional odds model. Unlike the proportional hazards model, the hazards converge under the proportional odds model, and we believe this will more closely model treatment arms whose effects wane over time. I will begin by introducing sequential monitoring and some of the models and statistics currently used, and I will then describe the settings in which the proportional odds would be preferred. After discussing the origins and interpretation of the proportional odds model, I will talk about its estimation and some semiparametric efficiency issues that we have encountered. Finally, I will discuss the extension of this estimation to multiple interim analyses and list what questions remain.

05/13/09: Time-dependent Predictive Accuracy: Extending Binary Classification Accuracy Methods for Censored Survvival Data

Paramita Saha

I will be talking about my dissertation. In this dissertation, we characterize the prognostic value of a scalar score or a marker by extending standard binary classification accuracy summaries like sensitivity or True Positive (TP),  specificity or 1 – False Positive (FP), Receiver Operating Characteristic (ROC) curve and Area Under the ROC Curve (AUC) for censored survival data. In my dissertation, I introduce novel statistical methodology to solve some of these problems. First, we propose time-dependent accuracy measures for a marker when we have censored survival times and competing risks. We extend time-dependent definitions of TP and FP to incorporate causes of failure for competing risks outcomes. The proposed methods extend the time-dependent predictive accuracy measures of Heagerty et al. (2000), and Heagerty and Zheng (2005). Next, we propose a direct, non-parametric estimator of the time-dependent AUC curve, and show that the proposed estimator performs comparably or better than the semi-parametric AUC curve estimator proposed by Heagerty and Zheng (2005).  The proposed method extends non-parametric AUC estimates for the binary data and we establish asymptotic properties. An overall measure of concordance is also proposed. Time-dependnet markers can also be accommodated in the estimation to capture the evolving nature of the marker. Finally, we introduce a time-averaged ROc curve to summarize the predictive accuracy of a marker accrued over time. We also introduce methods for comparison of markers via this summary ROC curve and demonstrate that this approach may be used to optimize screening schedules for diseases like breast cancer.

05/06/2009 — Recent thoughts on survival analysis

Gary Chan

I will present some recent research interests on survival analysis methodologies in three broad areas. (1) Empirical Bayes and prediction of survival probabilities. (2) Prevalent cohort covariate bias and information. (3) Recurrent marker process with informative terminal event. The methods discussed would be slightly difficult in focus from the mainstream survival analysis, and I hope this will stimulate students to view survival analysis in a broader context.