Citation :

Laxmi Pawar, Suhas Patil, "An Interpretable Deep Learning Framework for Multi-Class COPD Severity Classification using Clinical Biomarkers," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 4, pp. 101-115, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I4P108

Abstract

Respiratory dysfunction and reduced airflow are the main symptoms of Chronic Obstructive Pulmonary Disease (COPD), a chronic and sometimes fatal respiratory illness. For immediate action and individualized treatment, accurate severity assessment of COPD patients is essential. An interpretable deep learning approach for classifying COPD severity using clinical biomarkers and demographic information is given in this research. A Multi-Layer Perceptron (MLP)-based architecture trained using patient-level tabular information, including age, smoking history, pulmonary function parameters, comorbidity, and exercise test results, is used in the proposed model. Nonlinear connections between biomarkers and COPD severity levels are successfully learned by the model. To guarantee data homogeneity, extensive preprocessing was used, including data imputation, scaling, and categorical encoding. The Synthetic Minority Over-sampling Technique (SMOTE) was used to alleviate class imbalance. Across the mild, moderate, severe, and very severe COPD classifications, the proposed COPD severity prediction model achieved a mean accuracy of 99.0%, a Macro-F1 score of 98.5%, and an ROC-AUC of 1.00 under five-fold cross-validation. Additionally, Explainable Artificial Intelligence (XAI) techniques, more especially, SHAP (SHapley Additive exPlanations) were used to interpret model predictions and pinpoint important biomarkers affecting the severity of COPD. Strong discriminative ability was validated by the ROC-AUC curve study. According to experimental findings, combining interpretable deep learning with clinical biomarkers provides a powerful tool for clinical decision support in the treatment of COPD.

Keywords

Clinical biomarkers, COPD severity, GOLD, MLP, SHAP, SMOTE.

References

[1] Fangfei Wang et al., “Computed Tomography‐based Artificial Intelligence in Lung Disease-Chronic Obstructive Pulmonary Disease,” MedComm-Future Medicine, vol. 3, no. 1, pp. 1-10, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Yaman Akbulut, “Automated Pneumonia based Lung Diseases Classification with Robust Technique based on a Customized Deep Learning Approach,” Diagnostics, vol. 13, no. 2, pp. 1-17, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Rehan Khan et al., “Auscultation-based Pulmonary Disease Detection through Parallel Transformation and Deep Learning,” Bioengineering, vol. 11, no. 6, pp. 1-19, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Youssef Abadade et al., “Empowering Healthcare: TinyML for Precise Lung Disease Classification,” Future Internet, vol. 16, no. 11, pp. 1-14, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[5]Pshtiwan Qader Rashid, and İlker Türker, “Lung Disease Detection using U-Net Feature Extractor Cascaded by Graph Convolutional Network,” Diagnostics, vol. 14, no. 12, pp. 1-14, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Rima Tri Wahyuningrum et al., “Enhancing Lung Disease Diagnosis with Deep-Learning-based CT Scan Image Segmentation,” Intelligent Systems with Applications, vol. 27, pp. 1-17, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Md. Nahiduzzaman et al., “Parallel CNN-ELM: A Multiclass Classification of Chest X-Ray Images to Identify Seventeen Lung Diseases Including COVID-19,” Expert Systems with Applications, vol. 229, pp. 1-19, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Ahmed I. Taloba, and R.T. Matoog, “Detecting Respiratory Diseases using Machine Learning-based Pattern Recognition on Spirometry Data,” Alexandria Engineering Journal, vol. 113, pp. 44-59, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Goram Mufarah M. Alshmrani et al., “A Deep Learning Architecture for Multi-Class Lung Diseases Classification using Chest X-Ray (CXR) Images,” Alexandria Engineering Journal, vol. 64, pp. 923-935, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[10] World Health Organization, World Health Statistics 2024: Monitoring Health for the SDGs, Sustainable Development Goals, Global Report, 2024. [Online]. Available: https://www.who.int/publications/i/item/9789240094703

[11] Zhuoneng Zhang et al., “Detection of Chronic Obstructive Pulmonary Disease with Deep Learning using Inspiratory and Expiratory Chest Computed Tomography and Clinical Information,” Journal of Thoracic Disease, vol. 16, no. 9, pp. 6101-6111, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Johan N. Siebert et al., “Deep Learning Diagnostic and Severity-Stratification for Interstitial Lung Diseases and Chronic Obstructive Pulmonary Disease in Digital Lung Auscultations and Ultrasonography: Clinical Protocol for an Observational Case-Control Study,” BMC Pulmonary Medicine, vol. 23, no. 1, pp. 1-6, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Alvar Agusti et al., “Global Initiative for Chronic Obstructive Lung Disease 2023 Report: GOLD Executive Summary,” American Journal of Respiratory and Critical Care Medicine, vol. 207, no. 7, pp. 819-837, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Al-Anazi Saad et al., “Artificial Intelligence in Respiratory Care: Current Scenario and Future Perspective,” Annals of Thoracic Medicine, vol. 19, no. 2, pp. 117-130, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Xiuying Mou et al., “Detection and Airflow Obstruction Severity Grading of Chronic Obstructive Pulmonary Disease based on Capnography,” Nanotechnology Precision Engineering, vol. 8, no. 3, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Nicole M Robertson, Connor S Centner, and Trishul Siddharthan, “Integrating Artificial Intelligence in the Diagnosis of COPD Globally: A Way Forward,” Chronic Obstructive Pulmonary Diseases: Journal of the COPD Foundation, vol. 11, no. 1, pp. 114-120, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Xueting Shen, and Huanbing Liu, “Using Machine Learning for Early Detection of Chronic Obstructive Pulmonary Disease: A Narrative Review,” Respiratory Research, vol. 25, no. 1, pp. 1-9, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Laurie D Snyder et al., “Predictive Machine Learning Algorithm for COPD Exacerbations using a Digital Inhaler with Integrated Sensors,” BMJ Open Respiratory Research, vol. 12, no. 1, pp. 1-12, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Luke A Smith et al., “Machine Learning and Deep Learning Predictive Models for Long‑Term Prognosis in Patients with Chronic Obstructive Pulmonary Disease: A Systematic Review and Meta‑Analysis,” The Lancet Digital Health, vol. 5, no. 12, pp. E872-E881, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Siyang Zeng, Mehrdad Arjomandi, and Gang Luo, “Automatically Explaining Machine Learning Predictions on Severe Chronic Obstructive Pulmonary Disease Exacerbations: Retrospective Cohort Study,” JMIR Medical Informatics, vol. 10, no. 2, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[21] XiaoLing Zou et al., “Screening and Staging of Chronic Obstructive Pulmonary Disease with Deep Learning based on Chest X‑Ray Images and Clinical Parameters,” BMC Pulmonary Medicine, vol. 24, no. 1, pp. 1-10, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Ali Hussain et al., “Forecast the Exacerbation in Patients of Chronic Obstructive Pulmonary Disease with Clinical Indicators using Machine Learning Techniques,” Diagnostics, vol. 11, no. 5, pp. 1-17, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[23] Zian Liu et al., “Construction of a Severity Prediction Model for Hospitalized Patients with Acute Exacerbation of Chronic Obstructive Pulmonary Disease based on Machine Learning,” European Journal of Medical Research, vol. 31, no. 1, pp. 1-15, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[24] Erkang Yi et al., “An Integrated Machine Learning Model of Transcriptomic Genes in Multi-Center Chronic Obstructive Pulmonary Disease Reveals the Causal Role of TIMP4 in Airway Epithelial Cell,” Respiratory Research, vol. 26, no. 1, pp. 1-22, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[25] Uppuluri Ruchitha Venkata Sai Meenakshi, and Vikas Jindal, “A Hybrid Feature Selection Model for Predicting Chronic Obstructive Pulmonary Disease,” Third International Conference on Inventive Research in Computing Applications (ICIRCA), Coimbatore, India, pp. 589-596, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[26] Shuhao Mei et al., “Deep Learning for Detecting and Early Predicting Chronic Obstructive Pulmonary Disease from Spirogram Time Series,” npj Systems Biology and Applications, vol. 11, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[27] Seung Yeob Ryu et al., “Machine Learning-based Prediction of in-Hospital Mortality in Patients with Chronic Respiratory Disease Exacerbations,” Digital Health, vol. 11, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[28] Genevera I. Allen, Luqin Gan, and Lili Zheng, “Interpretable Machine Learning for Discovery: Statistical Challenges and Opportunities,” Annual Review of Statistics and its Application, vol. 11, no. 1, pp. 77-101, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[29] Scott M Lundberg, and Su-In Lee, “A Unified Approach to Interpreting Model Predictions,” Advances in Neural Information Processing Systems, vol. 30, 2017.
[Google Scholar] [Publisher Link]

[30] Israa Mohamed, “Prediction of Chronic Obstructive Pulmonary Disease Stages Using Machine Learning Algorithms,” International Journal of Decision Support System Technology, vol. 14, no. 1, pp. 1–13, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[31] Zhuoneng Zhang et al., “Detection of Chronic Obstructive Pulmonary Disease with Deep Learning using Inspiratory and Expiratory Chest CT and Clinical Information,” Journal of Thoracic Disease, vol. 16, no. 9, pp. 6101-6111, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[32] Nian Cai et al., “Deep Learning Assisted Diagnosis of Chronic Obstructive Pulmonar Disease based on a Local-to-Global Framework,” Electronics, vol. 13, no. 22, pp. 1-13, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[33] He Sui et al., “Diagnosis and Severity Assessment of COPD based on Machine Learning of Chest CT Images,” International Journal of Chronic Obstructive Pulmonary Disease, vol. 20, pp. 2853-2867, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[34] Chew-Teng Kor et al., “Explainable Machine Learning Model for Predicting First-Time Acute Exacerbation in Patients with Chronic Obstructive Pulmonary Disease,” Journal of Personalized Medicine, vol. 12, no. 2, pp. 1-19, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[35] Arnold Kamis et al., “Obtaining the Most Accurate, Explainable Model for Predicting Chronic Obstructive Pulmonary Disease: Triangulation of Multiple Linear Regression and Machine Learning Methods,” JMIR AI, vol. 3, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[36] Walaa H. Elashmawi et al., “Machine Learning for Enhanced COPD Diagnosis: A Comparative Analysis of Classification Algorithms,” Diagnostics, vol. 14, no. 24, pp. 1-26, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[37] Xiuying Mou et al., “A Novel Approach for the Detection and Severity Grading of Chronic Obstructive Pulmonary Disease based on Transformed Volumetric Capnography,” Bioengineering, vol. 11, no. 6, pp. 1-15, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[38] Prakhar Rathi, COPD Patients Dataset, Data of Physical Characteristics of Patients with COPD, 2021. [Online]. Available: https://www.kaggle.com/datasets/prakharrathi25/copd-student-dataset

[39] GOLD Report 2024: Global Initiative for Chronic Obstructive Lung Disease, Global Strategy for the Diagnosis, Management, and Prevention of COPD, 2024. [Online]. Available: https://goldcopd.org/2024-gold-report/

[40] Deepshikha Bhati, Fnu Neha, and Md Amiruzzaman, “A Survey on Explainable Artificial Intelligence (XAI) Techniques for Visualizing Deep Learning Models in Medical Imaging,” Journal of Imaging, vol. 10, no. 10, pp. 1-26, 2024.
[CrossRef] [Google Scholar] [Publisher Link]