Draft:Sepsis Watch

Submission declined on 3 June 2026 by Stuartyeates (talk). This draft's references do not show that the subject meets Wikipedia's criteria for inclusion. The draft requires multiple published secondary sources that: provide significant coverage: discuss the subject in detail, not just brief mentions or routine announcements; are reliable: from reputable outlets with editorial oversight; are independent: not connected to the subject, such as interviews, press releases, the subject's own website, or sponsored content. Please add references that meet all three of these criteria. If none exist, the subject is not yet suitable for Wikipedia. If you would like to continue working on the submission, click on the "Edit" tab at the top of the window. If you have not resolved the issues listed above, your draft will be declined again and potentially deleted. If you need extra help, please ask us a question at the AfC Help Desk or get live help from experienced editors. Please do not remove reviewer comments or this notice until the submission is accepted. Where to get help If you need help editing or submitting your draft, please ask us a question at the AfC Help Desk or get live help from experienced editors. These venues are only for help with editing and the submission process, not to get reviews. If you need feedback on your draft, or if the review is taking a lot of time, you can try asking for help on the talk page of a relevant WikiProject. Some WikiProjects are more active than others so a speedy reply is not guaranteed. How to improve a draft Wikipedia:Contributing to Wikipedia – a basic overview on how to edit Wikipedia. Help:Wikitext – how to use the markup Help:Referencing for beginners – how to include references Wikipedia:Article development – how to develop your article Wikipedia:Writing better articles – how to improve your article Wikipedia:Verifiability – make sure your article includes reliable third-party sources You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Add tags to your draft Editor resources Easy tools: Citation bot (help) | Advanced: Fix bare URLs Declined by Stuartyeates 2 months ago. Last edited by Citation bot 26 days ago. Reviewer: Inform author. Resubmit Please note that if the issues are not fixed, the draft will be declined again.

• Comment: The academic sources are stacked with Duke staffers. These are not independent sources. Stuartyeates (talk) 09:21, 3 June 2026 (UTC)

Sepsis Watch is a deep learning clinical decision support system developed at Duke University Health System to provide early warning of sepsis risk in hospitalized patients. It is notable as the first deep learning model to be integrated into routine clinical care in the United States.

Sepsis Watch was developed between 2016 and 2018 by a team at the Duke Institute for Health Innovation (DIHI), led by Mark Sendak, MD, MPP, in collaboration with clinical staff at Duke University Hospital. The system uses real-time electronic health record data to generate risk scores for patients at risk of sepsis up to 36 hours before clinical presentation. Development took approximately two and a half years and involved close collaboration with emergency department physicians and rapid response nurses to design the clinical workflow around the model's output.

The system went live at Duke University Hospital on November 5, 2018, marking the first time a deep learning model had been integrated into routine clinical care in the United States. Within six months of deployment, Duke University Hospital reached the top decile of performance on the Centers for Medicare and Medicaid Services SEP-1 sepsis bundle compliance measure, having doubled its prior compliance rate.^[1]

Following the pilot at Duke University Hospital, Sepsis Watch was subsequently implemented at Duke Regional Hospital and Duke Raleigh Hospital. The DIHI team published a Model Facts label for Sepsis Watch in npj Digital Medicine in March 2020, providing a standardized transparency framework for AI tools in clinical settings, similar in concept to nutrition facts labels for food products.^[2] This work later informed the Office of the National Coordinator for Health Information Technology's HTI-1 Final Rule on algorithm transparency.

A peer-reviewed implementation study was published in JMIR Medical Informatics in 2020 documenting the real-world integration process, workflow design, and clinical outcomes.^[3]

Despite federal funding to accelerate commercialization, Sepsis Watch had been deployed at only two health systems a decade after its initial development. Mark Sendak cited this limited diffusion as a primary motivation for founding Vega Health in 2025, a company focused on distributing and implementing clinically validated AI tools across health systems.^[4]