Recognizing Patterns of Emerging Chronic Obstructive Pulmonary Disease in Heart Failure Patients Through the Use of Machine Learning Techniques

Heart failure and chronic obstructive pulmonary disease often present with overlapping clinical signs, making differential diagnosis challenging. This work applies machine learning, primarily random forest ensembles trained on heterogeneous clinical data (physical examination, blood biomarkers, disease history, symptoms, echocardiography and ECG findings), to classify heart-failure patients by their risk of developing COPD. Using disease history, symptoms and echocardiography together, the best model reached 87% accuracy and an F1 score of 91% for the high-risk class, with other feature combinations achieving 78-85% accuracy. This work was presented at the 4th Serbian International Conference on Applied Artificial Intelligence (SICAAI 2025), Zlatibor, Serbia, and was carried out within the STRATIFYHF project.