Joe Lennerz, Medical Director, Pathology Innovations at Natera, shared a post on LinkedIn:
‘Al in pathology should not be deployed because it is accurate. It should be deployed because it has been validated, is reliable, operates under pathologist oversight, and demonstrably improves patient care. On behalf of the Digital Pathology Association, we are putting forth a ՛Recommendation Statement՛ on the validation, implementation, and clinical application of AI within clinical laboratories.
The paper outlines a practical framework centered on several principles:
- Separate validation of digital pathology infrastructure and AI algorithms
- Demonstration of analytical validity, clinical validity, and reliability (under pressure)
- Pathologist oversight for clinical AI applications
- Assessment of clinical utility (not just technical or clinical performance)
- Transparency regarding intended use, limitations, and generalizability
Note: especially points 4 (clinical utility) and 5 (generalizability) are frequently overlooked.
Importantly, the recommendations emphasize that AI should be evaluated based on its ability to improve diagnostic accuracy, consistency, efficiency, access to expertise, and ultimately patient outcomes. As computational pathology continues to mature, the discussion is shifting from whether ՛AI works՛ to how it can be ՛responsibly implemented, validated, monitored, and reimbursed՛ in real-world clinical practice.”
Douglas Flora, Executive Medical Director of Yung Family Cancer Center at St. Elizabeth Healthcare, President-Elect of the Association of Cancer Care Centers, and Editor-in-Chief of AI in Precision Oncology, shared Joe Lennerz՛s post, adding:
“Congratulations, Joe Lennerz (and team) on your exceptional work adding sage guidance around AI in pathology.
Nikhil Thaker, this manuscript is the perfect example of why we started this journal in the first place. It’s wonderful to see the vision coming to fruition, capped off by our provisional Web of Science indexing!
Hats off to all the authors. This is exactly how we ensure the responsible, real-world adoption of these brilliant tools.”
Title: Recommendation Statement for the Validation, Implementation, and Clinical Application of Artificial Intelligence Within a Clinical Laboratory from the Digital Pathology Association
Authors: Nathan Silberman, Anil Parwani, David McClintock, Giovanni Lujan, Dibson Gondim, Christopher Garcia, Matthew Hanna, Liron Pantanowitz, Jochen Lennerz, Timothy Showalter, Paul Gerrard
Read the Full Article.
Other articles about AI in Oncology on OncoDaily.