Although presepsin, a crucial biomarker for the diagnosis and management of sepsis, has gained prominence in contemporary medical research, its relationship with routine laboratory parameters, including demographic data and hospital blood test data, remains underexplored. This study integrates machine learning with explainable artificial intelligence (XAI) to provide insights into the relationship between presepsin and these parameters. Advanced machine learning classifiers provide a multilateral view of data and play an important role in highlighting the interrelationships between presepsin and other parameters. XAI enhances analysis by ensuring transparency in the model's decisions, especially in selecting key parameters that significantly enhance classification accuracy. Utilizing XAI, this study successfully identified critical parameters that increased the predictive accuracy for sepsis patients, achieving a remarkable ROC AUC of 0.97 and an accuracy of 0.94. This breakthrough is possibly attributed to the comprehensive utilization of XAI in refining parameter selection, thus leading to these significant predictive metrics. The presence of missing data in datasets is another concern; this study addresses it by employing Extreme Gradient Boosting (XGBoost) to manage missing data, effectively mitigating potential biases while preserving both the accuracy and relevance of the results. The perspective of examining data from higher dimensions using machine learning transcends traditional observation and analysis. The findings of this study hold the potential to enhance patient diagnoses and treatment, underscoring the value of merging traditional research methods with advanced analytical tools.

Takho Kang, M.D., Ryoojung Choi, M.T., Dong-Sik Kim, M.D., Ph.D., Duck Cho, M.D., Ph.D., and Dae Won Kim, M.D., Ph.D.. Ann Lab Med -0001;0:. https://doi.org/10.3343/alm.2024.0399

Background: Rigorous evaluation of vacuum blood collection tubes is essential to ensure the reliability of laboratory results. Methods: In this study, we compared the serum separator tube V-Tube™ (V-Tube SST), the quick-clotting serum separator tube VQ-Tube™ (VQ-Tube SST), and the K₂EDTA V-Tube™ (V-Tube K₂EDTA) manufactured by AB Medical (Seoul, Republic of Korea), with their respective counterparts from Becton Dickinson (BD, Franklin Lakes, NJ, USA): BD Vacutainer^® SST™ II Advance Tube (BD SST) and BD Vacutainer^® K₂EDTA 5.4 mg Tube (BD K₂EDTA). The evaluation encompassed 61 measurands across the fields of chemistry, immunology, and hematology, and incorporated a stability assessment for the VQ-Tube SST. Results: The V-Tube SST, VQ-Tube SST, and V-Tube K₂EDTA demonstrated comparable analytical performance to the BD tubes for the majority of measurands. However, glucose, lactate dehydrogenase, mean corpuscular volume, and mean corpuscular hemoglobin concentration indicated clinically significant differences according to the desirable biological variation database (Ricos). Conclusions: These findings suggest that, while the V-tube and VQ-tube SST generally serve as alternatives to BD tubes, caution should be taken when interpreting results for specific measurands that demonstrated clinically significant discrepancies.

Background/Objectives: Longitudinal monitoring after CD19-directed chimeric antigen receptor (CAR) T-cell therapy primarily focuses on CAR-T-cell expansion. However, comprehensive immunophenotypic characterization of both CAR-T and endogenous T cells remains limited. We investigated longitudinal immune dynamics following tisagenlecleucel treatment using multiparameter flow cytometry. Methods: Nineteen patients with relapsed or refractory B-cell malignancies (11 diffuse large B-cell lymphoma and eight B-cell acute lymphoblastic leukemia) receiving tisagenlecleucel were prospectively enrolled. Serial peripheral blood samples collected during the first 28 days after infusion were analyzed for CAR-T-cell kinetics, differentiation status, activation and exhaustion marker expression, longitudinal phenotypic changes, as well as associations with treatment response and immune-related toxicities. Results: CAR-T-cell expansion predominantly peaked on day 7 after infusion. However, in several patients with B-cell acute lymphoblastic leukemia, delayed peak expansion was observed. At peak expansion, CAR-T-cells were enriched for a central memory phenotype and exhibited significantly higher HLA-DR and PD-1 expression than endogenous T cells. During follow-up, the proportion of central memory T-cells progressively declined, whereas the proportion of terminal effector T-cells increased, which was accompanied by reduced expression of HLA-DR, PD-1, and TIGIT. Despite the distinct activation profiles, CAR-T and endogenous T-cells displayed broadly similar differentiation patterns. Exploratory analyses further demonstrated higher absolute CAR-T-cell counts in patients who developed immune effector cell-associated neurotoxicity syndrome. Conclusions: This clinically applicable approach provides immunophenotypic information beyond CAR-T-cell enumeration alone and may facilitate biomarker discovery and longitudinal immune monitoring in patients receiving CAR-T-cell therapy.

Background /Objectives: Longitudinal monitoring after CD19-directed chimeric antigen receptor (CAR)-T-cell therapy primarily focuses on CAR-T cell expansion. However, comprehensive immunophenotypic characterization of both CAR-T and endogenous T-cells remains limited. We investigated longitudinal immune dynamics following tisagen-lecleucel treatment using multiparameter flow cytometry. Methods: Nineteen patients with relapsed or refractory B-cell malignancies (11 diffuse large B-cell lymphoma and 8 B-cell acute lymphoblastic leukemia) receiving tisagenlecleucel were prospectively enrolled. Serial peripheral blood samples collected during the first 28 days after infusion were analyzed for CAR-T-cell kinetics, differentiation status, activation and exhaustion marker expression, longitudinal phenotypic changes, as well as associations with treatment response and immune-related toxicities. Results: CAR-T-cell expansion predominantly peaked on day 7 after infusion. However, in several patients with B-cell acute lymphoblastic leukemia, delayed peak expansion was observed. At peak expansion, CAR-T-cells were enriched for a central memory phenotype and exhibited significantly higher HLA-DR and PD-1 expression than endogenous T-cells. During follow-up, the number of central memory T-cells progressively declined, whereas terminal effector T-cell numbers increased, which was accompanied by reduced expression of HLA-DR, PD-1, and TIGIT. Despite the distinct activation profiles, CAR-T and endogenous T-cells displayed broadly similar differentiation patterns. Exploratory analyses further demonstrated higher absolute CAR-T-cell counts in patients who developed immune effector cell-associated neurotoxicity syndrome. Conclusions: This clinically applicable approach provides immunophenotypic information beyond CAR-T-cell enumeration alone and may facilitate biomarker discovery and longitudinal immune monitoring in patients receiving CAR-T-cell therapy.