Platelet count trajectory patterns and prognosis in critically ill patients with thrombocytopenia: Based on latent growth mixture model analysis

Abstract

Background

The role of longitudinal platelet count trajectories in critically ill patients with thrombocytopenia is unclear. This study aimed to identify the association between trajectory patterns and prognosis and assess whether these patterns could enhance the predictive capability of Acute Physiology and Chronic Health Evaluation (APACHE) IV or Sequential Organ Failure Assessment (SOFA) scores for mortality.

Methods

This retrospective cohort study employed latent growth mixture modeling (LGMM) to identify platelet count trajectory patterns. Cox proportional hazards model was used to evaluate the association between the patterns and mortality. Receiver Operating Characteristic (ROC) curves were plotted, and the areas under the curves (AUCs) were compared between models using the APACHE IV or SOFA score alone and those incorporating trajectory patterns.

Results

A total of 1683 patients from the eICU Collaborative Research Database (eICU-CRD) and 931 patients from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database were included. Two trajectory patterns were identified: Class 1, characterized by “Gradual increase,” and Class 2, with “Persistent low.” Patients in Class 2 had higher ICU mortality (eICU-CRD: 2.273[1.457–3.546]; MIMIC-IV database: 1.991[1.162–3.412]). Incorporating trajectory patterns into the APACHE IV or SOFA scores substantially enhanced the AUC of these scoring systems alone in predicting ICU mortality (eICU-CRD: P < 0.001; MIMIC-IV database: P = 0.0018).

Conclusion

The longitudinal platelet count trajectory patterns are complementary predictors of survival in critically ill patients with thrombocytopenia. Persistently low platelet counts are significantly associated with unfavorable clinical outcomes.