What is ABCDS?

Algorithm-Based Clinical Decision Support (ABCDS) Oversight is a “people-process-technology” framework for the governance and evaluation of clinical algorithms created for use at Duke Health. This framework fosters innovative, safe, equitable, and high-quality patient care by introducing checkpoints throughout the development lifecycle as well as after deployment to ensure that transparency, quality, and ownership are maintained for ABCDS algorithms and tools. The ABCDS Oversight is a collaborative effort between the Duke University School of Medicine and the Duke University Health System.

Our Goal

In keeping with our focus on patient safety and high-quality care, our mission is to guide algorithm-based clinical decision support (ABCDS) tools through their lifecycles by providing governance, evaluation, and monitoring.

Have you deployed, or are you working on an algorithm to be deployed at Duke Health?

our team

Michael Pencina

Chair

As vice dean of data science, Dr. Pencina is responsible for developing and implementing quantitative science strategies as they pertain to the education and training, and laboratory, clinical science, and data science missions of the Duke University School of Medicine. He leads the School’s data science strategic direction and investments, working in collaboration with the vice presidents and chief information officers of Duke Health and Duke University’s Office of Information Technology. Dr. Pencina is a professor of Biostatistics and Bioinformatics at Duke University and also served as director of Biostatistics at the Duke Clinical Research Institute (DRCI). He is an internationally recognized expert in risk prediction model development and evaluation.

Eric Poon

Chair

Eric Poon currently serves as the Chief Health Information Officer for Duke Medicine. He also practices primary care internal medicine at the Durham Medical Center as part of Duke Primary Care. In his capacity as CHIO, he is responsible for the visioning and strategic planning of clinical and analytic information systems that impact patient care, research and education. He works with the Duke Medicine leadership to ensure technology solutions are well aligned with Duke’s overall organizational objectives. Dr. Poon oversees the optimization of the Maestro Care (Epic) electronic health record, and partner with physicians, patients and operational leaders to effectively leverage innovative IT in support of the Duke mission.

Portrait photograph of ABCDS Oversight Director Nicoleta J. Economou-Zavlanos, PhD

Nicoleta Economou-Zavlanos

Program Director

Nicoleta J Economou, PhD, serves as the director of ABCDS Oversight leading the operations and framework design effort for the governance, evaluation, and monitoring of ABCDS software at Duke. She is also leading all Duke AI Health initiatives relevant to evaluation and governance of health AI technologies, and leads operations of the Coalition for Health AI, a coalition establishing the guidelines and guardrails for health AI technologies. Previously, Dr. Economou led projects supporting a learning health system at Duke working alongside faculty and health system leadership to bring together people, processes, technologies, and data streams required to drive improvement and innovation in healthcare delivery and operations.

Benefits of a Well-Coordinated
ABCDS Governance Ecosystem

The FDA is stepping into this space. By being proactive in aligning ourselves to FDA’s processes and thinking, we are innovating while accelerating patient care at the institution level.

✓  Improved Accuracy, Impact & Efficiency
✓  Quality by Design Meeting the Intent of Use & the Institution’s Needs
✓  Quality Control & Assurance
✓  Model Ownership & Accountability
✓  Best-Practice Knowledge Sharing
✓  Registration & Collaboration

The ABCDS Software Lifecycle

Inspired by the medical device regulatory approval process and best practices of the software development lifecycle, we divide the ABCDS software lifecycle into 4 stages:

We introduce three gate checkpoints (G0, G1 and G2) between the ABCDS lifecycle stages and intermittent checkpoints (Gm) during general deployment to monitor the ABCDS tool in production.