Related Experiment Video
Updated: Dec 14, 2025

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Analysis of prediction and early warning indexes of patients with COVID-19
Lu Song1, Yongkang Dong2, Ming Xu3
1Department of Critical Care Medicine, Shanxi Provincial People's Hospital , Taiyuan, China.
Background:
The aim was to compare the laboratory data of patients with suspected and confirmed new coronavirus pneumonia (COVID-19) and look for diagnostic predictive and early warning indicators, which will help to better manage the disease.
Methods:
A total of 36 confirmed COVID-19 patients were divided into the general (n = 17) and critical group (n = 19). The suspected group enrolled 23 suspected COVID-19 patients with the negative nucleic acid test result. We collected all patients' clinical characteristics and some laboratory indicators at the time of admission and conducted Logistic regression analysis after comparing the differences between groups.
Results:
There were no significant differences in age, gender, disease duration, fever history, and comorbidities between the suspected and general group (P > 0.05); however, fibrinogen was statistically different (P < 0.05). Compared with the general group, the oxygenation index and lymphocytes were significantly reduced and the Neutrophil-to-lymphocyte Ratio (NLR) and total bilirubin were increased in the critical group (P < 0.05). The fibrinogen OR value was 2.52 (95% CI 1.18-5.36, P = 0.017) and the NLR OR value was 2.91 (95% CI 1.36-6.21, P = 0.006).
Conclusions:
Fibrinogen is a valuable diagnostic predictor for patients with suspected COVID-19. For confirmed COVID-19 patients, the NLR is a valuable early warning indicator.
Related Concept Videos
Steps in Outbreak Investigation
Pareto Chart
The Pareto chart is named after the Italian economist Vilfredo Pareto, who described the Pareto...
Statistical Software for Data Analysis and Clinical Trials
Sensitivity, Specificity, and Predicted Value
Sensitivity is the...
Prediction Intervals
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
Interpreting Run Charts

