Related Experiment Video

Updated: Jul 16, 2025

Author Spotlight: Integrated Multi-Omics Analysis for Unveiling Multicellular Immune Signatures in Clinical Heart Attack Cohorts
08:51

Author Spotlight: Integrated Multi-Omics Analysis for Unveiling Multicellular Immune Signatures in Clinical Heart Attack Cohorts

Published on: September 20, 2024

1.3K

Reconstructing the cytokine view for the multi-view prediction of COVID-19 mortality

Yueying Wang1,2,3,4, Zhao Wang5, Yaqing Liu1

  • 1College of Computer Science and Technology, Jilin University, 130012, Changchun, China.

BMC Infectious Diseases
|September 22, 2023
PubMed

Insights

This study developed a COVID-19 mortality prediction model using complete blood counts to predict cytokine levels. Predicted cytokine levels significantly improved mortality prediction accuracy compared to original values.

Area of Science:

  • Biomedical Informatics
  • Computational Biology
  • Epidemiology

Background:

  • Coronavirus disease 2019 (COVID-19) poses a significant threat, necessitating accurate mortality prediction for patient care and resource allocation.
  • Complete blood counts (CBCs) and cytokine levels are altered during COVID-19 infection.
  • CBCs are readily accessible, unlike cytokine levels, highlighting a need for accessible predictive markers.

Purpose of the Study:

  • To develop an accurate COVID-19 mortality prediction model using readily available complete blood counts.
  • To explore the feasibility of predicting cytokine levels from CBC data.
  • To enhance COVID-19 mortality prediction by integrating predicted cytokine levels with CBC data.

Main Methods:

  • Utilized complete blood counts to predict cytokine levels via an autoencoder, principal component analysis, and linear regression.
  • Employed support vector machine classifiers and adaptive boost for feature selection in mortality prediction.
  • Developed predictive models for both cytokine levels and COVID-19 patient mortality.

Main Results:

  • Complete blood counts achieved an Area Under the Curve (AUC) of 0.9678 for COVID-19 mortality classification.
  • Predicted cytokine levels, derived solely from feature sets, yielded a superior AUC of 0.9844 for mortality classification.
  • Predicted cytokine levels demonstrated a stronger association with COVID-19 mortality than original cytokine measurements.

Conclusions:

  • Integrating predicted cytokine levels with CBC data significantly enhanced the COVID-19 mortality prediction model.
  • The developed models for cytokine level prediction and COVID-19 mortality prediction are publicly accessible.
  • This approach offers a cost-effective and accessible method for improving COVID-19 mortality risk assessment.
Abstract

Keywords:
COVID-19Complete blood countsCytokine predictionModel-adjusted cytokineMortality prediction

More Related Videos

Author Spotlight: Unveiling the Polyfunctionality and Heterogeneity in Immune Responses09:43

Author Spotlight: Unveiling the Polyfunctionality and Heterogeneity in Immune Responses

Published on: March 8, 2024

1.7K
A Data-Driven Approach to Quantifying Immune States in Sepsis07:42

A Data-Driven Approach to Quantifying Immune States in Sepsis

Published on: February 7, 2025

208

Related Concept Videos

End Point Prediction: Gran Plot01:07

End Point Prediction: Gran Plot

A Gran plot is used to predict the equivalence volume or endpoint of a potentiometric or acid-base titration without reaching the endpoint. Typically, titration data is collected as a function of the titrant's volume up to a point less than the equivalence volume and then transformed into a linear format. The straight line is extended to the x-axis, indicating the necessary titrant volume to achieve the equivalence point.
For potentiometric titration, the Gran plot is created by plotting...
369
Cancer Survival Analysis01:21

Cancer Survival Analysis

Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
380
Statistical Methods for Analyzing Epidemiological Data01:25

Statistical Methods for Analyzing Epidemiological Data

Epidemiological data primarily involves information on specific populations' occurrence, distribution, and determinants of health and diseases. This data is crucial for understanding disease patterns and impacts, aiding public health decision-making and disease prevention strategies. The analysis of epidemiological data employs various statistical methods to interpret health-related data effectively. Here are some commonly used methods:
400
Mouse Models of Cancer Study02:43

Mouse Models of Cancer Study

Mice have long served as models for studying human biology and pathology because of their phylogenetic and physiological similarity with humans. They are also easy to maintain and breed in the laboratory, and hence, many inbred strains are now available for research. Studies on mice have contributed immeasurably to our understanding of cancer biology.
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
5.6K
Prediction Intervals01:03

Prediction Intervals

The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
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. 
2.3K