Predictive scheduling for procedure medicine

• US 8,069,055 B2
• Filed: 02/09/2006
• Issued: 11/29/2011
• Est. Priority Date: 02/09/2006
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Keen, Ronald
• Primary Examiner(s): Morgan; Robert
• Assistant Examiner(s): BURGESS, JOSEPH D
• Application Number:
  US11/352,043
• Publication Number:
  US 20070203761A1
• Time in Patent Office: 2,119 Days
• Field of Search: 705 2- 3, 705/7
• US Class Current: 705/2
• CPC Class Codes: G06Q 10/02 Reservations, e.g. for tickets, services or events
• CPC Class Codes: G16H 20/40 relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
• CPC Class Codes: G16H 40/20 for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

Scheduling techniques are disclosed that employ one or more predictive scheduling classification algorithms configured to exploit historical data of previously scheduled and completed medical procedures. Thus, a new patient that is similarly-situated to previously treated patients can have a medical procedure automatically predicted and scheduled based on historical procedure data associated with those previously treated patients.

Claims

1. A computer-implemented method for predictively scheduling a patient for a medical event, comprising:

configuring a set of executable code in a tangible storage medium, wherein the set of executable code is executed by a processor, effectuating the following steps;

receiving historical patient-procedure data;

transforming the received historical patient-procedure data into a schema;

building one or more prediction models using the transformed patient-procedure data from the schema;

predictively scheduling the medical procedure for the patient, wherein the step of predictively scheduling the medical procedure further comprises;

processing a set of target patient procedure data in each of the plurality of prediction models and determining a score for each of the results of the processing step;

determining a majority of the scores from the plurality of prediction models agree by determining whether each score exceeds a predetermined threshold; and

predictively scheduling the medical appointment utilizing the plurality of prediction models that agree and the set of target patient-procedure data.

2. The method of claim 1, further comprising:

in response to determining new historical patient-procedure data has been received, updating the one or more prediction models.

3. The method of claim 1 wherein the step of predictively scheduling the medical procedure is preceded by:

receiving a new scheduling event request, including the target patient-procedure data.

4. The method of claim 3 wherein the target patient-procedure data is transformed to comply with the schema.

5. The method of claim 1 wherein the historical patient-procedure data comprises actual data from previously completed patient procedures, including at least one of procedure attributes, procedure durations, patient demographics, equipment used, and attending personnel.

6. The method of claim 1 wherein the one or more prediction models include at least one of Naï

ve Bayes, logistics regression, neural network, maximum entropy, and decision tree prediction models.

7. The method of claim 1 wherein the one or more prediction models include any of a Naï

ve Bayes prediction model, logistics regression prediction model, and neural network prediction model.

8. A tangible machine-readable medium encoded with instructions, that when executed by one or more processors, cause the processor to carry out a process for predictively scheduling a patient for a medical event, the process comprising:

receiving historical patient-procedure data;

transforming the received historical patient-procedure data into a schema;

building one or more prediction models using the transformed patient-procedure data from the schema;

predictively scheduling a medical procedure for the patient, wherein the step of predictively scheduling the medical procedure further comprises;

processing a set of target patient procedure data in each of the plurality of prediction models and determining a score for each of the results of the processing step;

determining a majority of the scores from the plurality of prediction models agree by determining whether each score exceeds a predetermined threshold; and

predictively scheduling the medical appointment utilizing the plurality of prediction models that agree and the set of target patient-procedure data.

9. The machine-readable medium of claim 8, the process further comprising:

in response to determining new historical patient-procedure data has been received, updating the one or more prediction models.

10. The machine-readable medium of claim 8 wherein the step of predictively scheduling a medical procedure is preceded by:

receiving a new scheduling event request, including the target patient-procedure data.

11. The machine-readable medium of claim 10 wherein the target patient-procedure data is transformed to comply with the schema.

12. The machine-readable medium of claim 8 wherein the historical patient-procedure data comprises actual data from previously completed medical procedures, including at least one of procedure attributes, procedure durations, patient demographics, equipment used, and attending personnel.

13. The machine-readable medium of claim 8 wherein the one or more prediction models include any one of Naï

ve Bayes, logistics regression, neural network, maximum entropy, and decision tree prediction models.

14. The machine-readable medium of claim 8 wherein the one or more prediction models include a Naï

ve Bayes prediction model, logistics regression prediction model, and neural network prediction model.

15. A system for predictively scheduling a patient for a medical procedure, comprising:

a tangible storage medium including a set of executable code;

a processor wherein when the processor executes the set of executable code, the following are effectuated;

a learning module, wherein the learning module transforms received historical patient-procedure data into a schema, and builds one or more prediction models using the transformed patient-procedure data from the schema; and

a classifier module, wherein the classifier module predictively schedules the medical procedure for the patient, utilizing both target patient-procedure data and the one or more prediction models;

wherein the classifier module processes a set of target patient procedure data in each of the plurality of prediction models and determines a score for each of the results of the processing step, determines a majority of the scores from the plurality of prediction models agree by determining whether each score exceeds a predetermined threshold, and predictively schedules the medical appointment utilizing the plurality of prediction models that agree and the set of target patient procedure data.

16. The system of claim 15 wherein in response to receiving new historical patient-procedure, the learning module is further configured for updating the one or more prediction models.

17. The system of claim 15 wherein the one or more prediction models include any one of a Naï

ve Bayes prediction model, logistics regression prediction model, and neural network prediction model.

18. A method of predictively scheduling a patient for a medical appointment, comprising:

configuring a set of executable code in a tangible storage medium, wherein the set of executable code is executed by a processor, effectuating the following steps;

receiving historical data relating to the medical appointment;

transforming the received historical data into a schema;

building a plurality of prediction models using the transformed historical data from the schema;

processing a set of target patient procedure data in each of the plurality of prediction models and determining a score for each of the results of the processing step;

determining a majority of the scores from the plurality of prediction models agree by determining whether each score exceeds a predetermined threshold; and

predictively scheduling the medical appointment utilizing the plurality of prediction models that agree and the set of target patient-procedure data.

19. The method of claim 18 wherein the historical data comprises data from previously completed medical appointments, including at least one of medical procedure attributes, appointment durations, patient demographics, equipment used and attending personnel.

20. The method of claim 18 wherein the one or more prediction models include at least one of Naï

ve Bayes, logical regression, neuro network, maximum entropy, and decision tree prediction models.

21. The method of claim 18 wherein the steps of predictive scheduling the medical appointment is preceded by receiving a new scheduling event request, the new scheduling event request including target patient-procedure data for the medical appointment to be scheduled, wherein the medical appointment is predictively scheduled based upon the target patient-procedure data.

22. The method of claim 18 wherein the historical data includes actual data from previously completed medical appointments similar to the medical appointment being scheduled.