Computerized system and method for predicting mortality risk using a lyapunov stability classifier

• US 20050228241A1
• Filed: 11/12/2004
• Published: 10/13/2005
• Est. Priority Date: 05/08/2003
• Status: Active Grant

• Current Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Original Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Inventors: McNair, Douglas S.
• Granted Patent: US 7,258,667 B2
• Time in Patent Office: Days
• US Class Current: 600/300
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: Y10S 128/92 Computer assisted medical diagnostics

Abstract

A method and system suitable for automated surveillance of intensive care unit patients for information denoting likelihood of in-hospital survival or mortality, represented in the timeseries of scoring systems such as APACHE III. Techniques from digital signal processing and Lyapunov stability analysis are combined in a method that allows for optimization of statistical hypothesis testing that is robust against short time series of as few as five time points. Once optimized, the method and system can achieve high-sensitivity high-specificity classification of survivorship, while avoiding false-positive prediction of mortality.

Claims

1. A computerized system for effecting a statistical assessment of mortality-predictive patterns in longitudinal timeseries data from individual persons admitted to hospital-based intensive care, the system comprising:

an accessing component for accessing mortality-predictive serial data received from a plurality of scores;

a performing component for performing spectral analysis;

a calculating component for calculating a Lyapunov exponent; and

an outputting component for outputting values for the exponent for at least one point in time in the timeseries so that the outcome for the individual person may be predicted if the Lyapunov exponent is negative.