Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.04033 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909825510670336 |
|---|---|
| author | Noori, Ayush Rodman, Adam Karthikesalingam, Alan Mateen, Bilal A. Longhurst, Christopher A. Yang, Daniel deBronkart, Dave Galea, Gauden Wolf III, Harold F. Waxman, Jacob Mandel, Joshua C. Rotich, Juliana Mandl, Kenneth D. Mustafa, Maryam Miles, Melissa Shah, Nigam H. Lee, Peter Korom, Robert Mahoney, Scott Hain, Seth Wong, Tien Yin Mundel, Trevor Natarajan, Vivek Dagan, Noa Clifton, David A. Balicer, Ran D. Kohane, Isaac S. Zitnik, Marinka |
| author_facet | Noori, Ayush Rodman, Adam Karthikesalingam, Alan Mateen, Bilal A. Longhurst, Christopher A. Yang, Daniel deBronkart, Dave Galea, Gauden Wolf III, Harold F. Waxman, Jacob Mandel, Joshua C. Rotich, Juliana Mandl, Kenneth D. Mustafa, Maryam Miles, Melissa Shah, Nigam H. Lee, Peter Korom, Robert Mahoney, Scott Hain, Seth Wong, Tien Yin Mundel, Trevor Natarajan, Vivek Dagan, Noa Clifton, David A. Balicer, Ran D. Kohane, Isaac S. Zitnik, Marinka |
| contents | Modern computer systems often rely on syslog, a simple, universal protocol that records every critical event across heterogeneous infrastructure. However, healthcare's rapidly growing clinical AI stack has no equivalent. As hospitals rush to pilot large language models and other AI-based clinical decision support tools, we still lack a standard way to record how, when, by whom, and for whom these AI models are used. Without that transparency and visibility, it is challenging to measure real-world performance and outcomes, detect adverse events, or correct bias or dataset drift. In the spirit of syslog, we introduce MedLog, a protocol for event-level logging of clinical AI. Any time an AI model is invoked to interact with a human, interface with another algorithm, or act independently, a MedLog record is created. This record consists of nine core fields: header, model, user, target, inputs, artifacts, outputs, outcomes, and feedback, providing a structured and consistent record of model activity. To encourage early adoption, especially in low-resource settings, and minimize the data footprint, MedLog supports risk-based sampling, lifecycle-aware retention policies, and write-behind caching; detailed traces for complex, agentic, or multi-stage workflows can also be captured under MedLog. MedLog can catalyze the development of new databases and software to store and analyze MedLog records. Realizing this vision would enable continuous surveillance, auditing, and iterative improvement of medical AI, laying the foundation for a new form of digital epidemiology. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_04033 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A global log for medical AI Noori, Ayush Rodman, Adam Karthikesalingam, Alan Mateen, Bilal A. Longhurst, Christopher A. Yang, Daniel deBronkart, Dave Galea, Gauden Wolf III, Harold F. Waxman, Jacob Mandel, Joshua C. Rotich, Juliana Mandl, Kenneth D. Mustafa, Maryam Miles, Melissa Shah, Nigam H. Lee, Peter Korom, Robert Mahoney, Scott Hain, Seth Wong, Tien Yin Mundel, Trevor Natarajan, Vivek Dagan, Noa Clifton, David A. Balicer, Ran D. Kohane, Isaac S. Zitnik, Marinka Artificial Intelligence Modern computer systems often rely on syslog, a simple, universal protocol that records every critical event across heterogeneous infrastructure. However, healthcare's rapidly growing clinical AI stack has no equivalent. As hospitals rush to pilot large language models and other AI-based clinical decision support tools, we still lack a standard way to record how, when, by whom, and for whom these AI models are used. Without that transparency and visibility, it is challenging to measure real-world performance and outcomes, detect adverse events, or correct bias or dataset drift. In the spirit of syslog, we introduce MedLog, a protocol for event-level logging of clinical AI. Any time an AI model is invoked to interact with a human, interface with another algorithm, or act independently, a MedLog record is created. This record consists of nine core fields: header, model, user, target, inputs, artifacts, outputs, outcomes, and feedback, providing a structured and consistent record of model activity. To encourage early adoption, especially in low-resource settings, and minimize the data footprint, MedLog supports risk-based sampling, lifecycle-aware retention policies, and write-behind caching; detailed traces for complex, agentic, or multi-stage workflows can also be captured under MedLog. MedLog can catalyze the development of new databases and software to store and analyze MedLog records. Realizing this vision would enable continuous surveillance, auditing, and iterative improvement of medical AI, laying the foundation for a new form of digital epidemiology. |
| title | A global log for medical AI |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.04033 |