A recent study conducted by researchers at the University of California San Diego School of Medicine has revealed that an artificial intelligence (AI) surveillance tool has been successful in predicting sepsis and thereby saving lives. Sepsis is a serious blood infection that can lead to a life-threatening chain reaction throughout the body, causing approximately 350,000 deaths each year in the United States alone.
The study, published in npj Digital Medicine, utilized an AI algorithm called COMPOSER to quickly identify patients at risk for sepsis in the emergency departments at UC San Diego Health. The algorithm, previously developed by the research team, contributed to a 17% reduction in mortality.
Dr. Gabriel Wardi, Chief of the Division of Critical Care in the Department of Emergency Medicine at UC San Diego School of Medicine and co-author of the study, explained that the COMPOSER model uses real-time data to predict sepsis before noticeable symptoms occur. The algorithm continuously monitors over 150 different patient variables, including lab results, vital signs, medications, demographics, and medical history. If a patient presents with multiple variables indicating a high risk for sepsis, the algorithm notifies the nursing staff through the hospital’s electronic health record. The nursing team then reviews the information with the physician to determine the most appropriate treatment plan.
Co-author Dr. Shamim Nemati, Director of Predictive Analytics at UC San Diego School of Medicine, highlighted the AI algorithm’s ability to detect patterns that may not be apparent to the human eye. By analyzing various risk factors, the system can accurately predict sepsis. Conversely, if the risk patterns can be attributed to other conditions with greater certainty, the algorithm will not send alerts.
The study analyzed more than 6,000 patient admissions before and after the implementation of COMPOSER in the emergency departments of UC San Diego Medical Center and Jacobs Medical Center. The results indicate that the AI deep-learning model, which utilizes artificial neural networks to identify health concerns, improved patient outcomes. The model can identify complex and multiple risk factors, which are then reviewed by the healthcare team to confirm the presence of sepsis.
Dr. Wardi, an emergency medicine and critical care physician at UC San Diego Health, emphasized that the AI model enables faster life-saving therapy for patients. By promptly identifying those at risk of sepsis, medical professionals can provide the necessary treatment and reduce mortality rates.
This study is a significant advancement in the field of AI-assisted healthcare. By harnessing the power of machine learning and predictive analytics, medical professionals can improve patient outcomes and save more lives. The success of the COMPOSER algorithm in identifying sepsis risk factors demonstrates the potential of AI in revolutionizing critical care and emergency medicine. As further research and development continue, AI surveillance tools like COMPOSER could become invaluable assets in hospitals worldwide, helping to prevent and treat life-threatening conditions with greater efficiency and accuracy.
