Dataset Information

Initial complete blood count score and predicting disease progression in COVID-19 patients.

ABSTRACT:

Introduction

Coronavirus has caused a pandemic since it was first detected in Wuhan in December 2019. The mortality rate is high in moderate and severe cases. Our study aimed to screen the CBC parameters as a useful predictive factor for COVID-19 resulting in critical illness.

Methods

A total of 285 patients with positive PCR results were analyzed. The median age was 55 (24-90), and 64.2% of patients were male. Sixty-eight percent of cases were hospitalized with moderate, 32% with severe disease at initial admission.

Results

We found that lymphocyte count <620/mcl, neutrophil-to-lymphocyte ratio (NLR) >6, and platelet to lymphocyte ratio (PLR) >350 were predictive of the outcome. We scored our cohort 0-3 for these three parameters. Patients with a score of 2-3 were more likely to have progressive disease, anti-cytokine treatment, intensive care admission, intubation, and death, compared to patients with a score of 0-1. Additionally, they tended to be hospitalized for longer (median 11.5 days, mean 15.6), compared to those with a score 0 or 1 (median 9 days, mean 11.3). Twenty-eight of 38 cases with scores of 2-3 were discharged (73.6%), whereas the rate was 89% for patients with a score of 0-1 (P=0.009).

Conclusion

Based on the absolute lymphocyte count (<620/mcl, NLR >6, PLR >350), our three-parameter score was able to predict disease progression, and the likelihood of anti-cytokine treatment, intubation, and death. We think that COVID-19 patients presenting with moderate to severe pneumonia, and having scores of 2 or 3 on our scale, should be closely monitored and robustly supported.

SUBMITTER: Ozbalak M

PROVIDER: S-EPMC8010608 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundCOVID-19, caused by SARS-CoV-2, presents distinct diagnostic challenges due to its wide range of clinical manifestations and the overlapping symptoms with other common respiratory diseases. This study focuses on addressing these difficulties by employing machine learning (ML) methodologies, particularly the XGBoost algorithm, to utilize Complete Blood Count (CBC) parameters for predictive analysis.MethodsWe performed a retrospective study involving 2114 COVID-19 patients treated between December 2022 and January 2023 at our healthcare facility. These patients were classified into fever (1057 patients) and pneumonia groups (1057 patients), based on their clinical symptoms. The CBC data were utilized to create predictive models, with model performance evaluated through metrics like Area Under the Receiver Operating Characteristics Curve (AUC), accuracy, sensitivity, specificity, and precision. We selected the top 10 predictive variables based on their significance in disease prediction. The data were then split into a training set (70% of patients) and a validation set (30% of patients) for model validation.ResultsWe identified 31 indicators with significant disparities. The XGBoost model outperformed others, with an AUC of 0.920 and high precision, sensitivity, specificity, and accuracy. The top 10 features (Age, Monocyte%, Mean Platelet Volume, Lymphocyte%, SIRI, Eosinophil count, Platelet count, Hemoglobin, Platelet Distribution Width, and Neutrophil count.) were crucial in constructing a more precise predictive model. The model demonstrated strong performance on both training (AUC = 0.977) and validation (AUC = 0.912) datasets, validated by decision curve analysis and calibration curve.ConclusionML models that incorporate CBC parameters offer an innovative and effective tool for data analysis in COVID-19. They potentially enhance diagnostic accuracy and the efficacy of therapeutic interventions, ultimately contributing to a reduction in the mortality rate of this infectious disease.