Transcript Slide 1
Dose-response Explorer: An Open-source-code Matlab-based tool for modeling treatment outcome as a function of predictive factors Gita Suneja Issam El Naqa, Patricia Lindsay, Andrew Hope, James Alaly, Jeffrey Bradley, Joseph O. Deasy Supported by NIH grant R01 CA 85181 What is DREX? An open-source-code Matlab-based tool for: 1) Modeling tumor control probability (TCP) and normal tissue complication probability (NTCP) 2) Evaluating robustness of models 3) Graphing the results for purposes of outcomes analysis for practitioners, training for residents, and hypothesis-testing for further research Motivation & Objectives • Motivation – Cornerstone of treatment planning is the need to balance tumor control probability (TCP) with normal tissue complication probability (NTCP) • Objective – Physicians and scientists need a tool that is straightforward and flexible in the study of treatment parameters and clinical factors Features 1. 2. 3. 4. 5. 6. Analytical modeling of normal tissue complication probability (NTCP) and tumor control probability (TCP) Combination of multiple dose-volume variables and clinical variables using multi-term logistic regression modeling Manual selection or automated estimation of model parameters Estimation of uncertainty in model parameters Performance assessment of univariate and multivariate analysis Capacity to graphically visualize NTCP or TCP prediction vs. selected model variable(s) Basic Modules Data Input 1 2 Analytical Poisson or Linear quadratic TCP Model type? 4 Radiobiologic al model? 3 Multi-metric Logistic regression Univariate/multivariate performance assessment Graphical representation 5 Export output NTCP Model type? Analytical Lyman-KutcherBurman (LKB) or Critical volume Modeling Method I: Analytical • NTCP – Lyman-Kutcher-Burman (LKB) Model (Lyman 1985, Kutcher and Burman 1989) NTCP ( EUD D50 ) mD50 – Critical Volume Model (Niemierko and Goitein 1993) NTCP ( • TCP ln( ln d ) ln( ln cr ) ) – Poisson Statistics – Linear-quadratic (LQ) Prediction TCP=exp(-Nexp(-(( + *d)*D+ln2*t/Tpot )) Modeling Method II: Multimetric • • Logistic regression – additive sigmoid model e g ( xi ) Y ( xi ) , i 1,..., n g ( xi ) 1 e Two types of data exploration 1. Manual 2. Automated - - Determining Model Order by Leave-one-out-CrossValidation (Ref.: “Multi-Variable Modeling of Radiotherapy Outcomes: Determining Optimal Model Size,” Deasy et al., poster SU-FF-T-376 ) Model parameters estimated by forward selection on multiple bootstrap samples Performance Assessment • Spearman’s Rank Correlation • Area under the Receiver Operating Characteristic (ROC) curve • Survival analysis using the Kaplan-Meier estimator Univariate Graphical Representations Graph/Plot Description/Function Selfcorrelation Color-washed Spearman’s cross-correlation image of selected variables and observed outcome Scatter •User selects abscissa and ordinate variables •Provides user with visual cues about the discrimination ability of certain factors Survival curves Use Kaplan-Meier estimates Multivariate Graphical Representations Graph/Plot Description/Function Histogram Cumulative plot of observed response (bar graph) and model-predicted response (line graph) Contour Demonstrates the effect of the model variables on shaping the predicted outcome Octile •Patients are uniformly binned into 8 groups •Helps visualized goodness of fit of model ROC Assess prediction power of model Conclusions • User-friendly software tool to analyze dose response effects of radiation • Incorporates treatment and clinical factors, as well as biophysical models • Various graphical representations • Available in the near future on the web at radium.wustl.edu/DREX