Continuously Learning Systems (CLS) Working Team

Be a part of the conversation; join our LinkedIn AI group today!

Be a part of the conversation; join our LinkedIn AI group today!

Goal

To increase the assurance of our product quality by becoming a predictive organization through the power of AI to provide more robust information to make more informed decisions than we can today. 

 

Team Leadership

Full list of working team members are listed at the bottom of page.

Co-Leaders

  • Berkman Sahiner, Senior Biomedical Research Scientist, FDA
  • Mohammed Wahab, Senior Manager, Informatics and Analytics, Abbott

Team Administrator

  • Mac McKeen, Fellow, Regulatory Science, Boston Scientific

Mentor from AI Core Team

  • Walt Mullikin, Head of Enterprise Analytics, Shire

AI Expert from AI Core Team

  • Kumar Madurai, Principal Consultant, CTG

 

Problem Statement to Address

Continuously learning systems bear the risks of unanticipated outcomes due to a lack of human involvement in the changes, unintended (and undetected) degradation in time, confusion for users, and incompatibility of results with other software that may use the output of the evolving algorithm.

 

Scope

  • There is already an existing body of literature concerning the validation of locked algorithms in medicine. The current thinking is therefore to limit the scope of the working team to continuously learning algorithms, although the experience from locked algorithms will be helpful.
  • The working team should leverage the experience gained in other industry sectors as much as possible. However, considering the focus of the summit attendees, the emphasis should be on medical applications. The group should discuss whether any medical application is within the scope, or whether to focus on only algorithms within the purview of the FDA.
  • The technical needs for validation both before the algorithm is deployed as well as after the algorithm starts evolving in the field should be considered.

 

Problem Solving Process

  1.  Identify the current landscape of continuously-learning algorithms as it relates to this work group.
  2. Develop a hierarchy of continuously learning algorithms, from the simplest (closest to the locked algorithms) to the most advanced.
  3. Start with what we think we know: Scientific needs for validation of locked algorithms.
  4. Identify important components of continuously-learning algorithms and potential ways to evaluate them.
  5. Role Reversal Experiment:  think of yourself as a customer of a continuously-learning algorithm.

 

Obstacles

  1.  Validation needs may be different depending on various factors, such as the risk of the algorithm, where it is deployed, whether the algorithm is considered a medical device or not, etc. Need a good framework to address multiple factors. Alternatively, narrow the focus.
  2. This is a very quickly changing field. Need to think comprehensively about the field so that the output does not become quickly obsolete.
  3. May need some time at the beginning to get all team members on the same page, speaking the same language (terminology issues).
  4.  Limited hands-on experience with continuously learning algorithms may be an impediment to our reasoning process in figuring out what the evaluation needs are. There is a need to be resourceful and use analogies to other industry sectors, while keeping in mind that risks in the medical field are sometimes unique.

 

Expected Deliverables

  1. Detailed examples of continuously-learning algorithms currently used in medicine
  2. A list of continuously-learning algorithm applications in medicine that we might likely encounter in the near future
  3. Preparation and conduct of a survey on the current landscape of continuously-learning algorithms in medicine
  4. Identification at a high level as to what scientific and technical information is important to know about a continuously-learning algorithm to have confidence in its safety and effectiveness:

a. Before the algorithm is deployed

b. After the algorithm starts to evolve while it is in use

 

CLS Working Team Members

  • Pat Baird, Head of Global Software Standards, Philips
  • Robert Banta, Quality Consultant, Eli Lilly and Company
  • Rick Chapman, Sanofi
  • John Daley, Vice President, IBM
  • Lacey Harbour, Ken Block Consulting
  • Lan Herrington, Director, Regulatory Affairs, Sotera Wireless, Inc.
  • Robert Kruth, Manager, IT Regulatory Compliance, Johnson & Johnson
  • Cindi Linville, Director of Quality, Best Sanitizers
  • Deepa Mahajan, Scientist, BSC
  • Dave Moore, Director, IT Regulatory Compliance, Johnson & Johnson
  • Rohit Nayak, Principal, Start Up
  • Gregory Pierce, CEO, EngiLifeSciences
  • Zach Rothstein, AVP, AdvaMed
  • Scott Thiel, Director, Navigant
  • Gregor Woodard, Biomedical Engineer, Ken Block Consulting
  • Eileen Alexander, Asst. Professor, Xavier University
  • Tom Doyle, Director, Data Science, Janssen Research & Development, LLC.
  • Cynthia Ipach, President, Compliance Insight
  • Stuart Merdian, AD - Corporate, QAP&G
  • Juan Perez, Principal Consultant, Infosys
  • Eda Ross Montgomery, Head of Commercial Prod and Technical Knowledge, Shire Pharmaceutical
  • Krista Woodley, Sr Director Quality Healthcare Texhnology, Johnson and Johnson
  • Gerald Zemble, Sr. Quality Specialist III, Purdue Pharma L.P.
  • Hui Zhao, Associate Professor of Supply Chain Management, Penn State
  • Paul Kostoff, Co-Founder, Cincy-Data
  • Andrew Langsner, Co-Founder, Cincy-Data
  • Bruce Friedman, GE Healthcare
  • Gary Ritchie, GER Compliance