AI and Blood Test Revolutionize Sepsis Diagnosis

Combining artificial intelligence with a simple blood test could revolutionize the diagnosis and treatment of sepsis, a life-threatening infection that kills millions of people worldwide each year. Swedish researchers at Lund University have developed a groundbreaking approach that combines the unique molecular signature of sepsis with machine learning to predict a patient’s risk of organ failure and death. By analyzing proteins associated with the body’s immune response to sepsis, the researchers were able to create molecular signatures that were then used to train an AI model. This AI model can predict who is likely to go into septic shock, classify patients into risk categories, and identify dysfunction in different organs.

Sepsis is a challenging condition to diagnose, often leading to delays in treatment and poor outcomes. Dr. Lisa Mellhammar, one of the researchers involved in the study, explains the significance of this new approach: “Given the challenges associated with timely diagnosis and the fact that sepsis kills millions of people around the world every year, there is an urgent demand for an alternative approach.” With an accurate and fast blood test combined with a personalized risk model, physicians can identify patients with suspected sepsis before organ failure occurs, potentially saving lives and improving clinical outcomes.

The study involved analyzing 1,364 plasma samples from adults admitted to the emergency department with suspected sepsis. Out of the 1,073 patients with an infection, 913 were confirmed to have sepsis. The researchers then trained the AI model to predict which patients were at high risk of developing septic shock. The technology classified patients into low, medium, and high-risk categories, with higher-risk patients having a higher rate of death. Additionally, the researchers identified panels of proteins that predicted dysfunction in different organs, including the heart, liver, and kidneys. This breakthrough could lead to improved understanding and classification of sepsis, ultimately guiding the development of more effective treatments.

While the findings of the study are promising, it is important to note that further clinical validation and regulatory approvals are needed before this approach can be implemented in healthcare settings. Dr. Ron Daniels, founder and joint chief executive of the UK Sepsis Trust, emphasizes the potential impact of this research: “This research has huge potential to refine our understanding of sepsis and may, in time, help us to redesign clinical systems.” The study’s results will be presented at the European Congress of Clinical Microbiology and Infectious Diseases in Barcelona at the end of April.

In parallel with these groundbreaking developments, NHS England is preparing to introduce the first phase of Martha’s Rule from next month. Named after Martha Mills, a 13-year-old who tragically died from sepsis in 2021, Martha’s Rule formalizes access to a critical care team for a second opinion when a patient’s condition is rapidly worsening. This process aims to ensure that patients receive the necessary care promptly, potentially addressing delays in sepsis diagnosis and treatment.

The future of early detection and personalized treatment for sepsis looks promising. As Dr. Lisa Mellhammar envisions, “A fast test that provides more accurate sepsis diagnosis and could also predict who is at greater risk of poorer outcomes now seems a genuine possibility.” With continued research, validation, and refinement of these innovative approaches, we may see a significant reduction in sepsis-related deaths and an improvement in patient outcomes worldwide.