Objective
The critical care management application provides critical care support and monitoring functionalities for patients admitted to hospital-like environments. Unsupervised machine learning techniques have been used to explore massive amounts of data encoded in electronic medical records. Models have been developed to obtain important information in a patient’s chart and identify high-cost patients. Supervised machine learning algorithms, given their potential for automated pattern recognition of images, have proven their utility in radiology and histopathology. Machine learning has been used extensively in the fields of surgery, in cardiology, or early detection of heart failure, and in cancer research to classify tumor types and growth rates.
Outcome
With the critical care management application, one should be able to get notifications and alerts regarding the change of the health status of active patients as well as recommendations for next best actions.
● Has the condition of a patient deteriorated?
● Any abnormal changes in the heartbeat?
● Is oxygen saturation above the required levels?
● Is the patient experiencing high temperature?
Business Value
Critical Care Management is powered by the H2O AI Cloud Driverless AI, AutoML, and H2O.ai Wave. The data science approaches include regression, time series, stacked ensembles, and advanced feature engineering. The data science approaches include time series, Classification, stacked ensembles, and Signal detection algorithms.