Researchers at King’s College London have mapped how the human immune system changes over time during sepsis, identifying three distinct immune states that could help pave the way for treatments that target the specific parts of the immune system that are altered over the time course of the illness. According to a study published in the journal Immunity, machine learning models analyzed multiple layers of blood sample data from critically ill patients, revealing biological trajectories that do not align with traditional clinical stages of the condition.
How Machine Learning Mapped Sepsis Immune States
Sepsis remains a life-threatening medical emergency triggered by a misfiring immune response to infection, resulting in vital organ failure and millions of deaths worldwide each year. To capture the biological reality of this condition, investigators led by Dr. Matthew Fish analyzed blood samples collected at four distinct timepoints between critical care admission and discharge at Guy’s and St Thomas’ NHS Foundation Trust, according to King’s College London.
Using machine learning approaches, the research team combined multiple layers of biological data from the samples. This comprehensive profiling included tracking changing immune cells, gene expression, and protein expression. The resulting analysis mapped an immune trajectory consisting of three distinct temporal immune states, designated as STImS, with each state defined by unique immune cell activity and response programs.
Divergence Between Immune States and Clinical Stages
A critical finding of the study is that these newly identified sepsis immune states do not match standard clinical timelines. For instance, data showed that the earliest biological immune state, designated as STImS1, does not necessarily align with the early clinical stage of sepsis typically marked by a physician’s initial diagnosis.
Historically, clinical treatments for sepsis have focused on administering antimicrobials to clear the underlying infection alongside supportive care for failing organs. While past efforts have attempted to treat a misfiring immune system, none have successfully improved outcomes for patients. The study authors note that these discoveries may offer vital insights when determining optimal sepsis care strategies—specifically regarding which interventions to use and the ideal timing for administration.
Next Steps for Targeted Sepsis Treatments
The work was conducted by Dr. Matthew Fish during his PhD at King’s College London within the laboratory of Professor Manu Shankar-Hari, with support from a National Institute of Academic Anesthesia BJA/RCoA fellowship. Dr. Fish currently serves as a postdoctoral researcher at Massachusetts General Hospital, continuing his investigation into sepsis and the immune system.
The research collaboration also included Dr. Chad Swanson, Reader in the School of Immunology & Microbial Sciences at King’s College London, and Professor Mervyn Singer, Professor of Intensive Care Medicine at University College London. According to the study authors, the next phase of research will investigate what causes changes in the immune system between onset of infection to the development of sepsis. Gaining insight into these alterations could assist in pinpointing novel therapeutic targets and strategies aimed at slowing the progression of sepsis or lessening its severity.
Keep reading