Predicting ARDS using the MIMIC II physiological database

Aline Taoum (1) , Farah Mourad-Chehade (2) , Hassan Amoud (1) , Ziad Fawal (1)

1 LU / ULB - الجامعة اللبنانية [بيروت] = Lebanese University [Beirut] = Université libanaise [Beyrouth]
2 LM2S - Laboratoire Modélisation et Sûreté des Systèmes

Acute Respiratory Distress Syndrome (ARDS) is a critical lung condition occurring in ill patients. Like many other cardiac disorders, ARDS can be assessed by physiological measurements. This study aims to predict ARDS in hospitalized patients using only physiological signals as heart rate and breathing rate. An approach based on hypothesis testing is developed to detect whether subjects' signals deviate from their initial states. The approach is applied on mechanically ventilated subjects in the MIMIC II database. As results, a sensitivity going up to 85% is achieved, with a prediction remaining possible before 24 hours of ARDS occurrence.

Domaines: Ingénierie biomédicale; Traitement du signal et de l'image [eess.SP]

Aline Taoum, Farah Mourad-Chehade, Hassan Amoud, Ziad Fawal. Predicting ARDS using the MIMIC II physiological database. 2016 IEEE International Multidisciplinary Conference on Engineering Technology (IMCET), Nov 2016, Beirut, Lebanon. pp.47-51, ⟨10.1109/IMCET.2016.7777425⟩. ⟨hal-02358782⟩