Background: Neutrophil gelatinase‐associated lipocalin (NGAL) is a urine biomarker related to acute renal injury. Whereas several studies have evaluated NGAL levels in hematological malignancy, using peripheral blood (PB). Recently, bone marrow (BM) NGAL level was reported to be higher than PB NGAL level in individuals with hematological malignancy, suggesting that BM NGAL would reflect BM microenvironment better than PB NGAL. We measured BM NGAL levels in patients with hematological malignancy, comparing those with NGAL levels in normal BM. We evaluated the association of BM NGAL with hematological parameters including neutrophil counts.Methods: BM samples were collected from 107 patients who underwent BM examination. Immunoassays were used to assess NGAL levels. Data on hematological parameters were collected from medical records. Intergroup comparisons were performed using the Kruskal‐Wallis H test and Pearson chi‐square test. Single and multiple regression analyses were performed to analyze the relationships.Results: The independent factors that affected the BM NGAL level were neutrophil counts and BM band neutrophil%, while neutrophil count was the main influencing factor. The acute myeloid leukemia (n = 18) and myelodysplastic syndrome (n = 25) groups showed statistically lower BM NGAL levels than patients with normal BM. The myeloproliferative neoplasm group (n = 34) showed higher BM NGAL levels than patients with normal BM, but this difference was not statistically significant. Neutrophil counts and BM band neutrophil% showed intergroup patterns similar to those of BM NGAL levels.Conclusion: BM NGAL was related to neutrophil count and BM band neutrophil%, showing different levels according to hematological malignant disease entities.

Jung BK, et al. J Korean Med Sci. 2017 Apr;32(4):695-699. https://doi.org/10.3346/jkms.2017.32.4.695

Background: Although neutrophil gelatinase‐associated lipocalin (NGAL) is a biomarker for acute kidney injury, recently, high NGAL levels have been reported in hematologic malignancies. Given the mechanism underlying NGAL synthesis and secretion in neutrophilic series, it is speculated that NGAL levels are higher in bone marrow (BM) than in peripheral blood (PB). Additionally, PB NGAL levels are thought to be associated with neutrophilic parameters. We aimed to test both hypotheses in hematologic malignancies.Methods: Paired BM and PB samples were collected from 41 patients undergoing BM examination for hematologic malignancies. NGAL levels were measured using immunoassays. Data on hematologic parameters were collected from medical records. Single and multiple regression analyses were performed to analyze the relationship.Results: PB and BM NGAL (n = 41) levels were significantly different (163.0 ± 258.3 and 413.1 ± 616.2 ng/mL [mean ± standard deviation], respectively; P < 0.05). Simple regression analysis and multicollinearity assessment showed that BM NGAL levels, BM neutrophil%, and neutrophil count were significant predictors of PB NGAL. Two multiple regression models were developed (model 1, PB NGAL = 21.467* neutrophil count ‐ 0.785*BM neutrophil%; model 2, PB NGAL = 21.202*neutrophil count‐ 0.915*BM neutrophil% +0.10*BM NGAL). Akaike's information criterion and adjusted R² values showed that model 1 had higher predictive accuracy for PB NGAL. In both models, neutrophil count was the only significant predictor.Conclusion: BM NGAL was significantly higher than PB NGAL in hematologic malignancy. In addition, PB NGAL could be expressed as a multiple regression model including neutrophil count and BM neutrophil%, being significantly influenced by neutrophil count.

Cho CH, et al. Ann Lab Med. 2016 Jul;36(4):362-366. http://dx.doi.org/10.3343/alm.2016.36.4.362

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.