Timing is Everything: Improving Sepsis Treatment Timing with Machine Learning

What is Sepsis?

Sepsis is a life-threatening condition caused by an overreaction of the immune system to an infection, usually bacterial. The extreme immune response produces a cascade of severe systemic inflammation, often leading to tissue damage, organ failure, and even death. Sepsis, sometimes called septicemia, is estimated to be responsible for nearly 6% of hospitalizations and 35% of in-hospital deaths.

Based on observational studies, the current best-practice guidelines for treating sepsis are to start antibiotic treatment within one hour of diagnosing or even suspecting sepsis or septic shock in a patient. However, mis-timing the administration of antibiotics in a septic patient or administering such a strong course of treatment in a patient with only suspected sepsis can cause more harm than good, including the development of antibiotic resistance or a C. difficile infection. 

New Machine Learning Model Predicts Best Timing for Antibiotic Administration

To replace this one-size-fits-all treatment model, Liu et. al. from Ohio State University developed a computational model to leverage electronic health record (EHR) data to identify the most effective timing for antibiotic administration in septic patients. Their result, published recently in Nature Machine Intelligence, is called Trustworthy Treatment Effects for Time-to-Treatment (T4) antibiotic stewardship in sepsis and evaluates EHR data to predict the effects of treatment in the future.

What makes T4 unique as a computational approach is its integration of time for drug administration. The problem addressed by the researchers is not whether or not to administer antibiotics, but when to administer them, so the model is configurable based on the time variation of the data and thus reducing confounding factors. When validating T4 on two real-world datasets, the authors found that patients that were treated with antibiotics within the T4 recommended time frame had significantly lower mortality than patients that were not.

The development of T4 suggests a new avenue in precision medicine – that of determining the ideal time to administer a medication to a given patient. Sepsis is one of many time-sensitive conditions, where rapid but correct action is essential for patient survival. The role of time in medicine is emerging as a vital but often overlooked component, with recent studies even determining that more robust protective immunity is induced by morning vaccination rather than evening vaccination. The influence of timing will be an interesting addition to the continued development of the precision medicine field.

Outsourcing Bioinformatics Analysis: How Bridge Informatics Can Help

Studies like these are made possible by technological advances rendering biological data generation, storage and analysis faster and more accessible than ever before. From pipeline development and software engineering to deploying existing bioinformatics tools, Bridge Informatics can help you on every step of your research journey.
As experts across data types from leading sequencing platforms, we can help you tackle the challenging computational tasks of storing, analyzing and interpreting genomic and transcriptomic data. Bridge Informatics’ bioinformaticians are trained bench biologists, so they understand the biological questions driving your computational analysis. Click here to schedule a free introductory call with a member of our team.

Jane Cook, Biochemist & Content Writer, Bridge Informatics

Jane Cook, leading Content Writer for Bridge Informatics, has written over 100 articles on the latest topics and trends for the bioinformatics community. Jane’s broad and deep interdisciplinary molecular biology experience spans developing biochemistry assays to genomics. Prior to joining Bridge, Jane held research assistant roles in biochemistry research labs across a variety of therapeutic areas. While obtaining her B.A. in Biochemistry from Trinity College in Dublin, Ireland, Jane also studied journalism at New York University’s Arthur L. Carter Journalism Institute. As a native Texan, she embraces any challenge that comes her way. Jane hails from Dallas but returns to Ireland any and every chance she gets. If you’re interested in reaching out, please email jennifer.martinez@old.bridgeinformatics.com or dan.ryder@old.bridgeinformatics.com.

Recent Posts