Systems and methods for assessing whether medical procedures should be approved
A rules engine that allows constructing and processing rules within a software application using protocol driven processing. A machine learning algorithm may be used to assess requested procedures that are initially rejected. The machine learning algorithm may also be saved periodically or at the time of each assessment and accessed at a later time.
1. A system for assessing whether one or more medical procedures should be approved, comprising:
a computer memory having a non-transitory machine-readable medium comprising machine-executable code recorded thereon, said machine-executable code comprising instructions for:
entering in a first database table a first record wherein said first record represents a first rule and wherein said first record comprises a confidence threshold number;
entering in a second database table one or more records wherein each record represents a clinical criterion and wherein each record comprises a confidence value associated with the clinical criterion;
receiving a selection of a first set of one or more clinical criteria;
determining whether the sum of the confidence values associated with the first set of one or more clinical criteria exceed the confidence threshold number;
in response to the determination of whether the sum of the confidence values associated with the first set of one or more clinical criteria exceed the confidence threshold number, receiving medical data and processing the medical data and the first set of one or more clinical criteria using a first machine learning algorithm to generate a first output indicating whether a first medical procedure should be approved;
after generating the first output, saving a first state of the machine learning algorithm;
displaying on a computer screen an indication of whether the procedure is approved;
receiving a selection of a second set of one or more clinical criteria;
determining whether the sum of the confidence values associated with the second set of one or more clinical criteria exceed the confidence threshold number;
in response to the determination of whether the sum of the confidence values associated with the second set of one or more clinical criteria exceed the confidence threshold number, using the machine learning algorithm to generate a second output indicating whether a second medical procedure should be approved, wherein the machine learning algorithm is converted from the first state to a second state;
after generating the second output indicating whether the second medical procedure should be approved, saving the second state of the machine learning algorithm and retrieving the first state of the machine learning algorithm; and
after retrieving the first state of the machine learning algorithm, receiving a selection of a third set of one or more clinical criteria, determining whether the sum of the confidence values associated with the clinical criteria exceed the confidence threshold number, and using the machine learning algorithm in the second state to generate a third output indicating whether a second medical procedure should be approved.
2. The system of claim 1 , wherein the machine-executable code further comprises instructions for displaying on the computer screen one or more alternative procedures.
3. The system of claim 2 , wherein the medical data comprises one or more selected from the group consisting of a patient's age, a patient's gender, a patient's weight, a patient's height, and the number of times the procedure has been previously administered.
4. The system of claim 2 , wherein the machine learning algorithm is a neural network.
5. The system of claim 4 , wherein the medical data comprises one or more selected from the group consisting of a patient's age, a patient's gender, a patient's weight, a patient's height, and the number of times the procedure has been previously administered.
6. The system of claim 1 , wherein the medical data comprises one or more selected from the group consisting of a patient's age, a patient's gender, a patient's weight, a patient's height, and the number of times the procedure has been previously administered.
7. The system of claim 6 , wherein the machine learning algorithm is a neural network.
8. The system of claim 1 , wherein the machine learning algorithm is a neural network.
9. A method for assessing whether one or more medical procedures should be approved, comprising:
entering in a first database table a first record wherein said first record represents a first rule and wherein said first record comprises a confidence threshold number;
entering in a second database table one or more records wherein each record represents a clinical criterion and wherein each record comprises a confidence value associated with the clinical criterion;
receiving a selection of a first set of one or more clinical criteria;
determining whether the sum of the confidence values associated with the first set of one or more clinical criteria exceed the confidence threshold number;
in response to the determination of whether the sum of the confidence values associated with the first set of one or more clinical criteria exceed the confidence threshold number, receiving medical data and processing the medical data and the first set of one or more clinical criteria using a first machine learning algorithm to generate a first output indicating whether a first medical procedure should be approved;
after generating the first output, saving a first state of the machine learning algorithm;
displaying on a computer screen an indication of whether the procedure is approved;
receiving a selection of a second set of one or more clinical criteria;
determining whether the sum of the confidence values associated with the second set of one or more clinical criteria exceed the confidence threshold number;
in response to the determination of whether the sum of the confidence values associated with the second set of one or more clinical criteria exceed the confidence threshold number, using the machine learning algorithm to generate a second output indicating whether a second medical procedure should be approved, wherein the machine learning algorithm is converted from the first state to a second state;
after generating the second output indicating whether the second medical procedure should be approved, saving the second state of the machine learning algorithm and retrieving the first state of the machine learning algorithm; and
after retrieving the first state of the machine learning algorithm, receiving a selection of a third set of one or more clinical criteria, determining whether the sum of the confidence values associated with the clinical criteria exceed the confidence threshold number, and using the machine learning algorithm in the second state to generate a third output indicating whether a second medical procedure should be approved.
10. The method of claim 9 , further comprising displaying on the computer screen one or more alternative procedures.
11. The method of claim 10 , wherein the medical data comprises one or more selected from the group consisting of a patient's age, a patient's gender, a patient's weight, a patient's height, and the number of times the procedure has been previously administered.
12. The method of claim 10 , wherein the machine learning algorithm is a neural network.
13. The method of claim 12 , wherein the medical data comprises one or more selected from the group consisting of a patient's age, a patient's gender, a patient's weight, a patient's height, and the number of times the procedure has been previously administered.
14. The method of claim 9 , wherein the medical data comprises one or more selected from the group consisting of a patient's age, a patient's gender, a patient's weight, a patient's height, and the number of times the procedure has been previously administered.
15. The method of claim 14 , wherein the machine learning algorithm is a neural network.
16. The method of claim 9 , wherein the machine learning algorithm is a neural network.
17. A system for assessing whether one or more medical procedures should be approved, comprising:
a computer memory having a non-transitory machine-readable medium comprising machine-executable code recorded thereon, said machine-executable code comprising instructions for:
entering in a first database table a first record wherein said first record represents a first rule and wherein said first record comprises a confidence threshold number;
entering in a second database table one or more records wherein each record represents a clinical criterion and wherein each record comprises a confidence value associated with the clinical criterion;
receiving a selection of a first set of one or more clinical criteria;
determining whether the sum of the confidence values associated with the first set of one or more clinical criteria exceed the confidence threshold number;
in response to the determination of whether the sum of the confidence values associated with the first set of one or more clinical criteria exceed the confidence threshold number, receiving medical data and processing the medical data and the first set of one or more clinical criteria using a first machine learning algorithm to generate a first output indicating whether a first medical procedure should be approved;
after generating the first output, saving a first state of the machine learning algorithm;
displaying on a computer screen an indication of whether the procedure is approved;
receiving a selection of a second set of one or more clinical criteria;
determining whether the sum of the confidence values associated with the second set of one or more clinical criteria exceed the confidence threshold number;
in response to the determination of whether the sum of the confidence values associated with the second set of one or more clinical criteria exceed the confidence threshold number, using the machine learning algorithm to generate a second output indicating whether a second medical procedure should be approved, wherein the machine learning algorithm is converted from the first state to a second state;
after generating the second output, saving the second state of the machine learning algorithm and retrieving the first state of the machine learning algorithm;
receiving a selection of a third set of one or more clinical criteria;
determining whether the sum of the confidence values associated with the third set of one or more clinical criteria exceed the confidence threshold number;
in response to the determination of whether the sum of the confidence values associated with the third set of one or more clinical criteria exceed the confidence threshold number, using the machine learning algorithm to generate a third output indicating whether a third medical procedure should be approved, wherein the machine learning algorithm is converted from the second state to a third state;
after generating the third output, retrieving the first state of the machine learning algorithm.
18. The system of claim 17 , wherein the machine-executable code further comprises instructions for displaying on the computer screen one or more alternative procedures.
19. The system of claim 17 , wherein the medical data comprises one or more selected from the group consisting of a patient's age, a patient's gender, a patient's weight, a patient's height, and the number of times the procedure has been previously administered.
20. The system of claim 17 , wherein the machine learning algorithm is a neural network.