Workflow predictive analytics engine

1. A predictive workflow analytics apparatus comprising:

a memory including instructions; and

at least one processor to execute the instructions to at least:

orchestrate, using an orchestration service, a combination of non-healthcare information with healthcare workflow data including patient information and a scheduled appointment for the patient;

generate a prediction including a probability of a patient no-show to the scheduled appointment using an artificial intelligence engine in an inferencing mode, the artificial intelligence engine including a trained patient no-show model selected from a plurality of models in the artificial intelligence engine to predict the probability of the patient no-show based on the combination of healthcare workflow data and non-healthcare information from the orchestration service;

synchronize the prediction and a schedule including the scheduled appointment for the patient; and

generate an interactive dashboard including the synchronized prediction and the schedule and at least one of: a) a first option to adjust the schedule to replace the patient based on the probability of the patient no-show, b) a second option to adjust the schedule to move the patient to a different time based on the probability of the patient no-show.

2. The apparatus of claim 1 , wherein the non-healthcare data includes at least one of weather forecast data, traffic forecast data, or holiday information.

3. The apparatus of claim 1 , wherein the patient no-show model is to be implemented using at least one of a random forest model or a neural network model.

4. The apparatus of claim 1 , wherein the at least one processor is to operate the artificial intelligence engine in a training mode to train the patient no-show model.

5. The apparatus of claim 4 , wherein patient no-show prediction accuracy feedback provided in the inferencing mode is to trigger the at least one processor to enter the training mode.

6. The apparatus of claim 1 , wherein the at least one processor is to synchronize the prediction and the schedule using a data cube.

7. The apparatus of claim 1 , wherein the interactive dashboard is to include a third option to send a reminder of the scheduled appointment to the patient.

8. The apparatus of claim 1 , wherein the at least one processor is to retrieve the healthcare workflow data using a fast healthcare interoperability resources application programming interface that defines the resources as a set of at least one of operations or interactions to retrieve the healthcare workflow data based on type.

9. The apparatus of claim 8 , wherein the at least one processor is to interface with a scheduling system to provide the schedule, the prediction, and a selected one of the first option or the second option to the scheduling system via the fast healthcare interoperability resources application programming interface.

10. The apparatus of claim 1 , wherein the interactive dashboard includes a predictive interface view and a retrospective interface view.

11. At least one non-transitory computer-readable storage medium comprising instructions which, when executed by at least one processor, cause the at least one processor to at least:

orchestrate, using an orchestration service, a combination of non-healthcare information with healthcare workflow data including patient information and a scheduled appointment for the patient;

generate a prediction including a probability of a patient no-show to the scheduled appointment using an artificial intelligence engine in an inferencing mode, the artificial intelligence engine including a trained patient no-show model selected from a plurality of models in the artificial intelligence engine to predict the probability of the patient no-show based on the combination of healthcare workflow data and non-healthcare information from the orchestration service;

synchronize the prediction and a schedule including the scheduled appointment for the patient; and

generate an interactive dashboard including the synchronized prediction and the schedule and at least one of: a) a first option to adjust the schedule to replace the patient based on the probability of the patient no-show, b) a second option to adjust the schedule to move the patient to a different time based on the probability of the patient no-show.

12. The at least one computer-readable storage medium of claim 11 , wherein the non-healthcare data includes at least one of weather forecast data, traffic forecast data, or holiday information.

13. The at least one computer-readable storage medium of claim 11 , wherein the instructions, when executed, cause the at least one processor to operate the artificial intelligence engine in a training mode to train the patient no-show model.

14. The at least one computer-readable storage medium of claim 13 , wherein patient no-show prediction accuracy feedback provided in the inferencing mode is to trigger the at least one processor to enter the training mode.

15. The at least one computer-readable storage medium of claim 11 , wherein the interactive dashboard is to include a third option to send a reminder of the scheduled appointment to the patient.

16. The at least one computer-readable storage medium of claim 11 , wherein the at least one processor is to retrieve the healthcare workflow data using a fast healthcare interoperability resources application programming interface that defines the resources as a set of at least one of operations or interactions to retrieve the healthcare workflow data based on type.

17. The at least one computer-readable storage medium of claim 16 , wherein the instructions, when executed, cause the at least one processor to interface with a scheduling system to provide the schedule, the prediction, and a selected one of the first option or the second option to the scheduling system via the fast healthcare interoperability resources application programming interface.

18. A method to apply predictive analytics to drive a patient care pathway, the method comprising:

orchestrating, using an orchestration service, a combination of non-healthcare information with healthcare workflow data including patient information and a scheduled appointment for the patient;

generating a prediction including a probability of a patient no-show to the scheduled appointment using an artificial intelligence engine in an inferencing mode, the artificial intelligence engine including a trained patient no-show model selected from a plurality of models in the artificial intelligence engine to predict the probability of the patient no-show based on the combination of healthcare workflow data and non-healthcare information from the orchestration service;

synchronizing the prediction and a schedule including the scheduled appointment for the patient; and

generating an interactive dashboard including the synchronized prediction and the schedule and at least one of: a) a first option to adjust the schedule to replace the patient based on the probability of the patient no-show, b) a second option to adjust the schedule to move the patient to a different time based on the probability of the patient no-show.

19. The method of claim 18 , wherein the non-healthcare data includes at least one of weather forecast data, traffic forecast data, or holiday information.

20. The method of claim 18 , further including, triggering, based on patient no-show prediction accuracy feedback, a training mode to retrain the patient no-show model.