WO2000017799A1

WO2000017799A1 - Dynamic modeling and scoring risk assessment

Info

Publication number: WO2000017799A1
Application number: PCT/US1999/022019
Authority: WO
Inventors: Stephen J. Brown
Original assignee: Health Hero Network, Inc.
Priority date: 1998-09-23
Filing date: 1999-09-22
Publication date: 2000-03-30
Also published as: AU6259799A

Abstract

The invention provides for modeling and scoring risk-assessment and a set of insurance products derived therefrom. Risk indicators are determined at a selected time. A population is assessed at that time and afterward for those risk indicators and for consequences associated therewith. Population members are coupled to client devices for determining risk indicators and consequences. A server receives data from each client, and in response thereto and in conjunction with an expert operator, (1) reasesses weights assigned to the risk indicators, (2) determines new risk indicators, (3) determines new measures for determining risk indicators and consequences, and (4) presents treatment options to each population member. The server determines, in response to the data from each client, and possibly other data, a measure of risk for each indicated consequence or for a set of such consequences. The server provides this measure with regard to each population member, or with regard to population subsets. The expert operator uses this measure to determine either (1) an individual course of treatment, (2) a resource utilization review model, (3) a risk-assessment model, or (4) an insurance pricing model, for each individual population member or for selected population subsets. Information requested by the client, information determined and presented by the server, and responsive measurements, are adapted dynamically to changing population aspects or changing population membership, or of an external environment having relevance to the population.

Description

/

Title of the Invention

Dynamic Modeling and Scoring Risk Assessment

Background of the Invention

1. Field of the Invention

This invention relates to computer systems and data structures for modeling and

scoring risk assessment, such as insurance risk.

2. Related Art

In the insurance industry and in other fields in which risk is assessed (including

such diverse fields as medical treatment, financial modeling and portfolio management,

and environmental impact regulation), it is known to develop and use a risk-assessment

model of a population. The risk-assessment model provides a technique for determining

which population members are more subject or less subject to particular risks (or to an

aggregate of risks) than the norm for that population. For example, in life insurance

underwriting, it is known to evaluate past and present medical data so as to determine

what insurance premium the underwriter wishes to charge.

While these known methods generally achieve the goal of assessing risk for

particular individuals in comparison to a population norm, they have the drawback of

making a risk assessment that is fixed at a particular point in time. That is, these risk-

assessment models rely on static data, in particular (1) static data about the individual

population member, (2) static data about the population norm, and (3) static data about

risks associated or correlated with the data about the individual population member.

However, risk for individual population members depends not only on their present data,

but also on their future data, including both data about behavior and environment.

A first type of problem for the known art includes those individuals that have a

progressive disease or degenerative condition, in which the disease or condition progresses at a rate that is responsive to behavior or environment of the individual. F.or

such individuals, risk is more accurately evaluated as a function of behavior measured

over time and environment measured over time, rather than as a static value that is a

function only of present behavior and environment. For example, a first patient with

diabetes can proceed with relatively small risk if that first patient is aware of and active in

management of behavioral and environmental risk factors. In . contrast, an otherwise

identical second patient will have significantly greater risk if that second patient is either

unaware of, or unable or unwilling to take charge of, behavioral and environmental risk

^' factors.

Related to this first type of problem is the problem of determining trends for

individual risk-assessment. For example, an individual with a history of diabetes may

suffer a significant increase or decrease in effects thereof, due at least in part to that

patient's actions with regard to behavioral and environmental risk factors. Similarly to

the first type of problem, that individual will be rationally assessed a significantly greater

or lesser risk than originally, if the new facts were known to the underwriter. Such trends

may differ significantly from any trends that might have been discerned from past

medical history alone; such trends may also themselves involve genetic, environmental,

or behavioral components, or some combination thereof.

A second type of problem for the known art includes individuals whose risk-

assessment significantly changes due to the vicissitudes of their life trajectory. This can / include progression of a disease or condition, responsive at least in part to behavioral or

2 environmental factors. For a more striking example, an individual may suffer a

3 myocardial infarction, or become infected with an HIV variant. Similarly to the first type

4 of problem, that individual would be rationally assessed a significantly greater risk than

5 originally, if the new facts were known to the underwriter. Alternatively, an individual

6 may be successfully treated for a "curable" disease such as Hodgkin's disease or some

7 forms of cancer. Such vicissitudes of life trajectory may themselves involve genetic,

8 environmental, or behavioral components, or some combination thereof.

9

ιo A third type of problem for the known art includes individuals who significantly

// change their behavior or environment, particularly when those individuals pre susceptible

12 to the elements of their behavior or environment they change. For example, an individual

13 with diabetes can determine to alter their diet favorably or unfavorably. For a more

14 striking example, an individual may take up smoking or skydiving as habits. That

15 individual will become a significantly greater risk than the underwriter originally

16 assessed.

17

18 Moreover, new medical research may indicate risk factors that were not known at

19 the time risk for the individual was originally assessed. These could include past medical

20 information not known at the time to be important, tests available in the future for risk

21 factors not known at the time at all, or changes in the medical history of the individual

22 that place that individual in different risk factor categories. Such past medical / information or risk factors may themselves involve genetic, environmental, or behavioral

2 elements, or some combination thereof.

4 Accordingly, it would be advantageous to collect feedback from individual

5 population members, whether on a periodic or aperiodic basis, and whether prompted by

6 selected events or not. Such feedback would allow underwriters or other risk-assessment

7 or risk-management personnel to determine specific risk-related information about each

8 individual population member, and to adjust (such as to make more accurate or precise)

9 insurance models and risk-assessment models to fit the new data. Such feedback enables

w the advantage of providing information about the time-varying nature of individual

11 measures which can be used in the dynamic risk assessment model presented in the

12 present invention. For instance, a weight gain of 10 pounds per year, an increase in

13 diastolic blood pressure of 10 points per year, and a increase of cholesterol of 10 points

14 per year could be tracked over time and would yield health risk information.

15

16 To achieve this advantage, a first aspect of the invention is that feedback is

17 collected by a client-server system in which data is requested or required from population

18 members. A server device, responsive to a risk-assessment model, prompts a client

19 device supplied to population members to request information from population members,

20 in order to determine whether aggregate measures or individual measures of risk-

21 assessment remain in coherence with the model. The client device collects the data and

22 supplies it to the server device, which can, in response to dynamically collected data, / adjust the model, adjust risk assessments for selected population members (or groups

2 thereof), or determine further information to collect from population members.

4 Upon achieving this advantage, a second aspect of the invention is to provide a set

j of superior risk-assessment models and insurance models in response to the feedback.

6 These superior risk-assessment models and insurance models can include information

7 about the risk-related behavior, risk-related trends, or forward-looking risk-assessment of

8 selected individuals or selected subsets of the population. These superior risk-assessment

9 models and insurance models can be responsive to data-mining techniques described in

10 related patent applications, described below, hereby incorporated by reference as if fully

// set forth herein. These superior risk-assessment models can also incorporate known

12 scientific information regarding health risk or disease progression, such as well-

13 determined correlations of risk factors and disease incidence or progression from large

14 research studies, or well-known shape of 5-year survival curves for patients having

15 specific types of cancer.

16

17 Accordingly, it would also be advantageous to provide a set of techniques for

18 modeling and scoring risk-assessment and a set of insurance products derived therefrom,

19 using dynamic assessment of risk indicators and associated consequences for a

20 population. This advantage is achieved in an embodiment of the invention in which a

21 population (such as a population of medical patients) is assessed both at a selected time

22 and afterward for those risk indicators and for consequences associated therewith. A CT/US99/22019

7 client-server system provides dynamic data collection and analysis, dynamic risk

assessment in response to that data collection and analysis, and dynamic treatment

options and utilization review for each population member.

Summary of the Invention

The invention provides a set of techniques for modeling and scoring risk-

assessment and a set of insurance products derived therefrom. A set of risk indicators

(such as medical risk factors for individuals) is determined at a selected time. A

population (such as a population of medical patients) is assessed at the selected time and

afterward for those risk indicators and for consequences associated therewith. For

example, the population can be periodically assessed for correlation between smoking

and heart disease, for correlation between alcohol use and heart disease, and for

multivariate correlation of a plurality of such indicators and consequences.

In a preferred embodiment, selected population members are each coupled to

client devices for determining risk indicators and consequences. For example, where the

population is a set of medical patients, the client device can include a local device for

asking medical, psychological and life-style questions, and for measurement of medical

parameters, for each of those patients. A server device receives data from each client

device, and in response thereto, can (1) reassess weights assigned to the risk indicators,

(2) determine new significant risk indicators, (3) determine new significant measures for / determining risk indicators and consequences, and (4) present treatment options to each-

2 population member. The server device can perform these tasks in conjunction with an

3 operator, such as a skilled medical professional, risk-management assessor, or other

4 expert.

5

6 The server device can determine, in response to the data from each client device,

7 and possibly in response to other data (such as provided by the expert operator), a

8 measure of risk for each indicated consequence or for a set of such consequences. The

9 server device can provide this measure with regard to each population member, or with

10 regard to population subsets (selected either with regard to the known risk indicators or

// other indicators). The expert operator can use this measure to determine either (1) an

12 individual course of treatment, (2) a resource utilization review model, (3) a risk-

13 assessment model, or (4) an insurance pricing model, for each individual population

14 member or for selected population subsets.

15

16 In a preferred embodiment, information requested by the client device,

17 information determined and presented by the server device, and measurements

18 determined in response thereto, can be adapted dynamically to changing aspects or

19 changing membership of the population, or of an external environment having relevance

0 to the population. For example, medical treatment or risk-assessment models can be

1 dynamically adapted to an aging population or to biomedical advances with regard to

22 detection or treatment of medical conditions for members of that population. Brief Description of the Drawings

Figure la shows a block diagram of a system for data collection and interpretation

for a population. Figure lb shows details of the client device 110 shown in figure la.

Figure lc shows devices that may be connected to client device 110. Figure Id shows

details of the data review device.

Figure 2 shows a response diagram of consequences to risk indicators, for

statistical aggregates of the population, which can be selected in response to dynamic

data collection and analysis.

Figure 3 a shows a process flow diagram of a method for dynamic data collection

to be performed by the system; verification of model, updating a model, or creating a new

model, and re-evaluation of risk assessment. Figure 3b shows a process flow diagram of

the step of dynamic data collection. Figure 3c shows a process flow diagram of the step

of verification of the model. Figure 3d shows a process flow diagram of the step of

updating the existing model.

Figure 4a shows a process flow diagram of a method for dynamic data analysis to

be performed by the system. Figure 4b shows a process flow diagram for data mining. Figure 5 shows a response diagram of consequences to risk indicators, for

statistical aggregates of the population, with data collected from an individual at different

points of time also plotted.

Figure 6 shows a process flow diagram for a method of providing treatment

options and information to each patient based on the data provided to the server.

^' Detailed Description of the Preferred Embodiment

In the following description, a preferred embodiment of the invention is described

with regard to preferred process steps and data structures. Embodiments of the invention

can be implemented using general purpose processors or special purpose processors

operating under program control, or other circuits, adapted to particular process steps and

data structures described herein. Implementation of the process steps and data structures

described herein would not require undue experimentation or further invention.

Related Applications

Inventions described herein can be used in combination or conjunction with

inventions described in the following patent applications: • Application Serial No. 09/041,809 filed in the name of Stephen J. Brown, titled

"Phenoscope and Phenobase," assigned to the same assignee, attorney docket

number RYA-136 and related application serial no. 08/946,341.

• Application Serial No. 07/977,323, filed November 17, 1992 in the name of

Stephen J. Brown, and issued April 26, 1994 as Patent No. 5,307,263, titled

"Modular Microprocessor Based Health Monitoring System," assigned to the

same assignee; and subsequent Continuation-in-Part applications including

Application Serial No. 08/481,925 filed June 7, 1995 and Application Serial

No. 08/233,397 filed April 26, 1994, and a Continuation-in-Part application

filed August 19, 1998, serial number unknown.

• Application Serial No. 09/127,404 filed July 31, 1998 in the nanje of Stephen

J. Brown, titled "Modular Microprocessor Based Diagnosed Measurement

System for Psychological Conditions", and previous applications of which this

is a continuation including Application Serial No. 08/843,495, filed April 16,

1997, which is a continuation of Application Serial No. 08/682,385 filed July

15, 1996, which is a continuation of Application Serial No. 08/479,570 filed

June 7, 1995, which is a continuation of Application Serial No. 08/233,674

filed April 26, 1994.

• Application Serial No. 08/666,242 filed June 20, 1996, in the name of Stephen

J. Brown, titled "Health Management Process Control System", assigned to the

same assignee, attorney docket number RYA-114. • Application Serial No. 08/669,613 filed June 24, 1996, in the names of Stephe.n

J. Brown and Erik K. Jensen, titled "On-line Health Education and Feedback

System Using Motivational Driver Profile Coding and Automated Content

Fulfillment", attorney docket no. RYA-115.

• Application Serial No. 08/732,158 filed October 16, 1996, in the name of

Stephen J. Brown, titled "Multiple Patient Monitoring System for Proactive

Health Management", attorney docket no. RYA-1 16.

• Application Serial No. 08/814,293 filed March 10, 1997, in the name of

Stephen J. Brown, titled "On-Line Health Education Using Composites of

Entertainment and Personalized Health Information", attorney docket no.

RYA-1 19.

• Application Serial No. 08/847,009 filed April 30, 1997, in the name of Stephen

J. Brown, titled "Monitoring System for Remotely Querying Individuals",

attorney docket no. RYA-126.

• Application Serial No. 08/975,774 filed in the name of Stephen J. Brown, titled

"Multi-User Remote Health Monitoring System", attorney docket no. RYA-

131.

and

• Application Serial No. , Express Mail Mailing No. EI027453472US, filed

September 23, 1998, in the name of Stephen J. Brown, titled "Reducing Risk Using Behavioral and Financial Rewards," assigned to the same assignee,

attorney docket number HHN-004.

These applications are hereby incorporated by reference as if fully set forth herein.

System for Data Collection

for a population.

Referring to figure la, a system 100 includes a client device 1 10, a server device

120 including a program memory 122 and database of patient information 121, and a data

review element 130. These devices are connected via a communication channel, such as

a communication network as in known in the art and more fully described in the

Phenoscope and Phenobase patent (U.S. 09/041,809) and related patent application serial

no. 08/946,341 and other patents and patent applications previously incorporated by

reference.

Referring to figure lb, the client device 1 10 is disposed locally to a patient 1 11,

and includes an output element 112 for presenting information to the patient 1 1 1, and an

input element 113 for entering information from the patient 111. As used herein,

"locally" refers to a logical relationship to the patient 11 1, and does not have any

necessary implication with regard to actual physical position. In a preferred embodiment, / the client device 1 10 is relatively small or compact, and can be disposed on a night table

2 or otherwise near the patient 1 11.

4 The output element 1 12 includes a display screen 1 14, on which questions and

5 suggested answers can be displayed for the patient 1 11, so as to facilitate information

6 entry, or on which instructions can be displayed for the patient 1 1 1, so as to instruct the

7 patient 111. The output element 1 12 can also include a speaker 115, so as to present

8 information in conjunction with or in alternative to the display screen 1 14. The output

9 element 1 12 can also include a bell or other sound element, or a bright light 1 19 or a flag,

10 so as to alert the patient 111 that the client device 110 has questions or information for

// the patient 11 1.

12

13 The input element 1 13 includes a plurality of buttons 116A-D for entering

14 information, preferably such as described in the patent applications referenced and

15 incorporated by reference above.

16

17 The input element 1 13 can also include one or more data ports 1 17A-D for

18 entering information from other devices. Referring to figure 1 c, such other devices 1 18

19 can include a medical measurement device, such as a blood glucose meter or a blood

20 pressure monitor. Such other devices i 18 can include a dispensing device for

21 medication.

22 Such other devices 118 can also include a general purpose or special purpose

client workstation, such as a personal computer or a hand-held digital calendar.

The server device 120 is disposed logically remotely from the patient 111, and

includes a database 121 of information about the patient 111 and about other patients in a

related population thereof. As used herein, "remotely" refers to a logical relationship to

the patient 111, and does not have any necessary implication with regard to actual

physical position.

The server 120 and patient profile database 121 are preferably accessible by means

of a standard network connection such as a world wide web connection. Server 120 and

database 121 may comprise single stand-alone computers or multiple computers

distributed throughout a network.

Referring to figure la and figure Id, the data review element 130 is disposed

logically remotely from the patient 111, and includes an interface 131 disposed for use by

an operator 132. The operator 132 can comprise medical personnel, a device operated by

medical personnel, or a similar device, capable of interacting with the interface 131 so as

to receive information from the data review element 130 and possibly to enter

information into the data review element 130. Information entered into the data review element 130 can be entered for ultimate transmission to the server device 120 or to the

client device 110.

The data review element 130 is preferably a personal computer, remote terminal,

web TV unit, Palm Pilot unit, interactive voice response system, or any other

communication technique. The data review element functions as a remote interface for

entering in server 120 or client device 110 messages and queries to be communicated to

the individuals.

Other and further information regarding the system 100 is shown in the following

pending patent applications and in other patent applications referenced above:

• Application Serial No. 09/041/809, filed in the name of Stephen J. Brown,

titled "Phenoscope and Phenobase," assigned to the same assignee, attorney

docket number RYA-136 and related application serial no. 08/946,341.

and

• Application Serial No. , Express Mail Mailing No. EI027453472US,

filed September 23, 1998, in the name of Stephen J. Brown, titled "Reducing

Risk Using Behavioral and Financial Rewards," assigned to the same assignee,

attorney docket number HHN-004.

These applications are hereby incorporated by reference as if fully set forth herein. / Aggregate Responses to Risk Indicators

3 Figure 2 shows a response diagram 200a of consequences to risk indicators, for

4 statistical aggregates of the population, which can be selected in response to dynamic

5 data collection and analysis. It is to be noted that figure 2 shows curves that are collapsed

6 to 2-dimεnsions, in a preferred embodiment the curves are N-dimensional, with N>2.

7

8 A diagram 200a includes a first axis X 201 and a second axis Y 202. The diagram

9 shows a first response curve R0 210 showing a normal trajectory for vital function and

ιo life expectancy of an individual or subpopulation of the population. The first axis X 201

u indicates a relative time, as measured toward a right side of the diagram. The scale of the

12 first axis X 201 is a relative time whose initial left hand point may be undetermined. As

13 to a first response curve R0 210, the second axis Y 202 represents a measure of vital

14 function and life expectancy.

15

16 A diagram 200a also shows a second response curve SO 220 showing a normal

17 trajectory for a measure of expected medical expense or risk for an individual or

18 subpopulation of the population. The first axis X 201 indicates a relative time as for a

19 first response curve R0 210. As to a second response curve SO 220, the second axis Y

20 202 shows increasing expense or risk as measured toward the top of the diagram.

21 In the first response curve R0 210, the normal trajectory for vital function and life

expectancy for a typical individual in the population shows that as time progresses,

vitality and life expectancy are expected to decrease. This general concept is known in

the art of actuaries. It is to be noted that the shape shown by the first response curve R0

210 is an example shape; for instance, it is known that for certain curable cancers, risk

increases, then levels off after a certain length of time such as a 5-year survival rate, then

later in life risk increases due to other causes.

The first response curve R0 210 includes a number of points with error bars 211

about the response curve R0 210. All of the points 211 are at an identical value, V0, of

the second axis Y 202, with identical error bars. Any one of the points represents a single

measurement of vitality taken for an individual. Given any single measurement of

vitality, it is difficult to determine where along the second axis X 201, that is, where

along the trajectory the individual is. Of particular interest is how close to a rapid decline

in vitality or increase in risk the individual is. The points 211 show the several places

along the curve where the individual might be placed, based on this single measurement

of vitality. Because the response curve R0 210 is slowly varying through much of the

time, that is, the values of vitality and life expectancy clustering in a selected region of

the second axis Y 202, shown by the bracket 203, and due to margins of error in both the

measurement as well as the response curve, there are several positions along the curve

where an individual with a specific measurement might be; these several positions are

shown by points 21 1. By contrast, if measurements are taken for an individual at more than one point in

time, greater information is present, and in particular trends may be discerned which

yield more information about where on the curve an individual is. This ability to discern

trends is greater when curves in N-dimensions are considered. For instance, an

individual whose excess weight has slowly climbed in conjunction with slowly increasing

cholesterol, blood pressure, stress levels and family medical history would be placed in a

greater risk category although the individual measures of, for instance, cholesterol, might

be within a normal range.

Similarly, in the second response curve SO 220, the normal trajectory for expected

medical expense and risk for that typical individual shows that as time progresses,

expected medical expense and risk are expected to increase. This general concept is also

known in the art of actuaries. It is to be noted that the shape shown by the second

response curve RO 220 is an example shape; for instance, upon diagnosis of a disease the

expense may climb, but if the patient is cured the expense will level off.

Similarly, the second response curve SO 220 includes a number of points 221 on

the response curve SO 220, showing possible places that an individual in the population

with measurement of expense or risk, with value E0, might be. Because most of the

values of response curve SO 220 cluster in a selected region of the second axis Y 202

shown by the bracket 204, it is difficult to know where along curve SO 220 an individual / with measurement E0 should be placed. This is due to both possible error in

2 measurement of E0 as well as uncertainty in the exact "true" position and shape of curve

3 SO 220. As for curve RO 210, measurements of expense or risk taken over time will yield

4 useful information about where on the curve SO 220 an individual is.

5

6 When subsets of the population are selected in response to specific risk factors, the

7 statistical aggregates of the population can differ substantially from the aggregate

8 response curves R0 210 and SO 220 for the entire population. The diagram 200a shows

9 response curves Rla 212 and Rib 213 showing a normal life trajectory for vital function

10 and life expectancy of an "average" individual in the population, depending on whether

// that individual is associated with a selected risk factor α. As with regard to the aggregate

12 for the entire population, it is difficult to determine from a specific single measurement

13 just where on either response curve Rla 212 or Rib 213 the individual should be

14 assessed. Depending on whether the value of α is known for an individual, it may also be

15 difficult to know whether the individual should be placed on response curve Rla 212 or

16 Rib 213. Measurements of several risk indicators taken over time may yield information

17 on whether a specific individual should be placed in category Rla 213 or the higher risk

18 category Rib 212. The general concept of using time-dependent information to

19 determine risk along is also illustrated in Figure 5.

0 The client device 1 10 determines information from which the server device 120 or

the data review element 130 can analyze the time varying nature of data. The server

device 120 or the data review element 130 can therefore determine both of the following:

• (1) just where on either response curve Rla 212 or Rib 213 the individual

should be assessed; and

• (2) whether the individual should be assessed on the response curve Rla 212 or

the response curve Rl b 213.

It is to be noted that the above analysis has been condensed to 2-dimensions for

convenience in presentation, with a single measurement along a single X-axis or Y-axis.

In a preferred embodiment, a measurement would have many attributes, i.e. the model

would have N-dimensions, and more sophisticated techniques for analyzing trends and

achieving objectives are used.

If the data for the population is not known for all individuals in the population or

subpopulation of interest, the server device 120 transmits a new set of information-

gathering instructions (such as questions and suggested answers) to the client device 1 10,

so as to measure that information individually for each patient 111. / Dynamic Modeling.and Risk Evaluation

2 Figure 3a shows a process flow diagram 300a for a method with steps of

3 dynamically collecting information 310, choosing to verify or update the model or to

4 create new model 320, verifying 350 or updating 330 the risk assessment model or

J creating a new model 340, deciding whether to re-evaluate risk 360 and re-evaluating risk

6 based on updated information and current model 370.

7

8 Dynamic Data Collection for Population

9 Figure 3b shows a process flow diagram 300b of a method for dynamic data

w collection to be performed by the system. This data collection may be done periodically

11 or aperiodically, upon a triggering event or decision by the expert operator. The

12 population or subpopulation from which to collect data is selected 380. The selection

13 criteria may be based on preset values or may be set by the expert operator. The set of

14 risk indicators or other information to be collected is selected 382, based either on preset

15 values or decision by the expert operator. The individuals in the subpopulation of interest

16 are queried 384 as to the information of interest and the database is updated 386. The

17 pre-query steps need not be done in the order indicated.

18

19 Verification of Existing Model and Update of Model

20

21 Figure 3c shows a process flow diagram 300c of a method by which the updated

22 data can be analyzed to determine whether the existing model is consistent with the updated data; that .is, to verify that the data conforms to the model within acceptable

variation or error. This is accomplished by putting the updated data into categories 390,

determining the updating measures of life vitality or costs 392, determining the values

predicted by the model 394, comparing the updated measures of life vitality or costs

against those predicted by the model 396, and determining whether the comparison is

acceptable 397. If the predicted value is within an acceptable distance from the updated

values based on well known measures such as statistical error, then the model need not be

adjusted. The expert operator may also visually determine whether the updated data and

existing model show an acceptable relationship to each other.

Figure 3d shows a process flow diagram 300d of a method for updating the

existing risk model in response to updated information. By updating, it is meant that no

new risk indicators are added, and no new external constraints on the model are added.

The risk model to be adjusted may be for the aggregate population or for various

subpopulations. The updated information for the subpopulation is categorized 398

according to profile information into one or more existing categories. The subpopulation

is categorized according to one or more existing measure of life vitality or medical

expense. Statistical analyses as described below or in other patents or patent applications

previously incorporated by reference or as known in the art of statistics are applied to

determine updated values for model parameters such as weights to give each factor 399. Re-evaluating Risk Assessment based on updated information

As shown in figure 3 a, a current model can be determined based on updated

information. Once a current model is determined, which may include simply using the

already existing model, individual or subpopulation risk assessment may be reevaluated

in response to one or more pieces of updated information, as desired by the expert

operator or as a preprogrammed operation.

Dynamic Data Analysis for Population

Figure 4a shows a process flow diagram 400a of a method for dynamic data

analysis ("data mining") to be performed by the system. The updated database can be

mined to create a new model that may include reassessment of weights assigned to the

risk indicators, addition of new significant risk indicators, or determination of new

significant measures for determining risk indicators and consequences. Applied

examples of data mining and additional explanation are shown in the related application

09/041,809 and other applications referenced above.

Figure 4b shows a process flow diagram of a method of using the statistical

method of calculating correlations on subpopulations, following the steps of: (1) choose a

risk factor 450; (2) divide the risk pool into two groups based on outcome 460; (3) search

all other data for correlation to high versus low risk 470; (3) create a new risk factor

based on this correlation 480. The new risk factor may be a discrete piece of data that was asked of the client but was not previously known to be a significant predictor, or it

may be a new factor that is generated by combining other pieces of data. Figure 4b is a

process flow diagram of the above steps.

In addition to data mined from the database, in creating a new model, scientific

information well known in the literature may supplement the data.. For instance,

scientific information regarding certain well studied correlations be considered such as

known correlations of time since quitting smoking and various health conditions, known

^" information regarding the shape of life expectancy curves for certain types of cancer

patients, or recent information regarding efficacy of new forms of treatment for diseases

such as recent significant improvements in treatment of AIDS.

Statistical analyses are known in the art of statistics, and include correlation

analyses, multivariate regressions, constrained multivariate regressions, or variance

analyses, may also be run on the data to reveal statistical relationships among the various

information or measures of life vitality or medical expense in order to improve the

predictive power of a model, although in a preferred embodiment data mining is done as

presented in the preceding paragraphs.

Modeling and Scoring Risk Assessment, Insurance Pricing Modeling risk is performed by assigning risk to individual in response to risk

factors identified for that individual, and such modeling may be done for the population

or for a subpopulation. There are many techniques for modeling, such as linearly risk

scoring by assigning a number to each risk factor and adding up each number to

determine a total risk score, non-linearly assessing risk by combining risk factors non-

linearly to determine risk which may be achieved by neural network techniques which are

known in the art of neural networks, or other techniques.

Figure 5 shows a diagram 500 including a first axis X 502 and a second axis Y

503 and a response curve R0 501, similar to that shown in figure 2. It shows several

measurements of vitality with error bars 511 of an individual taken at several different

points in time. Each measurement of vitality is taken at a later time from left to right.

Information about the time varying nature of the measurements, or the trends, can

improve the ability to predict future vitality, including imminent sharp declines in

vitality, as can been seen by visually examining the data over time or by using

sophisticated statistical techniques to examine the data and trends in the data over N-

dimensions.

Insurance pricing may be achieved from advantages in risk assessment. It is

known in the art of actuarial analysis to assign price in response to risk. Providing treatment options and information to each population member

Figure 6 is a process flow diagram 600 showing a method for providing treatment

options and information to each member based on the information provided. Upon

receiving information about the patient from the client 610, the server or expert operator

may identify a risk group 620 and identify an appropriate medical protocol 630, the

server may present one or more responses to the patient 640, including treatment options,

advice or merely health information that would be useful to the patient, and the client

' device may be configured to use an appropriate medical protocol in interacting with the

patient 650. It is known in the art of medicine that membership in a risk group may

indicate appropriate treatment. This may be done from an automated, preset set of

responses to individual queries made to the patient, on an aggregate of preset responses to

queries, or by an expert operator.

Alternative Embodiments

Although preferred embodiments are disclosed herein, many variations are

possible which remain within the concept, scope, and spirit of the invention, and these

variations would become clear to those skilled in the art after perusal of this application.

Claims

1. A method for assessing risk for selected individuals in a population, said method

including steps for

determining, at a first time, a first set of risk indicators for said

selected individuals;

collecting, at a second time after said first time, information about

said selected individuals; determining, at said second time, an additional risk indicator not in

said first set, in response to said information;

assessing risk for said selected individuals in response to said

additional risk indicators.

2. A method for assessing risk for selected individuals in a population, said method

including steps for

determining, at a first time, a set of risk indicators for said selected

individuals;

collecting, at a second time after said first time, information about

said selected individuals;

adjusting, at said second time, at least one of said risk indicators in

response to said information; assessing risk for said selected individuals in response to said

adjusted risk indicators.

3. A method as in claim 2, wherein said risk indicators include genetic risk

indicators, medical risk indicators, environmental risk indicators, or behavioral risk

indicators.

4. A method as in claim 2, wherein said steps for collecting include steps for

collecting, at said second time, information for said selected individuals about a set of

consequences associated with said risk indicators.

5. A method as in claim 2, including steps for determining a statistical

measure of relation between at least one said risk indicator and said information about

said selected individuals.

6. A method as in claim 2, including steps for determining a statistical

measure of relation between at least two said risk indicators and said information about

said selected individuals.

1. A method as in claim 2, wherein said steps for collecting include steps for

providing a client device for at least one of said selected individuals; applying a measurement device to said one selected individual at

said client device;

coupling said client device to a server device; and

transmitting a result of said steps for applying to said server device.

8. A method as in claim 2, wherein said steps for collecting include steps for

providing a client device for at least one of said selected individuals;

displaying questions at said client device; and

receiving answers to said questions from said at least one selected

individual;

9. A method as in claim 8, wherein said steps for displaying include steps for

receiving said questions from a server device coupled to said client

device;

timing said steps for displaying in response to a signal from said

server device; and

transmitting said answers to said server device.

10. A risk- assessment model, said model including

a set of risk indicators for selected individuals in a population;

a first set of values associated, at a first time, with each

corresponding risk indicator; a set of information associated, at a second time after said first time,

with said selected individuals;

a second set of values associated, at said second time, with each said

corresponding risk indicator, said second set of values being determined in

response to said set of information;

a risk-assessment, determined in response to said second set of

values, for said selected individuals.

11. A financial product including

a set of risk indicators for selected individuals in a population;

a first set of values associated, at a first time, with each

corresponding risk indicator;

a set of information associated, at a second time after said first time,

with said selected individuals;

a second set of values associated, at said second time, with each said

corresponding risk indicator, said second set of values being determined in

response to said set of information;

a pricing value, determined in response to said second set of values,

for said selected individuals.

12. A financial product as in claim 11 , wherein said pricing value is an insurance premium.