Computerized medical modeling of group life insurance using medical claims data

• US 20070021987A1
• Filed: 07/21/2006
• Published: 01/25/2007
• Est. Priority Date: 07/21/2005
• Status: Active Grant

• Current Assignee: Trurisk LLC
• Original Assignee: Trurisk LLC
• Inventors: Blumberg, Mark, Binns, Gregory
• Granted Patent: US 7,555,438 B2
• Time in Patent Office: Days
• US Class Current: 705/4
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

A method of model development for use in underwriting group life insurance for a policy period includes collecting medical claims data for the group to be underwritten, where each medical claim being related to a particular employee of the group. Morbidity categories are provided that categorize the medical claims in the medical claims data. A conditional probability model is developed and applied to the morbidity categories for each employee in the group using his medical claims, thereby calculating the expected conditional probability for each employee dying during the policy period. For each employee, an estimate of the expected life claim cost is estimated using an index of the life coverage to salary. Combining the expected conditional probability for each employee dying during the policy period with the estimate of the expected claim cost of death gives an estimate of the group'"'"'s total life exposure.

Claims

1. A method of developing a model to estimate life insurance exposure for a group of individuals to be underwritten for a coverage period comprising:

providing medical claim data comprising a plurality of medical claims made by a first model population having at least a respective plurality of first model population members;

providing life insurance claim data comprising a plurality of life insurance claims made by a second model population having at least a respective plurality of second model population members, which optionally may partially or wholly overlap with the first model population;

providing a clinical medical condition classification system that assigns corresponding medical condition causes to life insurance claims based on medical condition information included in life insurance claims;

applying the clinical medical condition classification system to the life insurance claim data for the second model population to generate a plurality of life insurance claims classified by medical condition;

categorizing the life insurance claims classified by medical condition, where each morbidity category comprises one or more medical conditions, to form a plurality of morbidity categories of life insurance claims;

calculating, for each of the morbidity categories of life insurance claims classified by medical condition, the proportion of life insurance claims for each morbidity category;

applying the clinical medical condition classification system to the medical claim data for the first model population to generate a plurality of medical claims classified by medical condition;

categorizing the medical claims classified by medical condition to form a plurality of morbidity categories of medical claims classified by medical condition;

calculating, for each of the morbidity categories of medical claims classified by medical condition, the proportion of medical claims arising for each of the morbidity categories;

calculating, for each of the morbidity categories, a probability of having a life claim during the coverage period using at least one conditional probability, the conditional probability being based on at least the proportion of life insurance claims and the proportion of medical claims for each of the morbidity categories; and

combining the probability of having a life claim given a morbidity category with the expected cost of the life claim to calculate the expected life exposure for the morbidity category.

2. A method of estimating life insurance exposure for a group of individuals to be underwritten for a coverage period comprising:

calculating, for each of the group of individuals, a measure of the expected exposure comprising the application of a model developed according to claim 1;

summing, across the group of individuals and their associated morbidity groupings, to obtain the measure of expected future exposure for the group.

3. The method of claim 1, wherein calculating the expected dollar amount of the life insurance claim is done by multiplying the amount of coverage in a time period by the measure of expected probability.

4. The method of claim 2, further comprising adjusting the measure of the expected exposure using net present valuation methods.

5. The method of claim 1, wherein each medical claim has information about at least one medical condition, and the medical eligibility database has information on the age and gender of each of the first plurality of individuals.

6. The method of claim 5, wherein the life insurance claims and medical claims are grouped into age by gender strata by each medical condition in the clinical classification system and the age by gender by clinical condition categories are used to define strata of expected exposure.

7. The method of claim 5, wherein the total expected exposure is calculated using the method of claim 1 for a block of medical claims and it is set to equal the total expected exposure for the plurality of individuals in the associated medical eligibility file using standard actuarial techniques that calculate the exposure based upon the eligible individuals'"'"' age by gender using standard actuarial tables that provide the expected frequency of claims multiplied by the expected exposure of that claim given the individuals'"'"' age and gender, thereby adjusting the estimate of the expected future exposure up or down for each clinical condition in that age by gender stratum so the sum of the standard actuarial estimates for the individuals in the eligibility file equals the clinically based expected future exposure for the individuals with medical claims and were included in the same eligibility file.

8. The method of claim 1, wherein for each individual with multiple medical claims the are adjusted for overlapping probabilities of death arising from the conditions indicated by the medical claims.

9. The method of claim 1, wherein the conditional probability is calculated using Bayes Theorem or other forms of Bayesian probability calculations.