Related Experiment Video
Updated: Jan 13, 2026
Monitoring Neuronal Survival via Longitudinal Fluorescence Microscopy
Published on: January 19, 2019
Exploratory characterization of dynamic soluble programmed death-ligand 1 trajectories and their association with
Shungo Takeuchi1, Eiji Kawamoto2,3, Takashi Matsusaki2
1Department of Anesthesiology, Mie University Graduate School of Medicine, Mie University, Tsu, Japan. stakeuchi@med.mie-u.ac.jp.
Insights
Persistent high soluble programmed death-ligand 1 (sPD-L1) levels in critical COVID-19 patients during the first ICU week predict mortality and organ dysfunction. Machine learning models incorporating sPD-L1 significantly improve risk prediction for better patient outcomes.
Area of Science:
- Immunology
- Critical Care Medicine
- Biomarker Discovery
Background:
- Critical COVID-19 is characterized by persistent immune checkpoint activation.
- The clinical significance and temporal dynamics of soluble programmed death-ligand 1 (sPD-L1) in severe COVID-19 remain underexplored.
Purpose of the Study:
- To investigate longitudinal changes in sPD-L1 levels in severe COVID-19 patients.
- To assess the relationship between sPD-L1 and organ dysfunction markers.
- To evaluate the prognostic value of sPD-L1, alone and with machine learning (ML), for predicting mortality.
Main Methods:
- Single-center observational study of 40 severe COVID-19 ICU patients and 23 healthy controls.
- Plasma sPD-L1 measured longitudinally (ICU days 1, 5, 7, 14, 21).
- Cox regression and eight ML classifiers used for mortality prediction, with SHAP for feature importance.
Main Results:
- sPD-L1 levels decreased over time but remained high in non-survivors.
- ICU day 5 and 7 sPD-L1 levels significantly differed between survivors and non-survivors.
- ICU day 7 sPD-L1 and admission lactate independently predicted mortality; ML models, particularly SVM, showed high accuracy (AUC=0.917), with day 5 sPD-L1 as a key predictor.
Conclusions:
- Sustained sPD-L1 elevation in the first ICU week indicates organ dysfunction and predicts death in critical COVID-19.
- Integrating serial sPD-L1 measurements into ML models enhances prognostic discrimination.
- sPD-L1 may serve as an integrative biomarker for immune-renal-coagulation interactions, requiring further validation.
Background:
Persistent immune checkpoint activation is a recognized feature of critical coronavirus disease 2019 (COVID-19). However, the temporal behavior and clinical utility of soluble programmed death-ligand 1 (sPD-L1) remain unclear. We investigated the longitudinal changes in sPD-L1, its relationship with organ dysfunction markers, and their prognostic value when combined with machine learning (ML) models.
Methods:
In this single-center observational study, we included 40 adults with severe COVID-19 pneumonia admitted to the intensive care unit (ICU) (April 2021-December 2022), and 23 healthy volunteers as controls. We measured plasma sPD-L1 on ICU day 1, 5, 7, 14, and 21. Routine biochemistry, complete blood counts, and arterial blood gas analyses were conducted in parallel. Cox regression was used to identify independent predictors of hospital mortality, the primary outcome. Eight ML classifiers were trained using admission variables and sPD-L1 levels from ICU day 1, 5, and 7. Discrimination was assessed using stratified fivefold cross-validation, and feature importance was evaluated using Shapley Additive Explanations (SHAP).
Results:
Of 40 patients, 10 died during hospitalization. Overall, sPD-L1 levels declined during the ICU stay but remained persistently high in non-survivors. ICU day 5 and 7 values differed significantly between survivors and non-survivors (p = 0.023 and 0.001, respectively). In multivariable Cox analysis, ICU day 7 sPD-L1 levels and arterial lactate levels on admission independently predicted mortality. ICU day 7 sPD-L1 levels correlated positively with creatinine, C-reactive protein, and fibrinogen levels (all p < 0.05) in cross-sectional correlation analyses. Among ML models, the support vector machine achieved the highest discriminative accuracy (mean area under the curve = 0.917). ICU day 5 sPD-L1 was designated as the primary predictor of mortality based on SHAP analysis, with lactate contributing minimally.
Conclusion:
Sustained sPD-L1 elevation during the first ICU week is strongly associated with early organ dysfunction and independently predicts death in critical COVID-19. Incorporating serial sPD-L1 measurements into bedside ML models significantly enhances risk discrimination. These findings support sPD-L1 as an integrative biomarker of the immune-renal-coagulation interplay, warranting validation in larger multicenter cohorts and exploration as a potential companion marker for immune-modulatory interventions.
