Details

Autor(en) / Beteiligte

• Yoon, J
• Mu, L
• Chen, L
• Dubrawski, A W
• Hravnak, M
• Pinsky, M R
• Clermont, G

Titel

C102 CRITICAL CARE: PREDICTING AND IDENTIFYING ARDS DEVELOPMENT, SEPSIS AND CLINICAL DETERIORATION: Data-Driven Prediction And Risk Score Model For Tachycardia Event In The Intensive Care Unit

Ist Teil von

• American journal of respiratory and critical care medicine, 2017-01, Vol.195

Ort / Verlag

New York: American Thoracic Society

Erscheinungsjahr

2017

Quelle

EZB Electronic Journals Library

Beschreibungen/Notizen

• Methods: A matched subset of clinical and 1Hz physiological signals data was extracted from MIMIC2 version 2.6, a richly annotated multi-domain, multigranular database. Regularized logistic regression (LR) and Random Forest (RF) classifiers were trained with 10-fold cross-validation to create a risk score for developing tachycardia.