Association between the changing trends of platelet distribution width and in-hospital mortality in critically ill patients with sepsis: a multicenter study based on machine learning

Comprehensive Summary

Xie et al studied how platelet distribution width correlates with inflammation and indicates sepsis subphenotypes in critically ill patients. The model used trajectory modeling to characterize inpatient admissions in the ICU of Shenzhen People’s Hospital qualifying for 3.0 sepsis criteria and categorized PDW measurements at 6 time-points. PDW was compared between survivors and nonsurvivorts to identify distinct trajectory groups. Results identified four distinct sepsis subphenotypes that varied in inflammatory marker levels and clinical outcomes.

Outcomes and Implications

Xie et al ideate a novel method of predicting mortality risk due to sepsis based on changes in platelet distribution width. Results showed significant physiological differences between trajectory groups with the PDW Rapidly Increasing Group having a mortality three times greater than that of the Low PDW Stable Group. Furthermore, the study identified that the levels of inflammatory markers vary depending on the critical nature of the patient. These findings hold important implications in improving our understanding of sepsis criticality.