Machine Learning for Enhanced COPD Diagnosis
Author Information
Author(s): Walaa H. Elashmawi, Adel Djellal, Alaa Sheta, Salim Surani, Sultan Aljahdali
Primary Institution: Department of Computer Science, Suez Canal University, Ismailia, Egypt
Hypothesis
Can machine learning accurately predict COPD without relying on spirometry?
Conclusion
The random forest classifier outperformed other models in diagnosing COPD, achieving an accuracy of 70.47%.
Supporting Evidence
- The random forest classifier achieved an accuracy of 70.47% in testing.
- Machine learning models showed accuracies ranging from 67.81% to 82.06% in training.
- The study utilized a dataset of 1603 patients referred for pulmonary function tests.
- Various machine learning classifiers were compared, including logistic regression and support vector machines.
Takeaway
This study used computers to help doctors find out if people have a lung disease called COPD, and it found that one computer method worked best.
Methodology
The study reviewed various machine learning classifiers applied to a dataset of COPD patients to evaluate their diagnostic accuracy.
Potential Biases
Potential biases in the dataset due to underdiagnosis and misdiagnosis of COPD.
Limitations
The study may not generalize to all populations due to the specific dataset used.
Participant Demographics
The dataset included 1603 patients, with 36.68% diagnosed with COPD and a gender distribution of 47.6% male and 52.4% female.
Statistical Information
P-Value
0.0634819
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website