RT Journal Article
SR Electronic
T1 A Machine Learning Approach to Predict Hypotensive Events in ICU Settings
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 794768
DO 10.1101/794768
A1 Mina Chookhachizadeh Moghadam
A1 Ehsan Masoumi
A1 Nader Bagherzadeh
A1 Davinder Ramsingh
A1 Guann-Pyng Li
A1 Zeev N Kain
YR 2019
UL http://biorxiv.org/content/early/2019/10/07/794768.abstract
AB Purpose Predicting hypotension well in advance provides physicians with enough time to respond with proper therapeutic measures. However, the real-time prediction of hypotension with high positive predictive value (PPV) is a challenge due to the dynamic changes in patients’ physiological status under the drug administration which is limiting the amount of useful data available for the algorithm.Methods To mimic real-time monitoring, we developed a machine learning algorithm that uses most of the available data points from patients’ record to train and test the algorithm. The algorithm predicts hypotension up to 30 minutes in advance based on only 5 minutes of patient’s physiological history. A novel evaluation method is proposed to assess the algorithm performance as a function of time at every timestamp within 30 minutes prior to hypotension. This evaluation approach provides statistical tools to find the best possible prediction window.Results During 181,000 minutes of monitoring of about 400 patients, the algorithm demonstrated 94% accuracy, 85% sensitivity and 96% specificity in predicting hypotension within 30 minutes of the events. A high PPV of 81% obtained and the algorithm predicted 80% of the events 25 minutes prior to their onsets. It was shown that choosing a classification threshold that maximizes the F1 score during the training phase contributes to a high PPV and sensitivity.Conclusion This study reveals the promising potential of the machine learning algorithms in real-time prediction of hypotensive events in ICU setting based on short-term physiological history.