Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: Journal of Medical Internet Research

Date Submitted: Oct 22, 2024
Open Peer Review Period: Oct 22, 2024 - Dec 17, 2024
Date Accepted: Mar 24, 2025
(closed for review but you can still tweet)

The final, peer-reviewed published version of this preprint can be found here:

Evaluation of a Machine Learning Model Based on Laboratory Parameters for the Prediction of Influenza A and B in Chongqing, China: Multicenter Model Development and Validation Study

Hu W, Liu Y, Dong J, Peng X, Yang C, Wang H, Chen Y, Shi S, Li J

Evaluation of a Machine Learning Model Based on Laboratory Parameters for the Prediction of Influenza A and B in Chongqing, China: Multicenter Model Development and Validation Study

J Med Internet Res 2025;27:e67847

DOI: 10.2196/67847

PMID: 40373305

PMCID: 12123241

Evaluation of a machine-learning model based on laboratory parameters for the prediction of influenza A and B: a multicenter model development and validation study in Chongqing, China

  • Weiwei Hu; 
  • Yulong Liu; 
  • Jian Dong; 
  • Xuelian Peng; 
  • Chunyan Yang; 
  • Honglin Wang; 
  • Yong Chen; 
  • Shan Shi; 
  • Jin Li

ABSTRACT

Background:

The influenza virus is a major pathogen causing acute respiratory infections (ARI) in humans, characterized by fever, cough, sore throat, muscle aches, and fatigue. Accurate identification of influenza A and B is crucial for effective treatment and reducing mortality.

Objective:

This study evaluates machine learning approaches and introduces an extreme gradient boosting model, optimized through a custom variable selection algorithm, to predict influenza subtypes based on routine laboratory parameters.

Methods:

This multicentre study used data from three independent hospitals databases. Patients aged 18 or older diagnosed with influenza A (A+ group), influenza B (B+ group), or those with influenza-like symptoms but testing negative for both (A-/B- group) between January 1, 2023, and May 31, 2024, were included. Model performance was evaluated using AUC, accuracy, specificity, sensitivity, PPV, NPV, and F1-score. The final tool, Artificial Intelligence Prediction of Influenza A and B (Ai-Lab) was developed from these models.

Results:

In the internal testing cohort, seven models (KNN, NB, DT, RF, XGB, GBDT, CATB) were evaluated. AUC values for diagnosing influenza A ranged from 0.865 to 0.971, and for influenza B from 0.815 to 0.961. The CATB-based Ai-Lab model, in the external validation cohort, achieved an accuracy of 86.8% for differentiating the A+ group from the A-/B- group and 85.6% for distinguishing the B+ group from the A-/B- group.

Conclusions:

Machine learning models, particularly the CATB-based Ai-Lab model, show promise in accurately predicting influenza A and B infections using routine laboratory parameters, potentially enhancing influenza diagnosis and management.


 Citation

Please cite as:

Hu W, Liu Y, Dong J, Peng X, Yang C, Wang H, Chen Y, Shi S, Li J

Evaluation of a Machine Learning Model Based on Laboratory Parameters for the Prediction of Influenza A and B in Chongqing, China: Multicenter Model Development and Validation Study

J Med Internet Res 2025;27:e67847

DOI: 10.2196/67847

PMID: 40373305

PMCID: 12123241

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.