IDBS Canadian Translational Medicine Symposium 2012

Mr. Eberhardt has a Bachelors in Economics and History from Duke, having graduated Cum Laude. Mr. Eberhardt has spent his career in performing complex analysis, initially in financial services and for DecisionQ Corporation since 2002. Mr. Eberhardt has led the complex analytical projects and the development of decision support systems in the healthcare, consumer products, financial services, and defense sectors and has spoken previously at conferences on data mining, healthcare, and entrepreneurship, and has published papers on the use of data mining tools for improving patient outcomes in healthcare

Mr. Eberhardt’s research interests include applied machine learning, information theory and data semantics, decision support system and workflow design, and statistics and how these technologies can be applied to real-world decision problems. Mr, Eberhardt’s publications include Assessing Differences Between Physicians’ Realized and Anticipated Gains from Electronic Health Record Adoption, published in the Journal of Medical Systems; Development of a clinical decision model for thyroid nodules, published in the August 2009 edition of BMC Surgery; Application of multivariate probabilistic (Bayesian) networks to screening for Chemical Dependency Cases and Estimating Cost; published in the Fall 2009 AHIMA Perspectives in Health Information Management; Development of a Bayesian Classifier for Breast Cancer Risk Stratification: A Feasibility Study, published in Volume 10 of ePlasty Open Access Journal; Translational research in surgical disease; published in the February 2010 edition of Archives of Surgery; Probabilistic (Bayesian) modeling of gene expression in transplant glomerulopathy, published in the September 2010 edition of the Journal of Molecular Diagnostics; and Clinical decision support systems: potential with pitfalls; published in a special April 2012 edition of the Journal of Surgical Oncology.

Translational research centers have substantial amounts of existing data that represent an untapped opportunity to develop novel clinical interventions. DecisionQ, in collaboration with clinical centers, has applied advanced machine learning methods to these data to develop novel Clinical Decision Support Systems (CDSS). DecisionQ will present one such example, a Colon Cancer CDSS under development in conjunction with Walter Reed National Military Medical Center. DecisionQ will discuss data input, analytical and validation methods, system output, and use.