Presentation is loading. Please wait.

Presentation is loading. Please wait.

Prognostic Model Building with Biomarkers in Pharmacogenomics Trials Li-an Xu & Douglas Robinson Statistical Genetics & Biomarkers Exploratory Development,

Similar presentations


Presentation on theme: "Prognostic Model Building with Biomarkers in Pharmacogenomics Trials Li-an Xu & Douglas Robinson Statistical Genetics & Biomarkers Exploratory Development,"— Presentation transcript:

1 Prognostic Model Building with Biomarkers in Pharmacogenomics Trials Li-an Xu & Douglas Robinson Statistical Genetics & Biomarkers Exploratory Development, Global Biometric Sciences Bristol-Myers Squibb 2006 FDA/Industry Statistics Workshop Theme - Statistics in the FDA and Industry: Past, Present, and Future Washington, DC September 27-29, 2006

2 2 Outline Statistical Challenges in Prognostic Model Building Data quantity and quality across multiple platforms Dimension reduction in model building process Model performance measures Realistic assessment of model performance Handling correlated predictors: when p >> n

3 3 Tumor samples for mRNA Trial A Sample Size : 161 Subjects 134 usable (sufficient quality and quantity) mRNA samples (85%) Trial B Sample Size : 110 Subjects 83 usable mRNA samples (75%) Plasma protein profiling (Liquid Chromatography / Mass Spectrometry) Trial B Sample Size : 110 Subjects 90 usable plasma samples (82%) Even if sample collection is mandatory, usable sample size < subject sample size Data Quantity and Quality Across Platforms Need to design studies based on expected usable sample size

4 4 Number of potential predictors is greater than number of subjects (p>>n) in high throughput biomarker studies No unique solutions in prognostic model fitting with traditional methods Regularized methods can provide some possible solutions Penalized logistic regression (PLR) + Recursive Feature Elimination (RFE) Threshold gradient descent + RFE Further dimension reduction may still be needed Incorporate prior information (e.g. results from preclinical studies as the starting point for p) Intersection of single-biomarker results from multiple statistical methods Dimension Reduction in Prognostic Model Building

5 5 Dimension Reduction Through Penalized Logistic Regression with Recursive Feature Elimination to Select Genes Training Set GenesGenes Patients ~22,000 genes 1 gene Choose the model with the smallest cross- validation error and fewest genes Average Cross-validation Error Number of predictors in model

6 6 Sensitive Resistant Example of one gene High Low Expression level Sensitive Resistant Predicting cell line sensitivity to a compound 18 cancer cell lines (12 sensitive, 6 resistant) Identified top 200 genes associated with in vitro sensitivity/resistance Dimension Reduction Through Preclinical Studies 18 Caner Cell Lines Expression

7 7 Predicting Response in Trial A ModelsPPV (95% CI) NPV (95% CI) Sensitivity (95% CI) Specificity (95% CI) Error Starting with full gene list, resulting in 6-gene model 0 (0-0.30) 0.81 (0.69-0.89) 0 (0 -0.26) 0.84 (0.72 -0.91) 0.580 Starting with preclinical top 200, resulting in 10-gene model 0.45 (0.21-0.72) 0.89 (0.79-0.95) 0.45 (0.21-0.72) 0.89 (0.79-0.95) 0.326 All treated patients N=161 Patients included in the genomics analysis N=134 Response29 (18%)23 (17%) Dimension reduction by using prior preclinical results seemed to help in this trial

8 8 Dimension Reduction Through Intersection of Single- Biomarker Results from Multiple Statistical Methods MethodResp1Resp2Resp3Resp4TTP Log RegXXXX t - TestXXXX CoxX Intersection resulted in 51 potential candidates It may be more beneficial to start model building with this set than the complete set of potential predictors (work currently in progress) Cox Proportional Hazards: 446 Probesets 97 46 51 Logistic Regression 297 Probesets t – Test 396 Probesets

9 9 Model Performance Measures Sensitivity, Specificity, Positive and Negative Predictive Value are common measures of model performance Dependent on the threshold Area under the ROC curve (AUC) may be a better measure for comparing models All three models yield complete separation between responders and non-responders Arbitrary threshold of 0.5 probability may lead one to believe that model 2 is superior AUC correctly shows equivalence SensitivitySpecificityPPVNPVAUC Model 10.73110.791 Model 211111 Model 310.770.8111 These figures are from simulated perfect predictors

10 10 Realistic Assessment of Model Performance When sample size is reasonably large Split sample into a training set and independent test Set Build the model on the training set and test the model performance on the test set Pro: One independent test of model performance for the model picked in the training set Cons: When sample size is small, the estimate of performance may have a large variance Reduced sample size for training may yield sub-optimal model Christophe Ambroise & Geoffrey J. McLachlan, PNAS 99(10): 2002 Entire model building procedure s hould be cross-validated

11 11 Realistic Assessment of Model Performance Number of Predictors Cross-validated AUC Cross-validation should be repeated multiple times Allows one to observe effects of sampling variability The average of replicate estimators gives a more accurate assessment of model performance When sample size is small, one cannot split data into training / test set Cross–validation alone is a reasonable alternative Warning: Initial performance estimate may be misleading Individual runs Average AUC

12 12 Handling Correlated Predictors: When p >> n Complex correlation structure (mRNA as example) Multiple probe sets interrogate the same gene Multiple genes function together in pathways Not all pathways are known Multiple response definitions that are interrelated False positive genes may be correlated with true positives Most prognostic modeling techniques do not handle this well Recursive feature elimination may remove important predictors because of correlations This is an open research problem

13 13 Summary Need to design studies based on expected usable sample size Dimension reduction in the model building process Overfitting problem can be mitigated by regularized methods To further reduce the candidate set of predictors Preclinical information can be useful Intersection of single-biomarker results by different statistical methods may also be useful Model performance Independent test set may be important for validation purposes. When sample size is small, cross-validation is a viable alternative. Cross-validation should include biomarker selection procedures and needs to be performed appropriately Cross-validation should be repeated multiple times Performance measures should be carefully chosen when comparing multiple models. AUC often is a good choice. Handling correlated predictors is still an open research problem

14 14 Acknowledgments Can Cai Scott Chasalow Ed Clark Mark Curran Ashok Dongre Matt Farmer Alexander Florczyk Shirin Ford Susan Galbraith Ji Gao Nancy Gustafson Ben Huang Tom Kelleher Christiane Langer Hyerim Lee Haolan Lu David Mauro Shelley Mayfield Oksana Mokliatchouk Relekar Padmavathibai Barry Paul Lynn Ploughman Amy Ronczka Katy Simonsen Eric Strittmatter Dana Wheeler Shujian Wu Shuang Wu Kim Zerba Renping Zhang


Download ppt "Prognostic Model Building with Biomarkers in Pharmacogenomics Trials Li-an Xu & Douglas Robinson Statistical Genetics & Biomarkers Exploratory Development,"

Similar presentations


Ads by Google