Method for identifying at risk patients diagnosed with congestive heart failure

• US 5,976,082 A
• Filed: 01/29/1997
• Issued: 11/02/1999
• Est. Priority Date: 06/17/1996
• Status: Expired due to Fees

• Current Assignee: Smithkline Beecham Corporation (Smithkline Beecham PLC)
• Original Assignee: Smithkline Beecham Corporation (Smithkline Beecham PLC)
• Inventors: Friedman, Felix, Wong, Bruce J. O.
• Primary Examiner(s): GILBERT, SAMUEL G
• Application Number:
  US08/790,690
• Time in Patent Office: 1,007 Days
• Field of Search: 600/300, 600/301, 128/920-924
• US Class Current: 600/300
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

A computer-implemented technique, including database processing, is used to identify at risk congestive heart failure patients where information about patients exists in a claims database. The technique includes processing the patient information in the claims database to find and extract claims information for a group of congestive heart failure patients. Next, using the extracted information, a set of events, relevant to congestive heart failure, is defined. Next, the extracted information and set of events are processed to create event level information which is organized with respect to events rather than claims. A time window is defined to provide a timeframe from which to judge whether events should be considered in subsequent processing; and, a set of variables is defined as being potential predictors of adverse health outcomes. Subsequently, the event level information, using the time window and the set of variables, is processed to generate an analysis file. Statistical analysis, such as logistic regression, is performed on the analysis file to generate a prediction model where the prediction model is a function of a subset of the set of variables. Finally, the prediction model is applied to the same or another claims database to identify and output at risk patients, diagnosed with congestive heart failure, likely to have adverse health outcomes.

Claims

1. A computer-implemented method for identifying at risk patients diagnosed with congestive heart failure, information about patients existing in a claims database, said method comprising the steps of:

processing, based on predetermined criteria, the patient information in the claims database to extract claims information for a group of congestive heart failure patients;

defining, using the information available in the claims database, a set of events relevant to congestive heart failure;

converting data representing the extracted claims information and the defined events into files containing event level information;

defining a time window to provide a timeframe from which to judge whether events should be considered in subsequent processing;

defining a set of variables as potential predictors;

processing the event level information, using the time window and the set of variables, to generate an analysis file; and

performing statistical analysis on the analysis file to generate a prediction model for use in identifying at risk patients diagnosed with congestive heart failure, said prediction model being a function of a subset of the set of variables; and

applying the prediction model to current data in the claims database to identify at risk patients for CHF.

2. The computer-implemented method of claim 1, wherein the step of processing extracts patients having been diagnosed with congestive heart failure or prescribed an anti-CHF drug.

3. The computer-implemented method of claim 1, wherein the step of defining a set of variables includes defining both dependent and independent variables and a hospital (HL) indicator is defined as a dependent variable, where independent variables are representative of predictors and the dependent variable is represenative of a adverse health outcome.

4. The computer-implemented method of claim 1, wherein the step of defining a set of variables includes defining both dependent and independent variables and a high cost indicator is defined as a dependent variable, where independent variables are representative of predictors and the dependent variable is representative of a adverse health outcome.

5. The computer-implemented method of claim 1 wherein the step of defining a set of variables includes defining both dependent and independent variables, substantially all of the data elements from the claims information, as well as at least one combination of data elements are used as independent variables.

6. The computer-implemented method of claim 1 wherein the step of performing statistical analysis includes performing logistic regression.