Data Numerica Institute, Inc. — Department of Health and Human Services SBIR Phase I: 400

Description

In this researchwe will study two related statistical topics aiming at evaluating longitudinal biomarkers that have impacts on clinical outcome and individualized medical decisionThe results of this study will be applicable to classifying patientsresponse rates based on marker evaluationpredicting disease onsetand selecting treatment protocol that would benefit individual patientsIn treating colon cancerthe patientssurvival rates might be associated with the interaction of surgery and biomarkerse gc myc gene expression levelsIn HIV studiesHIVRNA and CDlevels may result in different outcomes for various treatment groupsSuch biomarkers could be indicators predictors of which patient groups may benefit more from specific treatment optionsMarker evaluation methods and tools are critical in finding the optimal treatment protocol for patientsWe will develop a comprehensive and user friendly environment for analyzing marker dataand the first goal focuses on marker evaluation in treatment selectionTypicallya selection criterion is based on a threshold of a markerAn innovative approach is to evaluate a selection policy by the Selection ImpactSIscore based on the treatment assignment proportion of a given thresholdBy plotting such proportions and the SI score of a given thresholdone can easily find the optimal threshold of biomarker as well as the best marker in marker comparisonOur second goal focuses on the classification capability of markers in selecting diagnostic tests based on marker valuesReceiver Operating CharacteristicsROCcurve is the traditional method in evaluating images in radiological studiesThe challenges are that the level of biomarker may vary over time and the clinical outcome might be a time toevent with censored valuesTypicallythe conventional image diagnostic tests focus on binary outcome with fixed marker values at the baselinee gpositive or negative results in tumor evaluationWe will emphasize more on ROC curve for longitudinal markers and survival outcomeAt the endwe will develop various methods for SI and ROC curves and integrate them into a user friendly statistical softwareWith such toolswe will promote the applications of time varying markers and predictors in personalized treatment decision This project will provide statistical software with advanced methods useful for marker selectionevaluationand personalized treatmentStatistical methodsgraphicscomputational environment and case studies will be developed