Medical failure pattern search engine

• US 10,354,753 B2
• Filed: 03/15/2013
• Issued: 07/16/2019
• Est. Priority Date: 05/17/2001
• Status: Expired due to Fees

• Current Assignee: Lawrence A. Lynn
• Original Assignee: Lawrence A. Lynn
• Inventors: Lynn, Lawrence A., Lynn, Eric N.
• Primary Examiner(s): Ng, Jonathan
• Application Number:
  US13/843,481
• Publication Number:
  US 20130218600A1
• Time in Patent Office: 2,314 Days
• Field of Search: 705 2, 705 3
• 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 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: G16H 50/80 for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
• CPC Class Codes: G16H 70/20 relating to practices or guidelines

Abstract

A patient safety search engine and alarm processor is programmed to repetitively search the electronic medical records of all patients in a hospital system to automatically provide early detection of patients with evolving pathophysiologic cascades, and in particular the cascades of evolving death, such as cascades of septic shock. The search engine also searches for a wide range of evolving pathophysiologic failures which are commonly fatal if detected too late. An alarm processor is provided which is programmed to provide an alarm upon the detection of a cascade or failure. The processor is further be programmed to provide an image of the cascade, and to determine, the severity of the cascade, and the time of onset of the cascade in relation to the timing and type of procedures and treatment and the increased cost associated with the cascade. Discretionary real-time system-wide searches for a wide range of clinical failure patterns or images within the hospital system may be performed using the disclosed patient safety search engine.

Claims

1. A system for monitoring a plurality of patients in a hospital system to detect, in real time, the development of sepsis cascades and identify patients developing the sepsis cascades, the system comprising:

a plurality of local patient safety monitors, each of the plurality of local patient safety monitors configured to receive physiological measurements from at least a pulse oximeter and a blood pressure monitor for one or more patients,

a central patient safety monitor remote from the plurality of local patient safety monitors, the central patient safety monitor having a processor, and memory storing instructions that, when executed by the processor, cause the system to;

receive at least the physiological measurements from the plurality of local patient safety monitors;

search a database of laboratory data and physiologic parameters for perturbations of the laboratory data and physiologic parameters to identify a temporal grouping of at least four perturbations of the laboratory data and physiologic parameters associated with a patient, wherein the perturbations of the laboratory data and physiologic parameters are pathophysiologically linked, and wherein the database of laboratory data and physiologic parameters comprises an electronic medical record repository of data comprising data associated with a plurality of patients in at least one hospital;

generate a sepsis cascade pattern based on the identified temporal grouping of at least four perturbations of the laboratory data and the physiologic parameters, wherein the sepsis cascade pattern is indicative of sepsis;

associate the generated sepsis cascade pattern with the electronic medical record of the patient having the identified temporal grouping of at least four perturbations of the laboratory data and physiologic parameters; and

convert the generated sepsis cascade pattern into one or more images indicating progress of the sepsis cascade pattern;

send a notification to a patient safety console of at least one of the central patient safety monitor or one of the local patient safety monitors, for each patient of the one or more patients associated with a sepsis cascade pattern, an indication of the patient and the one or more images of the sepsis cascade pattern for the patient,

wherein the notification causes the patient safety console to display the indication of each patient of the one or more patients having a sepsis cascade pattern and the one or more images of the sepsis cascade pattern for each patient.

2. The system of claim 1, wherein the memory stores additional instructions that, when executed by the processor, cause the system to:

provide an automatic alarm at one of the central patient safety monitor and at least one of the plurality of local patient safety monitors based on identifying the one or more patients of the plurality of patients having the at least one sepsis cascade pattern.

3. The system of claim 1, wherein the at least one sepsis cascade pattern comprises a cascade of a progressively increasing number and severity of relational perturbations indicative of one or more of severe sepsis, septic shock, microcirculatory failure, or shock.

4. The system of claim 1, wherein the at least one sepsis cascade pattern comprises a plurality of linked perturbations or trends of physiologic and laboratory data defining a progressively enlarging aggregation of progressively greater numbers of perturbed physiologic and laboratory data.

5. The system of claim 1, wherein the memory stores additional instructions that, when executed by the processor, cause the system to:

determine at least one characteristic of the at least one sepsis cascade pattern, the at least one characteristic comprising one or more of a severity of the at least one sepsis cascade pattern, a duration of the at least one sepsis cascade pattern, a time of onset of the at least one sepsis cascade pattern, a maturity of the at least one sepsis cascade pattern, a timing relationship of the at least one sepsis cascade pattern to other events or another sepsis cascade pattern, a cost associated with the at least one sepsis cascade pattern, a global pattern of the at least one sepsis cascade pattern, a time of termination of the at least one sepsis cascade pattern, components of the at least one sepsis cascade pattern, a state of evolution of the at least one sepsis cascade pattern, a length of stay associated with the at least one sepsis cascade pattern, or treatments associated with the at least one sepsis cascade pattern.

6. The system of claim 5, wherein the at least one characteristic of the at least one sepsis cascade pattern is defined by one or more of a number of perturbations or trends which comprise the at least one sepsis cascade pattern, a severity of the perturbations or trends, a number of systems affected by the at least one sepsis cascade pattern, or a presence, number or severity of failure of compensation in response to perturbations associated with the at least one sepsis cascade pattern.

7. The system of claim 1, wherein the memory stores additional instructions that, when executed by the processor, cause the system to:

determine a rate of growth of the at least one sepsis cascade pattern.

8. The system of claim 1, wherein the memory stores additional instructions that, when executed by the processor, cause the system to:

determine a rate of growth of the at least one sepsis cascade pattern by at least one of an increase in number or severity of new perturbations being added per unit time, an increase in number of systems affected, or an increase in number of perturbations present in different systems.

9. The system of claim 1, wherein the memory stores additional instructions that, when executed by the processor, cause the system to:

detect events or components that are temporally or spatially associated with the at least one sepsis cascade pattern and are not part of the at least one sepsis cascade pattern.

10. The system of claim 1, wherein the memory stores additional instructions that, when executed by the processor, cause the system to:

convert electronic medical records from the electronic medical record repository of data into a format enabling the system to search for a sepsis cascade pattern.

11. The system of claim 10, wherein the format comprises sequential and timed variations comprised of at least positive variations and negative variations of the data.

12. The system of claim 10, wherein the electronic medical record repository of data comprises data from a plurality of hospitals, and wherein the memory stores additional instructions that, when executed by the processor, cause the system to:

identify the one or more patients of the plurality of patients having the at least one sepsis cascade patterns and one or more hospitals in which the one or more patients are located.

13. The system of claim 1, comprising:

the patient safety console.

14. A system for monitoring a plurality of patients in a hospital system to detect, in real time, the development of sepsis cascades and identify patients developing the sepsis cascades, the system comprising:

a plurality of local patient safety monitors, each of the plurality of local patient safety monitors configured to receive physiological measurements from at least a pulse oximeter and a blood pressure monitor for one or more patients,

a central patient safety monitor remote from the plurality of local patient safety monitors, the central patient safety monitor having a processor, and memory storing instructions that, when executed by the processor, cause the system to;

convert electronic medical records of patients in at least one hospital into sequential and timed trends;

generate, from the sequential and timed trends, positive trends and negative trends of physiologic parameters and laboratory data;

determine, from the positive trends and negative trends, relational trends comprising a combination of positive trends or negative trends associated with the physiologic parameters and the laboratory data;

generate sepsis cascade patterns associated with a plurality of combinations of the relational trends;

convert the generated sepsis cascade patterns into one or more images based on the plurality of combinations of the relational trends;

generate a warning based on detecting the sepsis cascade patterns, the warning identifying at least one patient generating the sepsis cascade patterns;

determine a growth or a decline of the sepsis cascade patterns and generate an indication responsive to the growth or the decline of the sepsis cascade patterns; and

send a notification to a patient safety console of at least one of the central patient safety monitor or one of the local patient safety monitors including the image of the sepsis cascade patterns generated based on the plurality of combinations of the relational trends, the warning generated based on detecting the sepsis cascade patterns, and the indication responsive to the growth or the decline of the sepsis cascade patterns,

wherein the notification causes the patient safety console to display one or more of the image of the sepsis cascade patterns generated based on the plurality of combinations of the relational trends, the warning generated based on detecting the sepsis cascade patterns, or the indication responsive to the growth or the decline of the sepsis cascade patterns.

15. The system of claim 14, wherein the sepsis cascade patterns are indicative of physiologic failure.

16. The system of claim 15, wherein the physiologic failure is associated with one or more of severe septic shock, or microcirculatory failure.

17. The system of claim 14, wherein generating the image of the sepsis cascade patterns based on the plurality of combinations of the relational trends comprises generating at least one moving picture based on the plurality of combinations of the relational trends.

18. The system of claim 17, wherein the memory stores additional instructions that, when executed by the processor, cause the system to:

determine and output, to a user interface displaying the at least one moving picture, an indication of timing and type associated with the relational trends.

19. The system of claim 17, wherein the memory stores additional instructions that, when executed by the processor, cause the system to:

determine and output, to a user interface displaying the at least one moving picture, an indication of length of a cascade.

20. The system of claim 17, wherein the memory stores additional instructions that, when executed by the processor, cause the system to:

determine and output, to a user interface displaying the at least one moving picture, an indication of timing of therapy in relation to a cascade.

21. The system of claim 14, comprising:

the patient safety console.

22. A system for monitoring a plurality of patients in a hospital system to detect, in real time, the development of sepsis cascades and identify patients developing the sepsis cascades, the system comprising:

a plurality of local patient safety monitors, each of the plurality of local patient safety monitors configured to receive physiological measurements from at least a pulse oximeter and a blood pressure monitor for one or more patients,

a central patient safety monitor remote from the plurality of local patient safety monitors, the central patient safety monitor having a processor and memory storing instructions that, when executed by the processor, cause the system to;

receive at least the physiological measurements from the plurality of local patient safety monitors and store the physiological measurements in an electronic medical record;

receive, from the electronic medical record, data associated with a plurality of patients in a hospital, the data being associated with a physiologic state for care of each patient of the plurality of patients in the hospital, and the data including at least the physiological measurements from the plurality of local patient safety patient monitors and one or more laboratory datasets derived from laboratory testing of blood samples associated with the plurality of patients in the hospital;

convert the physiological measurements and the one or more laboratory datasets into a plurality of time series; and

determine occurrences of perturbations associated with the plurality of time series by analyzing changes over time in each of the plurality of time series, the occurrences of perturbations associated with the plurality of time series comprising one or more of inflammatory occurrences, metabolic occurrences, volumetric occurrences, hemodynamic occurrences, therapy occurrences, hematologic occurrences, or respiratory occurrences;

determine a timing of each of the occurrences of perturbations associated with the plurality of time series;

generate an indication of a sepsis cascade responsive to identifying at least one relational pattern among the occurrences of perturbations associated with the plurality of time series and the determined timing of each of the occurrences of the perturbations, the sepsis cascade being defined by a temporal grouping of at least four of the occurrences of perturbations associated with the plurality of time series;

generate an alarm notification responsive to the generated indication of the sepsis cascade, the alarm notification identifying a patient in the hospital generating the sepsis cascade; and

send the alarm notification to a patient safety console of the central patient safety monitor or one of the local patient safety monitors in the hospital,

wherein the alarm notification causes the patient safety console in the hospital to display one or more images of the sepsis cascade and information identifying the patient in the hospital generating the sepsis cascade.

23. The system of claim 22, comprising:

the patient safety console;

a blood pressure monitor; and

a pulse oximeter,

wherein the memory stores additional instructions that, when executed by the processor, cause the system to;

receive, from the pulse oximeter, pulse oximetry data associated with at least one patient of the plurality of patients; and

receive, from the blood pressure monitor, blood pressure data associated with the at least one patient of the plurality of patients, and

wherein at least one of the occurrences of perturbations associated with the plurality of time series is identified based on the pulse oximetry data received from the pulse oximeter and the blood pressure data received from the blood pressure monitor.

24. A system for monitoring a plurality of patients in a hospital system to detect, in real time, the development of sepsis cascades and identify patients developing the sepsis cascades, the system comprising:

a patient safety console;

a plurality of blood pressure monitors;

a plurality of pulse oximeters;

a plurality of local patient safety monitors, each of the plurality of local patient safety monitors configured to receive physiological measurements from at least one of the plurality of pulse oximeters and at least one of the plurality of blood pressure monitors for one or more patients, and

a central patient safety monitor remote from the plurality of local patient safety monitors, the central patient safety monitor having a processor and memory storing instructions that, when executed by the processor, cause the system to;

receive at least the physiological measurements from the plurality of local patient safety monitors and store the physiological measurements in a database of laboratory data and physiologic parameters;

search the database of laboratory data and physiologic parameters for perturbations of the laboratory data and physiologic parameters to identify a cascade pattern indicative of sepsis,

wherein the cascade pattern indicative of sepsis is associated with a temporal grouping of at least four perturbations of the laboratory data and physiologic parameters,

wherein the perturbations of the laboratory data and physiologic parameters are pathophysiologically linked,

wherein the database of laboratory data and physiologic parameters comprises an electronic medical record repository of data comprising data associated with a plurality of patients in at least one hospital, and

wherein the data associated with the plurality of patients in the at least one hospital comprises pulse oximetry data received from the pulse oximeter and blood pressure data received from the blood pressure monitor of at least one local patient safety monitor;

based on searching the database, identify one or more patients of the plurality of patients as having at least one sepsis cascade pattern, wherein the at least one sepsis cascade pattern comprises a plurality of linked perturbations or trends of physiologic and laboratory data defining a progressively enlarging aggregation of progressively greater numbers of perturbed physiologic and laboratory data;

send a notification to the patient safety console comprising an indication of each patient of the one or more patients identified as having the at least one sepsis cascade pattern and one or more images of the at least one sepsis cascade pattern,

wherein the notification causes the patient safety console to display the indication of each patient of the one or more patients identified as having the at least one sepsis cascade pattern and the one or more images of the at least one sepsis cascade pattern;

determine at least one characteristic of the at least one sepsis cascade pattern, the at least one characteristic comprising one or more of a severity of the at least one sepsis cascade pattern, a duration of the at least one sepsis cascade pattern, a time of onset of the at least one sepsis cascade pattern, a maturity of the at least one sepsis cascade pattern, a timing relationship of the at least one sepsis cascade pattern to other events or another sepsis cascade pattern, a cost associated with the at least one sepsis cascade pattern, a global pattern of the at least one sepsis cascade pattern, a time of termination of the at least one sepsis cascade pattern, components of the at least one sepsis cascade pattern, a state of evolution of the at least one sepsis cascade pattern, a length of stay associated with the at least one sepsis cascade pattern, or treatments associated with the at least one sepsis cascade pattern;

output, to a graphical user interface displayed on the patient safety console, the at least one characteristic of the at least one sepsis cascade pattern;

determine a rate of growth of the at least one sepsis cascade pattern by at least one of an increase in number or severity of new perturbations being added per unit time, an increase in number of systems affected, or an increase in number of perturbations present in different systems;

output, to the graphical user interface displayed on the patient safety console, the rate of growth of the at least one sepsis cascade pattern,

generate at least one moving picture based on the identified sepsis cascade pattern to illustrate the progress of the sepsis cascade pattern over time, and

output the generated moving picture, to the graphical user interface, wherein the graphical user interface includes viewing regions corresponding to physiologic systems of the patient, the viewing regions including at least an inflammatory region, and wherein the viewing regions are configured so that the moving picture is displayed such that the identified sepsis cascade pattern is viewable spreading over time within or across at least the inflammatory region as the severity of the sepsis cascade pattern progresses over time from the origin of the sepsis cascade to the termination of the sepsis cascade.