Modular ML-Framework to develop and compare AI models for ARDS classification

Abstract: Acute Respiratory Distress Syndrome (ARDS) is a severe condition in intensive care units with high mortality. The current standard for the diagnosis of ARDS is the Berlin-Definition. However, epidemiological studies have shown, that ARDS is often diagnosed too late or missed completely. Artificial Intelligence, i.e. machine learning or deep learning methods are proposed to help clinicians to identify ARDS earlier to improve the patient’s outcome. In our work, we propose a modular machine learning framework for the development, comparison and use of AI models for ARDS classification.