Background
Sepsis poses a global threat to millions of lives. The Surviving Sepsis Campaign (SSC) guidelines provide evidence-based recommendations on the recognition and management of sepsis and its complications.
Methods
We formed a panel of 60 experts from 22 countries and 11 members of the public. The panel prioritized questions that are relevant to the recognition and management of sepsis and septic shock in adults. New questions and sections were addressed, relative to the previous guidelines. These questions were grouped under 6 subgroups (screening and early treatment, infection, hemodynamics, ventilation, additional therapies, and long-term outcomes and goals of care). With input from the panel and methodologists, professional medical librarians performed the search strategy tailored to either specific questions or a group of relevant questions. A dedicated systematic review team performed screening and data abstraction when indicated. For each question, the methodologists, with input from panel members, summarized the evidence assessed and graded the quality of evidence using the Grading of Recommendations, Assessment, Development and Evaluation (GRADE) approach. The panel generated recommendations using the evidence-to-decision framework. Recommendations were either strong or weak, or in the form of best practice statements. When evidence was insufficient to support a recommendation, the panel was surveyed to generate “in our practice” statements.
Results
The SSC panel issued 93 statements: 15 best practice statements, 15 strong recommendations, and 54 weak recommendations and no recommendation was provided for 9 questions. The recommendations address several important clinical areas related to screening tools, acute resuscitation strategies, management of fluids and vasoactive agents, antimicrobials and diagnostic tests and the use of additional therapies, ventilation management, goals of care, and post sepsis care.
Conclusion
The SSC panel issued evidence-based recommendations to help support key stakeholders caring for adults with sepsis or septic shock and their families.

/pdf/surviving-sepsis-campaign-international-guidelines-for-1trp1tl9am.pdf

Surviving sepsis campaign: international guidelines for management of sepsis and septic shock 2021.

Surviving Sepsis Campaign: International Guidelines for Management of Sepsis and Septic Shock 2021.

Acute critical illness is often preceded by deterioration of routinely measured clinical parameters, e.g., blood pressure and heart rate. Early clinical prediction is typically based on manually calculated screening metrics that simply weigh these parameters, such as early warning scores (EWS). The predictive performance of EWSs yields a tradeoff between sensitivity and specificity that can lead to negative outcomes for the patient. Previous work on electronic health records (EHR) trained artificial intelligence (AI) systems offers promising results with high levels of predictive performance in relation to the early, real-time prediction of acute critical illness. However, without insight into the complex decisions by such system, clinical translation is hindered. Here, we present an explainable AI early warning score (xAI-EWS) system for early detection of acute critical illness. xAI-EWS potentiates clinical translation by accompanying a prediction with information on the EHR data explaining it. Acute critical illness is often preceded by deterioration of routinely measured clinical parameters, e.g., blood pressure and heart rate. Here, the authors develop an explainable artificial intelligence early warning score system for its early detection.

/pdf/explainable-artificial-intelligence-model-to-predict-acute-22j2tn39yu.pdf

Explainable artificial intelligence model to predict acute critical illness from electronic health records.

We developed an explainable artificial intelligence (AI) early warning score (xAI-EWS) system for early detection of acute critical illness. While maintaining a high predictive performance, our system explains to the clinician on which relevant electronic health records (EHRs) data the prediction is grounded. Acute critical illness is often preceded by deterioration of routinely measured clinical parameters, e.g., blood pressure and heart rate. Early clinical prediction is typically based on manually calculated screening metrics that simply weigh these parameters, such as Early Warning Scores (EWS). The predictive performance of EWSs yields a tradeoff between sensitivity and specificity that can lead to negative outcomes for the patient. Previous work on EHR-trained AI systems offers promising results with high levels of predictive performance in relation to the early, real-time prediction of acute critical illness. However, without insight into the complex decisions by such system, clinical translation is hindered. In this letter, we present our xAI-EWS system, which potentiates clinical translation by accompanying a prediction with information on the EHR data explaining it.

Tahmina Nasrin

Papers

Prediction of sepsis patients using machine learning approach: A meta-analysis.