PATIENT SAFETY PROCESSOR

• US 20130290011A1
• Filed: 03/15/2013
• Published: 10/31/2013
• Est. Priority Date: 05/17/2001
• Status: Active Grant

• Current Assignee: Lawrence A. Lynn
• Original Assignee: Lawrence A. Lynn
• Inventors: Lynn, Lawrence A., Lynn, Eric N.
• Granted Patent: US 10,366,790 B2
• Time in Patent Office: Days
• US Class Current: 705/2
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing
• CPC Class Codes: G16H 40/60 for the operation of medical equipment or devices
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• 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: H04N 9/87 Regeneration of colour television signals H04N9/80 takes precedence

Abstract

A processor-based system for analyzing physiologic data and medical care is provided wherein the patient data is analyzed to construct images that are representative of a patient'"'"'s condition. The processor provides a self-modulating analysis, which is responsive to the occurrence of additional data items to increase the information contained in the images. Identifications of modes of physiologic failure by the analysis of the generated images provides for earlier recognition and intervention and improved protocolization of testing and treatment.

Claims

1. A patient data processing system comprising a processor programmed with instructions for:

converting an electronic medical record into trend data, wherein the trend data is sequential, and wherein the trend data comprises trends of physiologic parameters and laboratory data over time;

detecting relational trends between the trend data comprising positive and/or negative trends;

detecting a complex cascade pattern comprising a plurality of relational trends;

generating an image of the detected complex cascade pattern; and

comparing the image to a reference image to determine one or more characteristics of the complex cascade pattern.

2. The patient data processing system of claim 1, wherein the reference image comprises a database of reference images of different types of complex cascade patterns.

3. The patient data processing system of claim 1, wherein the reference image comprises an image from a patient with a diagnosis confirmed by autopsy, histopathology, microbiology, expert consensus or genetic testing.

4. The patient data processing system of claim 1, wherein the complex cascade pattern is indicative of physiologic failure.

5. The patient data processing system of claim 4, wherein the physiologic failure is at least one of sepsis, severe sepsis, septic shock, and microcirculatory failure, a shock cascade, or a septic shock cascade.

6. The patient data processing system of claim 1, comprising instructions for providing an indication of a type of the complex cascade pattern.

7. The patient data processing system of claim 1, comprising instructions for providing an indication of timing or type of the relational trends.

8. The patient data processing system of claim 1, comprising instructions for providing an indication of the length of the complex cascade pattern.

9. The patient data processing system of claim 1, comprising instructions for determining an onset of therapy and providing an indication of timing of the therapy in relation to the complex cascade pattern.

10. A method, comprising:

receiving data related to a plurality of physiological parameters from a patient over time;

generating a respective time series from the data from each of the plurality of physiological parameters;

converting the respective time series into respective discrete objects;

grouping two or more discrete objects together to create a binary object based on a physiological relationship between the two or more objects;

inserting the binary object into an image representation of a condition of the patient;

comparing the image representation to a second image representation; and

determining the condition of the patient based on the comparing.

11. The method recited in claim 10, wherein grouping two or more discrete objects to create the binary object comprises grouping two or more discrete objects representative of an increase in a physiological parameter over time.

12. The method recited in claim 10, wherein grouping two or more discrete objects to create the binary object comprises grouping two or more discrete objects representative of a decrease in a physiological parameter over time.

13. The method recited in claim 10, wherein grouping two or more discrete objects to create the binary object comprises grouping two or more discrete objects representative of a drug treatment, wherein one of the discrete objects represents a patient state prior to drug treatment.

14. The method recited in claim 10, wherein the second image is part of a database of previously acquired images.

15. The method recited in claim 10, wherein the comparing comprises matching the image representation and the second image representation for similarity.

16. The method recited in claim 10, comprising determining a diagnosis for the undiagnosed image representation and adding the undiagnosed image representation and its associated diagnosis to the database.

17. A patient data processing system comprising:

a database comprising a plurality of image representations of diseases from a respective plurality of patients; and

a processor programmed with instructions for;

receiving data from an electronic medical record;

converting the data to an undiagnosed image representation of a patient;

searching the database for the one or more image representations from the plurality of image representations that are the most similar to the undiagnosed image representation; and

providing an indication of the diseases associated with the one or more image representations that are the most similar to the undiagnosed image representation.

18. The system recited in claim 17, wherein converting the data comprises creating discrete objects from the data.

19. The system recited in claim 17, wherein converting the data comprises creating a matrix of time series data.