The present invention provides a data mining framework for mining high-quality structured clinical information. The data mining framework includes a data miner that mines medical information from a computerized patient record (CPR) based on domain-specific knowledge contained in a knowledge base. Th
The present invention provides a data mining framework for mining high-quality structured clinical information. The data mining framework includes a data miner that mines medical information from a computerized patient record (CPR) based on domain-specific knowledge contained in a knowledge base. The data miner includes components for extracting information from the CPR, combining all available evidence in a principled fashion over time, and drawing inferences from this combination process. The mined medical information is stored in a structured CPR which can be a data warehouse.
대표청구항▼
What is claimed is: 1. A system for producing structured clinical information from patient records, comprising: a computerized patient record comprising at least one data source storing patient information, at least some of the patient information being unstructured, the patient information includi
What is claimed is: 1. A system for producing structured clinical information from patient records, comprising: a computerized patient record comprising at least one data source storing patient information, at least some of the patient information being unstructured, the patient information including clinical information related to a plurality of variables representing a state of the patient; a memory comprising a domain knowledge base containing domain-specific criteria relating the clinical information to values of the variables; and a processor configured to apply a data miner for extracting the clinical information from the data source using the domain-specific criteria, the data miner operable to create structured clinical information from the extracted clinical information including at least some of the unstructured patient information, the structured clinical information including the variables representing a state of the patient as a summary, the data miner operable to resolve discrepancies of different clinical information indicating different values of one of the variables. 2. The system of claim 1, wherein the data miner comprises: an extraction component for extracting information from the data sources and outputting a set of probabilistic assertion; a combination component for combining the set of probabilistic assertions into one or more unified probabilistic assertion; and an inference component for inferring patient states from the one or more unified probabilistic assertion. 3. The system of claim 2, wherein the extraction component extracts from the data sources as a function of the domain-specific criteria. 4. The system of claim 2, wherein the combination component combines from the probabilistic assertions as a function of the domain-specific criteria. 5. The system of claim 2, wherein the inference component infers the patient states as a function of the domain-specific criteria. 6. The system of claim 1, wherein the data sources include one or more of: medical information, financial information, demographic information, billing information or combinations thereof. 7. The system of claim 6, wherein the medical information includes one or more of: free text information, medical image information, laboratory information, prescription drug information, waveform information or combinations thereof. 8. The system of step 1, wherein the data miner is run at arbitrary intervals. 9. The system of claim 1, wherein the data miner is run at periodic intervals. 10. The system of step 1, wherein the data miner is run in online mode. 11. The system of claim 2, wherein the extraction component extracts key phrases from free text treatment notes. 12. The system of claim 2, wherein probability values are assigned to the probabilistic assertions. 13. The system of claim 1, wherein the created structured clinical information is stored in a database. 14. The system of claim 1, wherein the created structured clinical information includes probability information. 15. The system of claim 2, wherein the inference component uses a statistical model that describes a pattern of evolution of a disease across a patient population and the relationship between a patient's disease and observed variables. 16. The system of claim 15, wherein the inference component draws a plurality of inferences, each with an assigned probability. 17. The system of claim 1, wherein the domain-specific criteria includes institution-specific domain knowledge. 18. The system of claim 17, wherein the institution-specific domain knowledge relates to one or more of: data at a hospital, document structures at a hospital, policies of a hospital, guidelines of a hospital, variations at a hospital or combinations thereof. 19. The system of claim 1, wherein the domain-specific criteria includes disease-specific domain knowledge. 20. The system of claim 19, wherein the disease-specific domain knowledge includes one or more of: factors that influence risk of a disease, disease progression information, complications information, outcomes related to the disease, variables related to a disease, measurements related to a disease, policies established by medical bodies, guidelines established by medical bodies or combinations thereof. 21. The system of claim 1, wherein at least some of the information contained in the data source is accessible with a repository interface. 22. The system of claim 21, wherein the repository interface is a configurable data interface. 23. The system of claim 22, wherein the configurable data interface varies depending on hospital. 24. The system of claim 1, wherein the data sources include structured information, the created structured clinical information being, in part, responsive to the structured information. 25. The system of claim 24, wherein the structured information is converted into standardized units. 26. The system of claim 1, wherein the unstructured information includes one or more of: ASCII text strings, image information in DICOM format, text documents or combinations thereof partitioned based on domain knowledge. 27. The system of claim 1, wherein the data miner is run using the Internet. 28. The system of claim 1, wherein the created structured clinical information is accessed using the Internet. 29. The system of claim 1, wherein the data miner is run as a service. 30. The system of claim 29, wherein the service is performed by a third party service provider. 31. The system of claim 2, wherein the inferred patient states include diagnoses. 32. The system of claim 1, wherein the created structured clinical information includes corrected information. 33. The system of claim 1, wherein the data miner comprises an extraction component for extracting information from the data sources and outputting a set of probabilistic assertion. 34. The system of claim 33, wherein the data miner comprises a component for combining the set of probabilistic assertions into one or more unified probabilistic assertions and for inferring patient states from the one or more unified probabilistic assertions. 35. The system of claim 34 wherein the component for combining and for inferring is operable pursuant to Bayes Theorem. 36. The system of claim 2 wherein the inference and combination components are operable pursuant to Bayes Theorem. 37. The system of claim 1 wherein the at least one data source comprises a health care provider patient record. 38. The system of claim 13 wherein the database comprises a healthcare provider database. 39. The system of claim 11, wherein the extraction component extracts the key phrases using phrase spotting. 40. The system of claim 1, wherein the domain-specific criteria comprises criteria learned from data. 41. A method for producing structured clinical information from patient records, comprising the steps of: providing a first computerized patient record comprising at least one data source containing patient information, at least some of the patient information being unstructured and at least some of the patient information being structured; providing a memory storing a domain knowledge base containing domain-specific criteria; extracting clinical information from the at least one data source by data mining using the domain-specific criteria; and creating, using a computer, structured clinical information as a function of the extracting, the structured clinical information being a summary of the unstructured and structured patient information. 42. The method of claim 41, wherein extracting the clinical information from the data sources comprises: creating a set of probabilistic assertions; combining the set of probabilistic assertions into one or more unified probabilistic assertions; and inferring patient states from the one or more unified probabilistic assertions. 43. The method of claim 42, wherein extracting information from the data sources includes extracting the extracted information from the data sources as a function of the domain-specific criteria. 44. The method of claim 42, wherein combining the set of probabilistic assertions includes combining the probabilistic assertions as a function of the domain-specific criteria. 45. The method of claim 42, wherein inferring the patient states includes inferring the patient states as a function of the domain-specific criteria. 46. The method of claim 41, wherein the data sources include one or more of: medical information, financial information, demographic information, billing information or combinations thereof. 47. The method of claim 46, wherein the medical information includes one or more of: free text information, medical image information, laboratory information, prescription drug information, waveform information or combinations thereof. 48. The method of claim 42, wherein probability values are assigned to the probabilistic assertions. 49. The method of claim 41, wherein the created structured clinical information is stored in a database. 50. The method of claim 41, wherein the created structured clinical information includes probability information. 51. The method of claim 41, wherein the domain-specific criteria for mining the data sources includes institution-specific domain knowledge. 52. The method of claim 51, wherein the institution-specific domain knowledge relates to one or more of: data at a hospital, document structures at a hospital, policies of a hospital, guidelines of hospital, variations at a hospital or combinations thereof. 53. The method of claim 41, wherein the domain-specific criteria includes disease-specific domain knowledge. 54. The method of claim 42, combining and inferring comprises using Bayes Theorem. 55. The method of claim 41 wherein providing at least one data source comprises providing a health care provider patient record. 56. The method of claim 49 wherein the database comprises a healthcare provider database. 57. The method of claim 51, wherein the disease-specific domain knowledge includes one or more of: factors that influence risk of a disease, disease progression information, complications information, outcomes related to the disease, variables related to a the disease, measurements related to the disease, policies established by medical bodies, guidelines established by medical bodies or combinations thereof. 58. The method of claim 41, wherein the data source includes structured information. 59. The method of claim 58, wherein the structured information is converted into standardized units. 60. The method of claim 41, wherein the unstructured information includes one or more of: ASCII text strings, image information in DICOM format, text documents or combinations thereof partitioned based on domain knowledge. 61. The method of claim 41, wherein the method is performed using the Internet. 62. The method of claim 41, wherein the method is performed by a third party service provider. 63. The method of claim 42, wherein the inferred patient states include diagnoses. 64. The method of claim 41, wherein the created structured clinical information includes corrected information. 65. A program storage device readable by a machine, tangibly embodying a program of instructions when executed on the machine to perform a method for producing structured clinical information from patient records, the method comprising: providing at least one data source containing patient information, at least some of the patient information being unstructured; providing a domain knowledge base containing domain-specific criteria; extracting clinical information from the data sources using the domain-specific criteria, wherein extracting the clinical information from the data sources comprises: creating a set of probabilistic assertions; combining the set of probabilistic assertions into one or more unified probabilistic assertions; and inferring patient states from the one or more unified probabilistic assertions; and creating structured clinical information as a function of the extracting.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (73)
Siegrist ; Jr. Richard B. (Acton MA) Siegrist Donald W. (Harvard MA), Analysis and reporting of performance of service providers.
Kirshner Ronald, Computerized interactive method and system for determining a risk of developing a disease and the consequences of developing the disease.
Little John P. (Minneapolis MN) McMahon R. Scott (Eden Prairie MN) Gingrich Mark (Downingtown PA) Martin Roleigh H. (Eden Prairie MN), Health care payment adjudication and review system.
Seare Jerry G. (Salt Lake City UT) Smith-Wilson Patricia A. (North Salt Lake UT) VanWagoner Kurt (Layton UT) Mattey Jean A. (Midvale UT) Snyder Eileen K. (Sandy UT) Wahlstrom Candace C. (Salt Lake Ci, Method and system for generating statistically-based medical provider utilization profiles.
Torma Michael J. (Dallas TX) Galing Bernard W. (Papillion NE) Palmer Robert J. (Omaha NE) West Suzanne K. S. (Bellevue NE), Method and system for measuring management effectiveness.
Yeh Hwa-Young M ; Lure Yuan-Ming F ; Lin Jyh-Shyan, Method and system for re-screening nodules in radiological images using multi-resolution processing, neural network, and image processing.
Billheimer, D. Dean; Booker, Andrew James; Condliff, Michelle Keim; Greaves, Mark Thomas; Holt, Fredrick Baden; Kao, Anne Shu-Wan; Pierce, Daniel John; Poteet, Stephen Robert; Wu, Yuan-Jye, Method and system for text mining using multidimensional subspaces.
Johnson Gary Duane (Lewisville TX) Campbell Kelly Scott (Richardson TX), Method for extracting pre-defined data items from medical service records generated by health care providers.
Edward Howard Gilbert, Method, apparatus, and data structure for capturing and representing diagnostic, treatment, costs, and outcomes information in a form suitable for effective analysis and health care guidance.
Tyuluman Samuel A. ; Ammann Larry P., System and method for assessing physician performance using robust multivariate techniques of statistical analysis.
Driscoll Gary ; Burns Richard ; Keener Barbara ; Sanchez-Lazer Teresa ; Snieckus Alison ; SooHoo Paul ; Tyler Linda ; Willian Kenneth ; Wichert Victor, System and method for computer based test creation.
Rensimer Edward R. ; Tomsovic Jacqueline P. ; Wright Pamela A., System and method for recording patient-history data about on-going physician care procedures.
Bocionek, Siegfried; Hanslik, Margo; Russwurm, Siegfried, System and user interface for use in providing medical information and health care delivery support.
Kraftson Raymond H. ; Kraftson Marguerite O. ; Mudditt Michael ; Schrogie John J. ; Simon William H., System for and method of collecting and populating a database with physician/patient data for processing to improve practice quality and healthcare delivery.
Barry David W. ; Underwood Carolyn S. ; McCreedy Bruce J. ; Hadden David D. ; Lucas Jason L., Systems, methods and computer program products for guiding the selection of therapeutic treatment regimens.
Farooq, Faisal; Rosales, Romer E.; Yu, Shipeng; Krishnapuram, Balaji; Rao, Bharat R., Healthcare information technology system for predicting or preventing readmissions.
Gonzales, Jr., Merced; Loya, III, Francisco; Gonzales, Michael, System and method for gauging performance based on analysis of hospitalist and patient information.
Nawana, Namal; Horton, William C.; Frasier, William J.; Serhan, Hassan A.; O'Neil, Michael; Sommerich, Robert E.; DiPietro, Jennifer; Nordstrom, Christopher; Parsons, Matthew; Martin, Thomas, Systems and methods for surgical and interventional planning, support, post-operative follow-up, and functional recovery tracking.
Nawana, Namal; Horton, William C.; Reinhardt, Max; Bellas, Jonathan; Cranson, Cody; DiPietro, Jennifer; Fowler, Mary Louise; Frasier, William J.; Griffin, John Paul; Hall, Mark T.; Konieczynski, David D.; LeClerc, Michelle; Martin, Thomas; Nordstrom, Christopher; O'Neil, Michael; Paiva, James; Parsons, Matthew; Pavento, Nicholas; Raymond, Douglas; Roveda, James J.; Selover, Sean P.; Serhan, Hassan A.; Slivka, Michael A.; Sommerich, Robert E., Systems and methods for surgical and interventional planning, support, post-operative follow-up, and, functional recovery tracking.
Markatou, Marianthi; Ball, Robert; Botsis, Taxiarchis; Nguyen, Michael D.; Woo, Emily J., Text mining for large medical text datasets and corresponding medical text classification using informative feature selection.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.