Identifying Influential Variables for an Explainable AI Based Clinical Decision Support System in the Healthcare Industry

This research developed an Explainable AI (XAI) based Clinical Decision Support System (CDSS) to assist practitioners during anamnesis by classifying patient diagnoses. Utilizing Electronic Health Records (EHR) data, we designed a machine learning (ML) model focusing on pain location and type, reduced variables from 299 to 51, and trained classifiers. The multi-label classifier model, with high precision, was most effective. Explainable outputs were evaluated by practitioners, ensuring transparency and aiding decision-making. This study enhances standardized patient care, reduces consultation times, and minimizes misdiagnoses, demonstrating the integration of ML in clinical settings for improved healthcare outcomes.