Usefulness of monocyte distribution width (MDW) as a sepsis biomarker

Complete Blood Count and Monocyte Distribution Width-Based Machine Learning Algorithms for Sepsis Detection: Multicentric Development and External Validation Study

BACKGROUND

Sepsis is an organ dysfunction caused by a dysregulated host response to infection. Early detection is fundamental to improving the patient outcome. Laboratory medicine can play a crucial role by providing biomarkers whose alteration can be detected before the onset of clinical signs and symptoms. In particular, the relevance of monocyte distribution width (MDW) as a sepsis biomarker has emerged in the previous decade. However, despite encouraging results, MDW has poor sensitivity and positive predictive value when compared to other biomarkers.

OBJECTIVE

This study aims to investigate the use of machine learning (ML) to overcome the limitations mentioned earlier by combining different parameters and therefore improving sepsis detection. However, making ML models function in clinical practice may be problematic, as their performance may suffer when deployed in contexts other than the research environment. In fact, even widely used commercially available models have been demonstrated to generalize poorly in out-of-distribution scenarios.

METHODS

In this multicentric study, we developed ML models whose intended use is the early detection of sepsis on the basis of MDW and complete blood count parameters. In total, data from 6 patient cohorts (encompassing 5344 patients) collected at 5 different Italian hospitals were used to train and externally validate ML models. The models were trained on a patient cohort encompassing patients enrolled at the emergency department, and it was externally validated on 5 different cohorts encompassing patients enrolled at both the emergency department and the intensive care unit. The cohorts were selected to exhibit a variety of data distribution shifts compared to the training set, including label, covariate, and missing data shifts, enabling a conservative validation of the developed models. To improve generalizability and robustness to different types of distribution shifts, the developed ML models combine traditional methodologies with advanced techniques inspired by controllable artificial intelligence (AI), namely cautious classification, which gives the ML models the ability to abstain from making predictions, and explainable AI, which provides health operators with useful information about the models' functioning.

RESULTS

The developed models achieved good performance on the internal validation (area under the receiver operating characteristic curve between 0.91 and 0.98), as well as consistent generalization performance across the external validation datasets (area under the receiver operating characteristic curve between 0.75 and 0.95), outperforming baseline biomarkers and state-of-the-art ML models for sepsis detection. Controllable AI techniques were further able to improve performance and were used to derive an interpretable set of diagnostic rules.

CONCLUSIONS

Our findings demonstrate how controllable AI approaches based on complete blood count and MDW may be used for the early detection of sepsis while also demonstrating how the proposed methodology can be used to develop ML models that are more resistant to different types of data distribution shifts.

Combined detection of monocyte distribution width and procalcitonin for diagnosing and prognosing neonatal sepsis

BACKGROUND

To assess the value of combined Monocyte Distribution Width (MDW) and Procalcitonin (PCT) detection in diagnosing and predicting neonatal sepsis outcomes.

METHODS

This retrospective study, conducted from January 2022 to December 2023.A retrospective analysis of 39 neonatal sepsis and 30 non-infectious systemic inflammatory response syndrome (SIRS) cases was conducted. MDW, PCT, and CRP levels were compared. Relationships between variables were analyzed with Pearson correlation and Cox regression models; diagnostic performance was assessed using ROC curves.

RESULTS

MDW, PCT, and CRP were significantly elevated in sepsis cases (p < 0.001). In non-survivors, MDW was higher and correlated with CRP, PCT, and SNAP scores. MDW was identified as an independent predictor of 28-day mortality. Optimal MDW, PCT, and CRP cut-offs (21.3, 1.23 ng/ml, 32.8 mg/L) achieved AUCs of 0.80, 0.84, and 0.60, respectively. Combined MDW/PCT detection achieved an AUC of 0.90 with 88.2% sensitivity and 88.7% specificity.

CONCLUSION

MDW, especially when combined with PCT, improves diagnostic accuracy for neonatal sepsis management.

Monocyte distribution width (MDW) kinetic for monitoring sepsis in intensive care unit

OBJECTIVES

Monocyte distribution width (MDW) is a measure of monocyte anisocytosis. In this study, we assessed the role of MDW, in comparison to C-reactive protein (CRP), procalcitonin (PCT), and lactate, as a screening and prognostic biomarker of sepsis in intensive care unit (ICU) by longitudinally measuring it in the first 5 days of hospital stay.

METHODS

We considered all consecutive patients admitted to the ICU. At admission, patients were classified as septic or not according to Sepsis-3 criteria. MDW, CRP, PCT, and lactate were measured daily in the first 5 days of hospitalization. ICU mortality was also recorded.

RESULTS

We included 193 patients, 62 with sepsis and 131 without sepsis (controls). 58% and 26 % of the patients, with and without sepsis respectively, died during ICU stay. MDW showed the highest accuracy for sepsis detection, superior to CRP, PCT, and lactate (AUC of 0.840, 0.755, 0.708, 0.622, respectively). At admission, no biomarker predicts ICU mortality in patients with sepsis. The kinetic of all biomarkers during the first 5 days of hospitalization was associated with ICU mortality. Noteworthy, above all, the kinetic of MDW showed the best accuracy. Specifically, an increase or decrease in MDW from day 1-4 and 5 was significantly associated with mortality or survival, respectively.

CONCLUSIONS

MDW is a reliable diagnostic and prognostic sepsis biomarker, better than traditional biomarkers.

The Role of Monocyte Distribution Width in the Early Prediction of Sepsis in Patients Undergoing Cardiovascular Surgery: A Cross-Sectional Study

Background and Objectives: This is the first study to examine the role of monocyte distribution width (MDW) in predicting sepsis after cardiovascular surgery. Methods: This study included 43 consecutive patients who had undergone cardiovascular surgery between July 2021 and July 2022. All patients were examined at the following three time points (TPs): preoperative period (TP1), postoperative at 24 h (TP2), and discharge (TP3). SOFA score, leukocyte count, neutrophil-to-lymphocyte ratio (NLR), MDW, C-reactive protein (CRP), and procalcitonin (PCT) levels were tested at each TPs. The Sepsis-3 criteria were used to diagnose patients with sepsis. Results: The mean values of all variables (leukocyte count, NLR, MDW, CRP, and PCT levels) were significantly higher at TP2 and TP3 than at TP1 (p < 0.05). All these values were significantly higher at TP2 than at TP3 (p < 0.05). Patients with sepsis had significantly higher mean values for leukocyte count, NLR, MDW, CRP, and PCT levels than those without sepsis (p < 0.05). There was a significant correlation between MDW and inflammatory markers (CRP, PCT, and NLR) during the three time periods (p < 0.05). According to the ROC analysis, the optimal MDW cutoff value with the highest sensitivity and specificity for predicting sepsis in the postoperative period was 20.5. Conclusions: Our findings indicate that elevated MDW levels may be a valuable predictor of sepsis in patients following cardiovascular surgery.

Value of monocyte distribution width for predicting severe cholecystitis: a retrospective cohort study

OBJECTIVES

Acute cholecystitis is a gallbladder inflammation, and the Tokyo Guidelines 2018 (TG18) can be used to predict its presence and severity with high sensitivity and specificity. However, TG18 grading require the collection of excessive parameters. Monocyte distribution width (MDW) is a parameter used to detect sepsis early. Therefore, we investigated the correlation between MDW and cholecystitis severity.

METHODS

We conducted a retrospective study of patients with cholecystitis admitted to our hospital from November 1, 2020, to August 31, 2021. The primary outcome was severe cholecystitis analyzed as a composite of intensive care unit (ICU) admission and mortality. The secondary outcomes were length of hospital stay, ICU stay, and TG18 grade.

RESULTS

A total of 331 patients with cholecystitis were enrolled in this study. The average MDWs for TG18 grades 1, 2, and 3 were 20.21 ± 3.99, 20.34 ± 3.68, and 25.77 ± 6.61, respectively. For patients with severe cholecystitis, the average MDW was 25.42 ± 6.83. Using the Youden J statistic, we set a cutoff MDW of 21.6. Multivariate logistic regression revealed that patients with an MDW≥21.6 had a higher risk of severe cholecystitis (odds ratio=4.94; 95 % CI, 1.71-14.21; p=0.003). The Cox model revealed that patients with an MDW≥21.6 were more likely to have a prolonged hospital stay.

CONCLUSIONS

MDW is a reliable indicator of severe cholecystitis and prolonged length of stay. Additional MDW testing and a complete blood count may provide simple information for predicting severe cholecystitis early.

Comparison of monocyte distribution width and Procalcitonin as diagnostic markers for sepsis: Meta-analysis of diagnostic test accuracy studies

AIM

We aimed to perform a meta-analysis to find out whether PCT and MDW could be used as accurate diagnostic markers for sepsis.

METHODS

We searched PUBMED, WOS, and SCOPUS databases. Inclusion criteria were any observational or clinical trials that compared monocyte Distribution Width [MDW] with Procalcitonin [PCT] as diagnostic markers in a patient with sepsis. Case reports, editorials, conference abstracts, and animal studies were excluded. RevMan software [5.4] was used to perform the meta-analysis.

RESULTS

After the complete screening, 5 observational studies were included in the meta-analysis. The total number of patients included in the meta-analysis in the sepsis group is 565 and 781 in the control group. The pooled analysis between the sepsis group and controls showed a statistically significant association between sepsis and increased levels of MDW and PCT [MD = 3.94, 95% CI = 2.53 to 5.36, p-value < 0.00001] and [MD = 9.29, 95% CI = 0.67 to 17.91, p-value = 0.03] respectively. Moreover, the subgroup analysis showed that the p-value of MDW levels [< 0.00001] is more significant than the p-value of PCT levels = 0.03, the p-value between the two subgroups [< 0.00001]. Additionally, the overall ROC Area for MDW [0.790] > the overall ROC Area for PCT [0.760].

CONCLUSION

Our study revealed a statistically significant association between sepsis and increased MDW and PCT levels compared with controls and the overall ROC Area for MDW is higher than the overall ROC Area for PCT, indicating that the diagnostic accuracy of MDW is higher than PCT.MDW can be used as a diagnostic marker for sepsis patients in the emergency department. More multicenter studies are needed to support our findings.

Monocyte distribution width (MDW) as an infection indicator in severe patients attending in the Emergency Department: a pilot study

OBJECTIVE

The aim of the present study was to evaluate the diagnostic performance of monocyte distribution width (MDW) as a biomarker for sepsis diagnosis in severe patients attended in the Emergency Department for different conditions and not only infections.

METHODS

We performed an observational study in a consecutive prospective cohort including severe patients attending the Emergency Department with different conditions. MDW and other biomarkers were determined from samples obtained during the first care of patients. The diagnostic performance of the different biomarkers was determined based on the final diagnosis at patient discharge.

RESULTS

One hundred two patients, with a mean age of 76.7 (SD 16.5) years were included, 53 being (51.9%) male. Among the patients included, 65 (63.7%) had an infectious disease while the remaining had other different conditions. A MDW cut-off of 20.115 provided the best accuracy to identify infected patients, with a sensitivity of 89.2 (95% CI 79.4-94.7), a specificity of 89.2 (95% CI 75.3-95.7), a positive predictive value of 93.5 (95% CI 84.6-97.5), a negative predictive value of 82.5% (95% CI 68.0-91.3), a positive likelihood ratio of 8.25 (3.26-20.91), and a negative likelihood ratio of 0.12 (0.06-0.24). The area under the receiver operating characteristic curve for infection according to MDW was 0.943 (95% CI 0.897-0.989; p<0.001).

CONCLUSIONS

A MDW > 20.115 may be associated with infection and could help to distinguish between infected and non-infected patients in severe patients. These results must be confirmed in new studies due to the limited patient sample included.

Comparison of the Diagnostic Accuracies of Monocyte Distribution Width, Procalcitonin, and C-Reactive Protein for Sepsis: A Systematic Review and Meta-Analysis

OBJECTIVES

We performed a systemic review and meta-analysis to evaluate the diagnostic accuracy of monocyte distribution width (MDW) and to compare with procalcitonin and C-reactive protein (CRP), in adult patients with sepsis.

DATA SOURCES

A systematic literature search was performed in PubMed, Embase, and the Cochrane Library to identify all relevant diagnostic accuracy studies published before October 1, 2022.

STUDY SELECTION

Original articles reporting the diagnostic accuracy of MDW for sepsis detection with the Sepsis-2 or Sepsis-3 criteria were included.

DATA EXTRACTION

Study data were abstracted by two independent reviewers using a standardized data extraction form.

DATA SYNTHESIS

Eighteen studies were included in the meta-analysis. The pooled sensitivity and specificity of MDW were 84% (95% CI [79-88%]) and 68% (95% CI [60-75%]). The estimated diagnostic odds ratio and the area under the summary receiver operating characteristic curve (SROC) were 11.11 (95% CI [7.36-16.77]) and 0.85 (95% CI [0.81-0.89]). Significant heterogeneity was observed among the included studies. Eight studies compared the diagnostic accuracies of MDW and procalcitonin, and five studies compared the diagnostic accuracies of MDW and CRP. For MDW versus procalcitonin, the area under the SROC was similar (0.88, CI = 0.84-0.93 vs 0.82, CI = 0.76-0.88). For MDW versus CRP, the area under the SROC was similar (0.88, CI = 0.83-0.93 vs 0.86, CI = 0.78-0.95).

CONCLUSIONS

The results of the meta-analysis indicate that MDW is a reliable diagnostic biomarker for sepsis as procalcitonin and CRP. Further studies investigating the combination of MDW and other biomarkers are advisable to increase the accuracy in sepsis detection.

Models for bacteraemia risk prediction. Clinical implications

Bacteraemia has important consequences for the patient, as it is associated with worse clinical outcomes. On the other hand, unnecessarily obtaining samples for blood cultures increases costs and the workload in the microbiology laboratory. Its diagnosis implies a time delay, but decisions about start antibiotic treatment, discharge, or admits the patient must be taken during the first attention and, therefore, before known the blood cultures results. This manuscript reviews the different strategies based on clinical scores and biomarkers that are useful for predicting bacteraemia and improving initial decision-making.