Decision support tool for determining patient length of stay within an emergency department

One or more computer storage media having computer-executable instructions embodied thereon that, when executed, provide a method for managing healthcare resources within an emergency department, the method comprising:

• receiving patient information for a plurality of patients being admitted into an emergency department;
• receiving facility information for a facility in which the emergency department is located;
• predicting a length of stay in the emergency department for each patient within the plurality of patients, each length of stay being predicted using a plurality of machine learning models and at least some of the patient information and at least some of the facility information, wherein the length of stay is predicted by using the plurality of machine learning models in a sequence, such that an output from one of the plurality of machine learning models is an input for a subsequent machine learning model of the plurality of machine learning models;
• and
• automatically initiating one or more response actions based on the lengths of stays predicted for the plurality of patients.

A computerized system for managing healthcare resources within an emergency department, the computerized system comprising:

• one or more processors;
• and
• one or more computer storage media having instructions that, when executed by the one or more processors, cause a method to be performed, the method comprising:
• receive patient information for a patient being admitted into an emergency department;
• receive facility information for a facility in which the emergency department is located;
• predict a length of stay in the emergency department for the patient, the length of stay being predicted using a plurality of machine learning models and at least some of the patient information and at least some of the facility information, wherein the length of stay is predicted by using the plurality of machine learning models in a sequence, such that an output from one of the plurality of machine learning models is an input for a subsequent machine learning model of the plurality of machine learning models;
• and
• automatically initiate one or more response actions based on the length of stay predicted for the patient.