Clinical predictive and monitoring system and method

• US 9,536,052 B2
• Filed: 09/13/2012
• Issued: 01/03/2017
• Est. Priority Date: 10/28/2011
• Status: Active Grant

• Current Assignee: Pieces Technologies, Inc.
• Original Assignee: Parkland Center for Clinical Innovation
• Inventors: Amarasingham, Rubendran, Swanson, Timothy S., Clark, Christopher A., Qian, Yu, Nalla, Sambamurthy, Oliver, George R., Gerra, Kimberly P., Ma, Ying
• Primary Examiner(s): Hill, Stanley K
• Assistant Examiner(s): Kim, David H
• Application Number:
  US13/613,980
• Publication Number:
  US 20130262357A1
• Time in Patent Office: 1,573 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• 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 clinical predictive and monitoring system comprising a data store operable to receive and store data associated with a plurality of patients selected from medical and health data; and a number of social, behavioral, lifestyle, and economic data; at least one predictive model to identify at least one high-risk patient associated with at least one medical condition; a risk logic module operable to apply the at least one predictive model to the patient data to determine at least one risk score associated the at least one medical condition and identify at least one high-risk patient; a data presentation module operable to present notification and information to an intervention coordination team about the identified at least one high-risk patient; and an artificial intelligence tuning module adapted to automatically adjust parameters in the predictive model in response to trends in the patient data.

Claims

1. A clinical predictive and monitoring system, comprising:

a data store configured to receive and store data associated with a plurality of patients including clinical and non-clinical data;

at least one predictive model including a plurality of weighted risk variables and risk thresholds in consideration of the clinical and non-clinical data to identify at least one high-risk patient as having a high risk of developing at least one specified medical condition;

a risk logic module configured to apply the at least one predictive model to the patient clinical and non-clinical data of the plurality of patients to determine at least one risk score associated with the at least one specified medical condition for each patient, and identify at least one high-risk patient from among the plurality of patients as having a high risk of developing the at least one specified medical condition indicated by the risk scores; and

a data presentation module configured to present notification and information to an intervention coordination team about the identified at least one high-risk patient.

2. The system of claim 1, further comprising an artificial intelligence tuning module configured to automatically adjust the weights of the plurality of risk variables in response to trends in patient data.

3. The system of claim 1, further comprising an artificial intelligence tuning module configured to automatically adjust the risk thresholds of the plurality of risk variables in response to trends in patient data.

4. The system of claim 1, further comprising an artificial intelligence tuning module configured to automatically add or remove risk variables in the at least one predictive model in response to trends in patient data.

5. The system of claim 1, further comprising an artificial intelligence tuning module configured to automatically adjust at least one of the weights, risk thresholds, and risk variables in response to trends in patient data.

6. The system of claim 1, further comprising an artificial intelligence tuning module configured to automatically adjust a parameter in the predictive model in response to detecting a change in the overall patient data to improve the accuracy of risk score determination.

7. The system of claim 1, wherein the data store is configured to receive and store real-time and historic data.

8. The system of claim 1, wherein the data presentation module is further configured to generate and transmit notification and information in a form selected from at least one member of the group consisting of text message, multimedia message, instant message, voice message, e-mail message, web page, web-based message, web pages, web-based message, and text files.

9. The system of claim 1, wherein the data presentation module is further configured to generate and transmit notification and information to at least one mobile device.

10. The system of claim 1, wherein the data presentation module further comprises a dashboard interface configured to present and display information in response to a user request.

11. The system of claim 1, further comprising a system configuration interface configured to receive configuration data from a user to initiate or adjust system operations.

12. The system of claim 1, further comprising a system configuration interface configured to set or reset at least one of the risk variable thresholds and weights in the predictive model.

13. The system of claim 1, wherein the risk logic module is further configured to analyze the clinical and non-clinical data and identify a disease associated with at least one of the plurality of patients.

14. The system of claim 1, wherein the data store is further configured to continue receiving and storing clinical and non-clinical data generated after a patient'"'"'s admission to a hospital, and the risk logic module is operable to continue applying at least one predictive model associated with an identified disease to a data set including all clinical and non-clinical data associated with the patient.

15. The system of claim 1, wherein the data store is further configured to continue receiving and storing clinical and non-clinical data generated after a patient'"'"'s discharge from a hospital, and the risk logic module is operable to continue applying at least one predictive model associated with an identified disease to a data set including all clinical and non-clinical data associated with the patient.

16. The system of claim 1, further comprising a data integration logic module configured to receive the clinical and non-clinical patient data, and perform data extraction, data cleansing, and data manipulation on the received data.

17. The system of claim 1, further comprising a data integration logic module configured to receive the clinical and non-clinical patient data, and perform natural language processing.

18. The system of claim 17, wherein the data integration logic module is configured to apply a plurality of rules and a statistical model to the patient data.

19. The system of claim 17, further comprising a data integration logic module including a rule-based model and a statistically-based learning model.

20. The system of claim 19, wherein the statistical-based learning model is configured to develop inferences based on repeated patterns and relationships in the patient data.

21. The system of claim 17, wherein the data integration logic module is configured to analyze the received and stored patient data, identify data elements, and map those data elements to definitions in a data dictionary.

22. The system of claim 1, wherein the data store is configured to receive and store data extracted from social media websites.

44. The system of claim 1 or 23, wherein the clinical data are selected from at least one member of the group consisting of:

vital signs and other physiological data;

data associated with physical exams by a physician, nurse, or allied health professional;

medical history;

allergy and adverse medical reactions;

family medical information;

prior surgical information;

emergency room records;

medication administration records;

culture results;

dictated clinical notes and records;

gynecological and obstetric information;

mental status examination;

vaccination records;

radiological imaging exams;

invasive visualization procedures;

psychiatric treatment information;

prior histological specimens;

laboratory data;

genetic information;

physician'"'"'s and nurses'"'"' notes;

networked devices and monitors;

pharmaceutical and supplement intake information; and

focused genotype testing.

45. The system of claim 1 or 23, wherein the clinical data comprises:

vital signs;

data associated with physical exams by a physician, nurse, or allied health professional;

medical history;

allergy and adverse medical reactions;

family medical information;

prior surgical information;

emergency room records;

medication administration records;

culture results;

dictated clinical notes and records;

vaccination records;

radiological imaging exams;

laboratory data;

genetic information;

physician'"'"'s and nurses'"'"' notes;

pharmaceutical and supplement intake information; and

focused genotype testing.

46. The system of claim 1 or 23, wherein the non-clinical data are selected from at least one member of the group consisting of:

social, behavioral, lifestyle, and economic data;

type and nature of employment data;

job history data;

medical insurance information;

hospital utilization patterns;

exercise information;

addictive substance use data;

occupational chemical exposure records;

frequency of physician or health system contact logs;

location and frequency of habitation change data;

predictive screening health questionnaires;

personality tests;

census and demographic data;

neighborhood environment data;

dietary data;

participation in food, housing, and utilities assistance registries;

gender;

marital status;

education data;

proximity and number of family or care-giving assistant data;

address data;

housing status data;

social media data;

educational level data; and

data entered by patients.

47. The system of claim 1 or 23, wherein the non-clinical data comprises:

social, behavioral, lifestyle, and economic data;

type and nature of employment data;

job history data;

medical insurance information;

hospital utilization patterns;

exercise information;

substance use data;

occupational chemical exposure records;

frequency of physician or health system contact logs;

location and frequency of habitation change data;

census and demographic data;

neighborhood environment data;

dietary data;

participation in food, housing, and utilities assistance registries;

gender;

marital status;

education data;

proximity and number of family or care-giving assistant data;

address data;

housing status data;

social media data;

educational level data; and

data entered by patients.

23. A clinical predictive and monitoring system, comprising:

a data store configured to receive and store data associated with a plurality of patients including clinical and non-clinical data;

at least one predictive model for at least one specified medical condition configured to process the patient clinical and non-clinical data to identify at least one high-risk patient as having a high risk of developing the at least one specified medical condition;

a risk logic module configured to apply the at least one predictive model to the patient clinical and non-clinical data of the plurality of patients to determine at least one risk score associated with the at least one specified medical condition for each patient, and identify at least one high-risk patient for the at least one specified medical condition indicated by the risk scores;

a data presentation module configured to present notification and information to an intervention coordination team about the identified at least one high-risk patient; and

an artificial intelligence tuning module configured to automatically adjust parameters in the predictive model in response to trends in the patient data.

24. The system of claim 23, wherein the artificial intelligence tuning module is further configured to automatically adjust the risk thresholds of the plurality of risk variables in response to trends in patient data.

25. The system of claim 23, wherein the artificial intelligence tuning module is further configured to automatically add or remove risk variables in the at least one predictive model in response to trends in patient data.

26. The system of claim 23, wherein the artificial intelligence tuning module is further configured to automatically adjust at least one of the weights, risk thresholds, and risk variables in response to trends in patient data.

27. The system of claim 23, wherein the data store is configured to receive and store real-time and historic data.

28. The system of claim 23, wherein the data presentation module is further configured to generate and transmit notification and information in a form selected from at least one member of the group consisting of text message, multimedia message, instant message, voice message, e-mail message, web page, web-based message, web pages, web-based message, and text files.

29. The system of claim 23, wherein the data presentation module is further configured to generate and transmit notification and information to at least one mobile device.

30. The system of claim 23, wherein the data presentation module further comprises a dashboard interface configured to present and display information in response to a user request.

31. The system of claim 23, further comprising a system configuration interface configured to receive configuration data from a user to initiate or adjust system operations.

32. The system of claim 23, further comprising a system configuration interface configured to set or reset at least one of the risk variable thresholds and weights in the predictive model.

33. The system of claim 23, wherein the risk logic module is further configured to analyze the clinical and non-clinical data and identify a disease associated with at least one of the plurality of patients.

34. The system of claim 23, wherein the data store is further configured to continue receiving and storing clinical and non-clinical data generated after a patient'"'"'s admission to a hospital, and the risk logic module is configured to continue applying at least one predictive model associated with an identified disease to a data set including all clinical and non-clinical data associated with the patient.

35. The system of claim 23, wherein the data store is further configured to continue receiving and storing clinical and non-clinical data generated after a patient'"'"'s discharge from a hospital, and the risk logic module is configured to continue applying at least one predictive model associated with an identified disease to a data set including all clinical and non-clinical data associated with the patient.

36. The system of claim 23, further comprising a data integration logic module configured to receive the clinical and non-clinical patient data, and perform data extraction, data cleansing, and data manipulation on the received data.

37. The system of claim 23, further comprising a data integration logic module configured to receive the clinical and non-clinical patient data, and perform natural language processing.

38. The system of claim 37, wherein the data integration logic module is configured to apply a plurality of rules and a statistical model to the patient data.

39. The system of claim 37, further comprising a data integration logic module including a rule-based model and a statistically-based learning model.

40. The system of claim 39, wherein the statistical-based learning model is configured to develop inferences based on repeated patterns and relationships in the patient data.

43. The system of claim 23, wherein the risk logic module is further adapted to generate evidence supporting the identification of the patient as high-risk.

41. A computerized method of providing clinical screening, diagnosis, treatment, monitoring and palliation, comprising:

receiving and storing data associated with a plurality of patients including clinical and non-clinical data;

processing the clinical and non-clinical data of the plurality of patients with a predictive model configured with risk variables and risk thresholds of at least one specified medical condition;

computing, using the predictive model, a risk score in response to the risk variables and risk thresholds for each patient that is indicative of the patient'"'"'s risk for developing the at least one specified medical condition;

in response to the computed risk scores, identifying at least one high-risk patient as having a high risk of developing the at least one specified medical condition;

presenting at least one of visual and audible notification to an intervention coordination team about the identified at least one high-risk patient; and

automatically monitoring and adjusting parameters in the predictive model in response to trends in the patient clinical and non-clinical data.

42. The method of claim 41, wherein receiving and storing data comprises receiving and storing patient data from data sources selected from at least one member of the group consisting of:

hospitals, clinics, health information exchanges, pharmacies, laboratories, social services entities, and social media websites.

48. The method of claim 41, wherein receiving clinical data comprise receiving clinical data selected from at least one member of the group consisting of:

vital signs and other physiological data;

data associated with physical exams by a physician, nurse, or allied health professional;

medical history;

allergy and adverse medical reactions;

family medical information;

prior surgical information;

emergency room records;

medication administration records;

culture results;

dictated clinical notes and records;

gynecological and obstetric information;

mental status examination;

vaccination records;

radiological imaging exams;

invasive visualization procedures;

psychiatric treatment information;

prior histological specimens;

laboratory data;

genetic information;

physician'"'"'s and nurses'"'"' notes;

networked devices and monitors;

pharmaceutical and supplement intake information; and

focused genotype testing.

49. The method of claim 41, wherein receiving clinical data comprise receiving:

vital signs;

data associated with physical exams by a physician, nurse, or allied health professional;

medical history;

allergy and adverse medical reactions;

family medical information;

prior surgical information;

emergency room records;

medication administration records;

culture results;

dictated clinical notes and records;

vaccination records;

radiological imaging exams;

laboratory data;

genetic information;

physician'"'"'s and nurses'"'"' notes;

pharmaceutical and supplement intake information; and

focused genotype testing.

50. The method of claim 41, wherein receiving clinical data comprise receiving non-clinical data at least one member of the group consisting of:

social, behavioral, lifestyle, and economic data;

type and nature of employment data;

job history data;

medical insurance information;

hospital utilization patterns;

exercise information;

addictive substance use data;

occupational chemical exposure records;

frequency of physician or health system contact logs;

location and frequency of habitation change data;

predictive screening health questionnaires;

personality tests;

census and demographic data;

neighborhood environment data;

dietary data;

participation in food, housing, and utilities assistance registries;

gender;

marital status;

education data;

proximity and number of family or care-giving assistant data;

address data;

housing status data;

social media data;

educational level data; and

data entered by patients.

51. The method of claim 41, wherein receiving non-clinical data comprise receiving:

social, behavioral, lifestyle, and economic data;

type and nature of employment data;

job history data;

medical insurance information;

hospital utilization patterns;

exercise information;

substance use data;

occupational chemical exposure records;

frequency of physician or health system contact logs;

location and frequency of habitation change data;

census and demographic data;

neighborhood environment data;

dietary data;

participation in food, housing, and utilities assistance registries;

gender;

marital status;

education data;

proximity and number of family or care-giving assistant data;

address data;

housing status data;

social media data;

educational level data; and

data entered by patients.