Sepsis is a major cause of death in hospitals. Could early symptoms be detected using a computer-aided model?
A computer-aided model has shown promise in using routinely collected data to identify early sepsis symptoms.
The new research, titled, Computer-aided National Early Warning Score to predict the risk of sepsis following emergency medical admission to hospital: a model development and external validation study, has been published in CMAJ (Canadian Medical Association Journal).
Early detection is crucial to preventing deaths from sepsis. Every hour of delay is linked with a seven percent reduction in survival, but such delays are common.
Currently there are several scores existing to help to identify patients who have sepsis, included the National Early Warning Score (NEWS), which is used in National Health Service (NHS) hospitals in the United Kingdom.
The computer-aided National Early Warning Score (cNEWS) has been developed to determine whether this could make predicting sepsis more accurate.
The cNEWS score can trigger screening for sepsis, usually within 30 minutes of admission once the routinely collected information has been electronically entered into the medical record.
cNEWS could be carefully introduced to hospitals with appropriate information technology infrastructure, and evaluated.
Using the computer-aided model to detect sepsis symptoms
Professor Mohammed A. Mohammed, University of Bradford, United Kingdom, said: “The main advantage of these computer models is that they are designed to incorporate data that exist in the patient record, can be easily automated and place no extra burden on the hospital staff to collect additional information.”
Professor Mohammed explained: “These risk scores should support, rather than replace, clinical judgment. We hope they will heighten awareness of sepsis with additional information on this serious condition. The main advantage of these computer models is that they are designed to incorporate data that exist in the patient record, can be easily automated and place no extra burden on the hospital staff to collect additional information.”.