Inference Model for Acute Lung Injury Detection in the ICU
Year: 2011
Type: conference-paper
Abstract: Acute Lung Injury (ALI) is a devastating complication of acute illness and one of the leading causes of multiple organ failureand mortality in the Intensive Care Unit (ICU). The detection of this syndrome is limited due to the complexity of the disease, insufficient understanding of its development and progression, and the large amount of risk factors and modifiers, and delayed radiographic results [1]. In this paper, we propose a novel detection framework forALI that encompasses physicians experience, knowledge of pathophysiology, results of clinical trials and patient data. It involves three complementary techniques, namely, rule-based Fuzzy Inference Systems, Bayesian Networks, and Finite State Machines. The proposed application was validated on Electronic Medical Record (EMR) data for 600patients from Mayo Clinic (300 ALI and 300 Controls) and it attained sensitivity in the range of 72.3-92.3% and specificity in the range of 60-80.3% depending on the technique used, as opposed to the 30%sensitivity by bedside clinicians [2].
Authors: Chbat, N.W., Chu, W., Ghosh, M., Li, G., Li, M., Chiofolo, C., Vairavan, S., Herasevich, V., Gajic, O.
Language: English
Subfield: Health Information Management
Field: Health Professions
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W16738756