REAL-TIME PREDICTIVE COMPUTER PROGRAM, MODEL, AND METHOD

• US 20080097944A1
• Filed: 03/09/2007
• Published: 04/24/2008
• Est. Priority Date: 10/23/2006
• Status: Active Grant

• Current Assignee: Health Care Information Services, LLC
• Original Assignee: Health Care Information Services, LLC
• Inventors: McDannald, E.R., Kelly, Bruce
• Granted Patent: US 7,716,147 B2
• Time in Patent Office: Days
• US Class Current: 706/21
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

A method for predicting a future occurrence of an event involves obtaining a history of prior occurrences of the event. A plurality of variables is created that are associated with the event. Weights are assigned to each variable. An artificial neural network is accessed and trained with the history of past occurrences of the event by comparing an output of the artificial neural network to the past occurrence of the event. The weights are adjusted until the output corresponds to the past occurrence of the event.

Claims

1. A method of predicting a worker'"'"'s compensation injury, the method comprising the steps of:

obtaining a history of injuries that required worker'"'"'s compensation;

accessing an artificial neural network;

training the artificial neural network with variables selected from the group consisting of;

Barthel Scale- pre-event, on date of accident, every week for 16 week, 1 year followup,

VAS scale for pain (1-10) at each Barthel Scale evaluation,

types of industry the individual worked in,

age, height, weight of the individual prior to the injury,

general health of the individual prior to the injury,

date of injury,

type of injury,

treatments received for the injury and costs of treatments,

worker was hospitalized,

worker received surgery,

worker received physical therapy/occupational therapy/job retraining,

type and amount of medications worker received,

type and amount of home care worker received,

number of days worker not working,

was worker able to return to their job,

was worker assigned light duty work,

total cost of worker compensation injury, and

how the worker would rate their work environment; and

utilizing the trained artificial neural network to predict the occurrence of the next worker'"'"'s compensation injury.

2. The method of claim 1, wherein the method further includes assigning a weight to each variable.

3. The method of claim 2, wherein the method further includes adjusting the weights of the variables.

4. The method of claim 1, wherein the method further includes comparing an output of the network with a past occurrence of the worker'"'"'s compensation injury.