Abstract: A patient discharge date prediction system generates probabilistic discharge timing predictions using a trained length of stay prediction model that receives patient data and operational workflow data encoded into data vectors. The model simultaneously outputs a predicted discharge date, a discharge horizon probability distribution indicating probabilities of discharge on a specified date, the next day, or two or more days from the specified date, and a time-of-day discharge probability distribution indicating probabilities of discharge within specific time windows during the day. Wilson score interval calibration is applied to the probability distributions based on historical observed discharge rates to generate calibrated probabilities and confidence intervals. The calibrated probabilities and confidence intervals are displayed in a graphical user interface.

Abstract: Systems and methods for multi-resource scheduling are disclosed and described. An example apparatus includes a scheduler engine configured to enable clinical system(s) to operate with the scheduler engine in an analytical mode and an operating mode. When in the analytical mode, the scheduler engine is to dynamically calculate one or more binding constraints on the one or more clinical systems for scheduling. When in the operating mode, the scheduler engine is to manage and output a schedule for the one or more clinical systems based on the one or more binding constraints calculated in the analytical mode. The example scheduler engine is to dynamically switch between the analytical mode and the operating mode based at least in part on a probabilistic determination of delay associated with the schedule.

Abstract: Systems and methods for multi-resource scheduling are disclosed and described. An example apparatus includes a scheduler engine configured to enable clinical system(s) to operate with the scheduler engine in an analytical mode and an operating mode. When in the analytical mode, the scheduler engine is to dynamically calculate one or more binding constraints on the one or more clinical systems for scheduling. When in the operating mode, the scheduler engine is to manage and output a schedule for the one or more clinical systems based on the one or more binding constraints calculated in the analytical mode. The example scheduler engine is to dynamically switch between the analytical mode and the operating mode based at least in part on a probabilistic determination of delay associated with the schedule.

Abstract: Systems and methods are provided to schedule clinical tasks involving multiple sub-tasks and multiple resources in a clinical enterprise. An example method includes identifying a slot for a task defined by a task duration and one or more resources, the task including a plurality of sub-tasks, each sub-task having a sub-task duration utilizing one or more of the one or more resources, wherein each sub-task to be performed consecutively based on resource constraints; selecting a time slot for the task based on resource availability, the plurality of sub-tasks in the task, and a duration associated with each sub-task, wherein resource availability information is obtained from a clinical information system, and wherein each resource is scheduled only for one or more sub-tasks in which the resource is involved; displaying the schedule including the task and the plurality of sub-tasks; and facilitating access to view and modify the schedule.

Abstract: Systems and methods are provided to schedule clinical tasks involving multiple sub-tasks and multiple resources in a clinical enterprise. An example method includes identifying a slot for a task defined by a task duration and one or more resources, the task including a plurality of sub-tasks, each sub-task having a sub-task duration utilizing one or more of the one or more resources, wherein each sub-task to be performed consecutively based on resource constraints; selecting a time slot for the task based on resource availability, the plurality of sub-tasks in the task, and a duration associated with each sub-task, wherein resource availability information is obtained from a clinical information system, and wherein each resource is scheduled only for one or more sub-tasks in which the resource is involved; displaying the schedule including the task and the plurality of sub-tasks; and facilitating access to view and modify the schedule.