Method and system for selection of patients to receive a medical device

• US 8,751,261 B2
• Filed: 11/15/2011
• Issued: 06/10/2014
• Est. Priority Date: 11/15/2011
• Status: Active Grant

• Current Assignee: Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: Srinivasan, Soundararajan, Farhangfar, Alireza
• Primary Examiner(s): BURGESS, JOSEPH D
• Application Number:
  US13/296,788
• Publication Number:
  US 20130124224A1
• Time in Patent Office: 938 Days
• Field of Search: 705 2- 4
• US Class Current: 705/2
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

In one embodiment, a method for identifying patients to receive a medical device has been developed. The method includes retrieving first medical data associated with one patient from a database, identifying a probability that a medical device provides a medical benefit to the one patient that exceeds a cost associated with providing the medical device to the one patient with reference to the first medical data and a probabilistic model, the probabilistic model having a plurality of model parameters, each model parameter corresponding to one type of datum in the first medical data, and providing the medical device to the one patient in response to the identified probability exceeding a first predetermined threshold.

Claims

1. A method for selecting recipients of a medical device comprising:

providing first medical data associated with one patient from a database stored in a memory to a controller communicatively coupled to the memory;

identifying with the controller a probability that a medical device provides a medical benefit to the one patient that exceeds a cost associated with providing the medical device to the one patient with reference to the first medical data and a probabilistic model, the probabilistic model having a plurality of model parameters stored in the memory and provided to the controller, each model parameter corresponding to one type of datum in the first medical data;

identifying a confidence value corresponding to the identified probability with the controller, the confidence value being identified by;

identifying a difference between a first probability value generated by the probabilistic model using the first medical data and a first plurality of model parameters and a second probability value generated by the probabilistic model using the first medical data and a second plurality of model parameters with the controller;

identifying a first scaling factor of the first plurality of model parameters with reference to the probabilistic model and a plurality of predetermined training data with the controller;

identifying a second scaling factor of the second plurality of model parameters with reference to the probabilistic model and the plurality of predetermined training data with the controller; and

identifying the confidence value with reference to the identified difference, the first scaling factor, and the second scaling factor with the controller; and

generating with the controller and a user interface device that is communicatively coupled to the controller an output indicating the one patient is eligible to receive the medical device, the output being generated in response to the identified probability exceeding a first predetermined probability threshold value stored in the memory and the confidence value being below a second predetermined threshold stored in the memory.

2. The method of claim 1, further comprising:

transmitting with the controller data corresponding to the identified probability that the medical device provides the medical benefit to the one patient that exceeds the cost associated with providing the medical device to the one patient to a medical database via a data network.

3. The method of claim 1, the first medical data further comprising:

a first medical data subset corresponding to the one patient at a first time; and

a second medical data subset corresponding to the one patient at a second time, the second time being later than the first time, the probability being identified by the controller with reference to a difference between at least one datum in the first medical data subset and at least one corresponding datum in the second medical data subset.

4. The method of claim 1, the confidence value being an entropy value generated by the controller with reference to the classification probability.

5. The method of claim 1, further comprising:

storing programmed instructions in the memory corresponding to a logistic regression probabilistic model; and

identifying with the controller the probability that the medical device provides the medical benefit to the one patient that exceeds the cost associated with providing the medical device to the one patient with reference to the first medical data and the logistic regression model.

6. The method of claim 1 further comprising generating the plurality of model parameters with the controller and storing the generated plurality of model parameters in the memory with reference to medical data corresponding to a plurality of patients stored in the database, the medical data corresponding to the plurality of patients including a plurality of values corresponding to each datum in the first medical data.

7. The method of claim 1, the first medical data including a datum corresponding to at least one of an age, sex, height, weight, medications, previous medical procedure, and diagnosed medical condition of the patient.

8. The method of claim 1, the medical device being a device configured to provide additional medical data corresponding to the one patient to the database.

9. The method of claim 1 further comprising:

providing a plurality of medical data associated with a plurality of patients from the database in the memory to the controller;

identifying with the controller a plurality of probabilities that the medical device provides a medical benefit to each of the plurality of patients that exceeds a cost associated with providing the medical device to each of the plurality of patients with reference to the plurality of medical data and the probabilistic model; and

generating with the controller and the user interface device an output indicating each of a selected group of the plurality of the patients is eligible to receive one of a first number of the medical device, the controller and user interface device generating the output for the selected group of the plurality of patients having identified probabilities that are greater than identified probabilities of a remaining group of the plurality of patients.

10. A system for controlling distribution of medical devices to patients comprising:

a user interface device;

a memory configured to store;

a database containing medical data corresponding to a plurality of patients;

a plurality model parameters corresponding to a probabilistic model, each model parameter corresponding to one type of datum in the plurality of medical data; and

a plurality of stored program instructions; and

a controller operatively connected to the user interface device and the memory, the controller being configured to execute the stored program instructions to;

retrieve first medical data corresponding to one patient from the database;

identify a probability that a medical device provides a medical benefit to the one patient that exceeds a cost associated with providing the medical device to the one patient with reference to the first medical data and the probabilistic model having the plurality of model parameters;

identify a difference between a first probability value generated by the probabilistic model using the first medical data and a first plurality of model parameters and a second probability value generated by the probabilistic model using the first medical data and a second plurality of model parameters;

identify a first scaling factor of the first plurality of model parameters with reference to the probabilistic model and a plurality of predetermined training data;

identify a second scaling factor of the second plurality of model parameters with reference to the probabilistic model and the plurality of predetermined training data;

identify a confidence value corresponding to the identified probability with reference to the identified difference, the first scaling factor, and the second scaling factor; and

display an output via the user interface device to indicate provision of the medical device to the one patient in response to the identified probability exceeding a first predetermined threshold and being below a second predetermined threshold.

11. The system of claim 10, the controller being further configured to:

transmit data corresponding to the identified probability that the medical device provides the medical benefit to the one patient that exceeds the cost associated with providing the medical device to the one patient to a medical database via a data network.

12. The system of claim 10, the first medical data further comprising:

a first medical data subset corresponding to the one patient at a first time; and

a second medical data subset corresponding to the one patient at a second time, the second time being later than the first time, the controller being further configured to identify the probability with reference to a difference between at least one datum in the first medical data subset and at least one corresponding datum in the second medical data subset.

13. The system of claim 10, the confidence value being an entropy value generated with reference to the classification probability.

14. The system of claim 10, the probabilistic model being a logistic regression model.

15. The system of claim 10, the controller being further configured to generate the plurality of model parameters with reference to medical data corresponding to the plurality of patients stored in the database, the medical data corresponding to the plurality of patients including a plurality of values corresponding to each datum in the first medical data.

16. The system of claim 10, the first medical data including a datum corresponding to at least one of an age, sex, height, weight, medications, previous medical procedure, and diagnosed medical condition of the patient.

17. The system of claim 10, the medical device being a device configured to provide medical data corresponding to the one patient to the database.

18. The system of claim 10, the controller being further configured to:

retrieve a plurality of medical data associated with a plurality of patients from the database;

identify a plurality of probabilities that the medical device provides a medical benefit to each of the plurality of patients that exceeds a cost associated with providing the medical device to each of the plurality of patients with reference to the plurality of medical data and the probabilistic model; and

generate a list of identifiers corresponding to each of a selected group of the plurality of the patients via the user interface device, each patient in the selected group of patients being selected to receive one of a first number of the medical devices, the selected group of the plurality of patients having identified probabilities that are greater than identified probabilities of a remaining group of the plurality of patients.