A machine-learning approach to predicting hypotensive events in ICU settings. (March 2020)

• Record Type: Journal Article
• Authors: Moghadam, Mina Chookhachizadeh; Abad, Ehsan Masoumi Khalil; Bagherzadeh, Nader; Ramsingh, Davinder; Li, Guann-Pyng; Kain, Zeev N.
• Is Part Of: Computers in biology and medicine. Volume 118(2020)
• Publication Date: 2020-03
• Subjects: Machine-learning -- Hypotension -- Prediction -- Short-term history -- ICU; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2020.103626
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Background: 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. This is due to the dynamic changes in patients' physiological status following drug administration, which limits the quantity of useful data available for the algorithm. Method: To mimic real-time monitoring, we developed a machine-learning algorithm that uses most of the available data points from patients' records to train and test the algorithm. The algorithm predicts hypotension up to 30 min in advance based on the data from only 5 min of patient physiological history. A novel evaluation method is also proposed to assess the performance of the algorithm as a function of time at every timestamp within 30 min of hypotension onset. This evaluation approach provides statistical tools to find the best possible prediction window. Results: During about 181, 000 min of monitoring of 400 patients, the algorithm demonstrated 94% accuracy, 85% sensitivity and 96% specificity in predicting hypotension within 30 min of the events. A high PPV of 81% was obtained, and the algorithm predicted 80% of hypotensive events 25 min prior to onset. It was shown that choosing a classification threshold that maximizes the F1 score during the training phase contributes to a high PPV and sensitivity. Conclusions: This study demonstrates the promising potential of machine-learning algorithms in the real-time prediction of hypotensive events in ICU settings based on short-term physiological history. Highlights: Machine-learning algorithms effectively predict hypotension in ICU settings. A labeling method is proposed to mimic real-time monitoring of ICU patients. Short-term physiological history is used to predict events at each data point. The algorithm performance is assessed as a function of time to event onset. Optimizing the F1 score helps to attain a high PPV and sensitivity on the test set.