The Yuan requests your support! Our content will now be available free of charge for all registered subscribers, consistent with our mission to make AI a human commons accessible to all. We are therefore requesting donations from our readers so we may continue bringing you insightful reportage of this awesome technology that is sweeping the world. Donate now
War of the machines: AI develops sepsis early warning systems
By Gaurav Chandra  |  Aug 30, 2022
War of the machines: AI develops sepsis early warning systems
Image courtesy of and under license from
After the development of antiseptics, antibiotics, and antibacterial drugs, humanity has had to contend with drug-resistant ‘super bacteria.’ This, problem and the ongoing one of sepsis - with its high risk of death if left untreated - remains unsolved, but if AI, Big Data, and ML are properly applied, they may finally achieve victory in this centuries-long fight.


“Gentlemen, it is the microbes who will have the last word” - Louis Pasteur.

In the early 1860s, Louis Pasteur identified microbes as the bane of human existence. Soon after, in 1867, Joseph Lister introduced the concept of antisepsis, and by 1928 Alexander Fleming had discovered penicillin. This already represents an impressive genealogy in humanity’s fight against this invisible army.

However, people’s best efforts at modern medicine have not only brought with it more advanced antimicrobial solutions, but also the super microbial soldiers seen in the multidrug-resistant organisms plaguing the world’s intensive care units (ICUs). Both the problem and the solution have arisen through a lack of policing of effective antimicrobial stewardship programs and a Chernobyl approach whereby people tend to throw the kitchen sink and the vacuum cleaner at any potential whiff of infection.

To be more effective with one’s armamentarium, one needs to focus on building more efficient sepsis early warning systems (SEWS) for advance alert that the enemy is at the door. The critical determinant of survival is time - a priceless commodity. A patient can go from potentially septic to full septic shock in just a matter of hours, and yet because of the non-specific nature of its diagnostic features, it takes a significant amount of time to assimilate and analyze information while preventing the inappropriate use of empiric antimicrobial therapy. Artificial intelligence (AI) is key to timely diagnosis and the discovery of new and important biomarkers.

The scope of the problem

The development of sepsis has multifactorial pathogenesis driven by a dysregulated host inflammatory response whose endpoint is a multi-organ failure (MOF). It kills 18 million people annual

The content herein is subject to copyright by The Yuan. All rights reserved. The content of the services is owned or licensed to The Yuan. Such content from The Yuan may be shared and reprinted but must clearly identify The Yuan as its original source. Content from a third-party copyright holder identified in the copyright notice contained in such third party’s content appearing in The Yuan must likewise be clearly labeled as such.
Continue reading
Sign up now to read this story for free.
- or -
Continue with Linkedin Continue with Google
Share your thoughts.
The Yuan wants to hear your voice. We welcome your on-topic commentary, critique, and expertise. All comments are moderated for civility.
Dr. Gaurav, thanks for sharing your insights with The Yuan's readers. You are correct that good AI will help to win the centuries-long war. But sometimes, we have to face harmful and biased AI products; they would twist the truth and interfere with the results of experiments. Probably, you could deliver your ideas on how to conquer bad AI and its influences on medical fields.