Machine learning-assisted construction of COPD self-evaluation questionnaire (COPD-EQ): a national multicentre study in China
2025

Developing a COPD Self-Evaluation Questionnaire in China

Sample size: 1824 publication Evidence: high

Author Information

Author(s): Ma Yiming, Zhan Zijie, Chen Yahong, Zhang Jing, Li Wen, He Zhiyi, Xie Jungang, Zhao Haijin, Xu Anping, Peng Kun, Wang Gang, Zeng Qingping, Yang Ting, Chen Yan, Wang Chen

Primary Institution: Central South University, Changsha, China

Hypothesis

The study aimed to develop and validate a COPD self-evaluation questionnaire (COPD-EQ) that is better suited for COPD screening in China.

Conclusion

The COPD-EQ questionnaire was validated to be reliable and accurate in COPD screening for the Chinese population.

Supporting Evidence

  • The study recruited 1824 outpatients from 12 sites, with 404 (22.1%) diagnosed with COPD.
  • The final version of the COPD-EQ questionnaire was shortened to six items.
  • The scoring-based method achieved an AUC score of 0.734 at a threshold of 4.0.
  • The study demonstrated that age and smoking history are significant risk factors for COPD.
  • Machine learning models improved the screening performance of the COPD-EQ questionnaire.

Takeaway

Researchers created a simple questionnaire to help doctors find out if people in China have COPD, which is a serious lung disease.

Methodology

The study used a Delphi method to develop the questionnaire and validated it through a nationwide multicentre prospective study with machine learning methods.

Potential Biases

Potential recall bias from participants not accurately remembering past events.

Limitations

The study may have issues with recall bias and the need for validation in different populations.

Participant Demographics

The average age of participants was 57.1 years, with 38.37% being male.

Statistical Information

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.7189/jogh.15.04052

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication