Developing an ML pipeline for asthma and COPD: The case of a Dutch primary care service

A complex combination of clinical, demographic and lifestyle parameters determines the correct diagnosis most effective treatment for asthma Chronic Obstructive Pulmonary Disease patients. Artificial Intelligence techniques help clinicians in devising designing suitable clinical pathway accordingly, tailored to specific patient conditions. In case machine learning (ML) approaches, availability real-world data train evaluate ML pipeline deputed assist their daily practice is crucial. However, it common exploit either synthetic sets or heavily preprocessed collections cleaning merging different sources. this paper, we describe an automated designed a set including patients from Dutch primary care service, provide performance comparison prediction models (i) assessing various parameters, (ii) interventions, (iii) defining diagnosis.