System and method using a predictive model for nurse intervention program decisions

• US 8,521,555 B2
• Filed: 12/09/2009
• Issued: 08/27/2013
• Est. Priority Date: 12/09/2009
• Status: Expired due to Fees

• Current Assignee: Hartford Fire Insurance Company (The Hartford Financial Services Group, Inc.)
• Original Assignee: Hartford Fire Insurance Company (The Hartford Financial Services Group, Inc.)
• Inventors: Adams, Jonathan Kaleb, Gawel, Ryan A., Pagano, Joseph D.
• Primary Examiner(s): Fuelling, Michael
• Application Number:
  US12/634,046
• Publication Number:
  US 20110137672A1
• Time in Patent Office: 1,357 Days
• Field of Search: 705 2- 4
• US Class Current: 705/2
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/045 Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/1057 Benefits or employee welfare, e.g. insurance, holiday or retirement packages
• 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 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

According to some embodiments, historical claim data may be stored in a computer storage unit. The historical claim data may be used to train and verify a predictive model, the predictive model being associated with an evaluation of claim transactions to determine whether to refer each claim transactions to a nurse intervention program. Data for current claim transactions may be processed, and the trained and verified predictive model may be applied to the data for the current claim transactions to generate a respective output for each of the current claim transactions. Some of the current claim transactions may be selectively routed to a case management center associated with the nurse intervention program based on the outputs generated by the predictive model.

Claims

1. A computer system for facilitating provisioning of a nurse intervention program, comprising:

a data storage module for receiving, storing, and providing access to data related to historical insurance claim information, including historical injury information and historical insurance claim result information, and to current insurance claim transactions, including current insurance claim transaction injury information;

a predictive model component, coupled to the data storage module, for determining whether to identify one of said current insurance claim transactions for referral to the nurse intervention program;

a computer processor for executing programmed instructions and for storing and retrieving said data related to current insurance claim transactions;

a program memory, coupled to the computer processor, for storing program instruction steps for execution by the computer processor;

a model training component, coupled to the computer processor, for (i) automatically training the predictive model component based on a first subset of the data related to the historical insurance claim information, including both historical injury information and historical insurance claim result information and (ii) automatically verifying the trained predictive model component based on a second subset of the data related to the historical insurance claim information, different than the first subset, in accordance with program instructions stored in the program memory and executed by the computer processor, thereby providing a trained and verified predictive model component;

an output device, coupled to the computer processor, for outputting an output indicative of whether said one of said current insurance claim transactions should be referred to the nurse intervention program, wherein the computer processor generates the output in accordance with program instructions in the program memory and executed by the computer processor, said output generated in response to a notice of injury received in connection with said one of said current insurance claim transaction and being based on an application of data for said one of said current insurance claim transactions to the trained and verified predictive model component; and

a routing module for directing workflow based on the output from the output device.

2. The computer system of claim 1, wherein different current insurance claim transactions are associated with different accounts, and said generation of said output is further based on the account associated with the current insurance claim transaction.

3. The computer system of claim 1, wherein the data stored in the data storage module includes both determinate and indeterminate data.

4. The computer system of claim 3, wherein the indeterminate data includes narrative text notes.

5. The computer system of claim 4, wherein the narrative text notes are associated with at least one of:

(i) a prior injury, or (ii) co-morbidity information.

6. The computer system of claim 5, wherein the narrative text notes are associated with at least one of:

(i) alcohol related co-morbidity information, (ii) drug related co-morbidity information, (iii) tobacco related co-morbidity information, (iv) arthritis related co-morbidity information, (v) diabetes related co-morbidity information, or (vi) obesity related co-morbidity information.

7. The computer system of claim 1, wherein the routing module routes said one of the current insurance claim transactions to the nurse intervention program based on the output from the output device.

8. The computer system of claim 1, wherein the routing module routes the current insurance claim transaction to a case management center associated with the nurse intervention program.

9. The computer system of claim 1, wherein the insurance claim transactions are worker'"'"'s compensation claims.

10. The computer system of claim 1, wherein the insurance claim transactions are bodily injury claims.

11. The computer system of claim 1, wherein said generation of said output is performed after a first time period based on a predicted ultimate insurance claim severity and is re-performed after a second time period based on a re-predicted ultimate insurance claim severity, the second time period being different than the first time period.

12. The computer system of claim 1, wherein said generation of said output is based on at least one of:

(i) demographic information, (ii) injury details, (iii) accident information, (iv) employment information, or (v) financial information.

13. The computer system of claim 1, wherein said generation of said output is based on at least one of:

(i) a part of body injured, (ii) a nature of injury, (iii) a claimant age, (iv) an industry or occupation, (v) a medical paid or reserves amount, (vi) an indemnity paid or reserves amount, (vii) a previously noted injury, (viii) a presence of a co-morbidity, (ix) a claim complexity, (x) an injury matrix, or (xi) a key factor.

14. A computer-implemented method of managing nurse intervention program decisions, the method comprising:

storing, in a computer storage unit, historical claim data, including historical injury information and historical insurance claim result information;

using a first subset of the historical claim data, by a computer processor, to develop a predictive model having a plurality of historical claim data inputs and variables, developing the predictive model including;

performing data cleansing to eliminate one or more data inputs in the predictive model;

performing data reduction to reduce the number of variables in the predictive model; and

performing data transformations to normalize variables in the predictive model,

the predictive model for evaluating claim transactions to determine whether to refer the claim transactions to a nurse intervention program;

using a second subset of the historical claim data, different than the first subset, to verify the developed predictive model;

automatically applying, by the computer processor, the verified predictive model to the data for the current claim transactions to generate a respective output for each of the current claim transactions, said generation being automatically performed for a current insurance claim both after a first time period and a second time period, the second time period being different than the first time period; and

selectively routing, by the computer processor, ones of the current claim transactions to a case management center associated with the nurse intervention program based on the outputs generated by the predictive model.