Center for Medical Ethics and Health Policy

Multi-Site Trial to Test Benefits of Adding a Personalized Risk Calculator to an Online Decision Aid for Left Ventricular Assist Device


Project Desription


The development and efficacy-testing of a holistic, personalized, electronically integrated clinical decision support system for left-ventricular assist device (LVAD) candidates will help to ensure that heart failure (HF) patients receive tailored treatments that lead to optimal and values-based outcomes. Our study involves utilization of an AI/machine learning system that predicts personalized risks using big data. Specifically, it applies the most advanced personalized risk prediction technologies and decision support available to make sure that evidence about cardiac outcomes is used by both patients and clinicians in the service of shared decision making that leads to more informed and value-concordant health decisions. The impact of this personalized approach to clinical decision making addresses the urgent need to better identify and respond to the specific and dynamic nature of patient needs in seeking treatment for advanced HF.

We will do this by updating and integrating a validated online risk prediction and communication tool, the Cardiac Outcomes Risk Assessment (CORA) developed by our colleagues at Cornell University, with our efficacy-tested decision aid (Deciding Together) for LVAD.

This five-year project builds on 6 years of research on the development, implementation and dissemination of LVAD decision support and a decade of research into accurate risk prediction models for LVAD.

Supported by: R01 HS027784, Agency for Healthcare Research and Quality


Project Personnel


Principal Investigator





Kostick, K.M., & Blumenthal-Barby, J.S. (2021). Avoiding “Toxic Knowledge”: The importance of framing personalized risk information in clinical decision-making. Personalized medicine, 18(2), 91–95. 

Kostick, K.M., Cohen, G., Gerke, S., Lo, B., Antaki, J., Movahedi, F., Njah, H., Schoen, L., Estep, J. & Blumenthal-Barby, J.S. (2022). Mitigating Racial Bias in Machine Learning. Special issue of the Journal of Law, Medicine & Ethics, 50(1), 92-100. doi:10.1017/jme.2022.13. 

Blumenthal-Barby, J., Lang, B., Dorfman, N., Kaplan, H., Hooper, W. B., & Kostick-Quenet, K. Research on the Clinical Translation of Health Care Machine Learning: Ethicists’ Experiences on Lessons Learned. American Journal of Bioethics, 22(5), 1–3. 

Accepted for Publication: 

K. M. Kostick-Quenet, Benjamin Lang, Natalie Dorfman, J.S. Blumenthal-Barby. A Call to Embed Behavioral Science into Embedded Bioethics. Accepted for publication by Perspectives in Biology and Medicine.