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▼
1. A system for producing structured clinical information from patient records, the system comprising: a patient record comprising at least two data sources having patient information, at least one of the data sources being an unstructured data source and at least one of the data sources being a str
1. A system for producing structured clinical information from patient records, the system comprising: a patient record comprising at least two data sources having patient information, at least one of the data sources being an unstructured data source and at least one of the data sources being a structured data source;a probabilistic data miner of a computer platform configured to (a) extract multiple pieces of information related to a variable for a patient from mining structured data of the at least one structured data source and mining unstructured data of the at least one unstructured data source of the patient record, the mining of the at least one unstructured data source comprising mining free text information, and (b) combine the extracted multiple pieces of information related to the variable into a value of the variable for the patient, the value being a function of the multiple pieces related to the variable, and the data miner configured to repeat (a) and (b) for a plurality of different variables of the same patient for a same time, each repetition of extracting and combining multiple pieces of information related to the variable of the different variables being handled in the repetition such that the multiple pieces of information for one variable are different than the multiple pieces of information for other ones of the different variables, the variable and the different variables comprising characteristics of the patient at the time;wherein one or both of (a) and (b) are performed as a function of domain-specific criteria. 2. The system of claim 1 wherein the data miner is operable to extract the multiple pieces of information as a function of the domain-specific criteria. 3. The system of claim 1 wherein the data miner is operable to combine the extracted multiple pieces of information as a function of the domain-specific criteria, the domain-specific criteria comprising knowledge about a disease, the multiple pieces being combined to determine the value for the variable. 4. The system of claim 1 wherein the data miner comprises an extraction component for extracting the multiple pieces of information and outputting a probabilistic assertion. 5. The system of claim 1 wherein the data miner is operable to infer a patient state as a function of the combined pieces of information. 6. The system of claim 5 wherein the data miner is operable to infer the patient state as a function of probabilities, one of the probabilities assigned to each of the combined pieces of information. 7. The system of claim 5 wherein the inference is a function of a statistical model of a pattern of evolution of a disease across a patient population and the relationship between a patient's disease and observed variables. 8. The system of claim 1 wherein the patient information includes one or more of: medical information, financial information, demographic information or combinations thereof, the at least one unstructured data source including two or more of: the free text information, medical image information, laboratory information, prescription drug information, waveform information or combinations thereof. 9. The system of claim 1 wherein the data miner is operable to extract key phrases from the at least one unstructured data source, the at least one unstructured data source comprising free text treatment notes, the key phrases comprising at least part of the domain-specific criteria. 10. The system of claim 1 wherein the data miner is operable to output structured clinical information with probability information. 11. The system of claim 1 wherein the domain-specific criteria includes institution-specific domain knowledge, disease-specific domain knowledge, or combinations thereof. 12. The system of claim 1 wherein the at least one unstructured data source includes two or more of: ASCII text strings, image information in DICOM format, text documents, or combinations thereof, partitioned based on domain knowledge. 13. The system of claim 1 wherein the data miner is run at arbitrary intervals, periodic intervals, in an online mode, or combinations thereof. 14. The system of claim 1 wherein a repository interface is used to access at least some of the information contained in the at least two data sources used by the data miner, wherein the repository interface is a configurable data interface, which varies depending on hospital. 15. A method for producing structured clinical information from patient records, comprising: (a) extracting, by a machine, multiple pieces of information from at least one structured data source and at least one unstructured data source of a patient record of a patient, the extracting from the at least one unstructured data source comprising mining unstructured free text information, the multiple pieces indicating different first values for a same variable recorded for the patient;(b) combining, probabilistically by the machine, the extracted multiple pieces of information into a second value of the variable representing the patient, the second value being a function of the first values recorded for the patient;wherein one or both of (a) and (b) are performed as a function of domain-specific criteria; andrepeating (a) and (b) for a different variable, the repetition searching for different pieces of information relevant to the different variable and combining the different pieces of information into a value for the different variable, the variable and the different variable representing the patient at a given time. 16. The method of claim 15 wherein (a) is performed as a function of the domain-specific criteria. 17. The method of claim 15 wherein the combining of (b) is performed as a function of the domain-specific criteria, the domain-specific criteria comprising knowledge of a disease. 18. The method of claim 15 wherein (a) comprises outputting a probabilistic assertion representative of each of the different first values for the same variable, and wherein (b) comprises combining the probabilistic assertions into a unified probabilistic assertion for the variable. 19. The method of claim 15 further comprising: (c) inferring a patient state as a function of the combined pieces of information. 20. The method of claim 19 wherein (c) comprises inferring the patient state as a function of probabilities associated with the combined pieces of information. 21. The method of claim 19 wherein (c) comprises inferring as a function of a statistical model of a pattern of evolution of a disease across a patient population and the relationship between a patient's disease and observed variables. 22. The method of claim 15 wherein (a) comprises extracting from one or more of: medical information, financial information, demographic information or combinations thereof, the at least one unstructured data source including two or more of: the free text information, medical image information, laboratory information, prescription drug information, waveform information or combinations thereof. 23. The method of claim 15 wherein (a) comprises extracting key phrases from the at least one unstructured data source, the at least one unstructured data source comprising free text treatment notes, the key phrases comprising at least part of the domain-specific criteria. 24. The method of claim 15 further comprising: (c) outputting structured clinical information with probability information. 25. The method of claim 15 wherein the domain-specific criteria includes institution-specific domain knowledge, disease-specific domain knowledge, or combinations thereof. 26. The method of claim 15 wherein the at least one unstructured data source includes one or more of: ASCII text strings, image information in DICOM format, text documents or combinations thereof partitioned based on domain knowledge. 27. A method for providing structured clinical information from patient records, the method comprising: (a) mining, by a processor, a patient record having at least one unstructured data source comprising unstructured patient information, the mining comprising mining unstructured free text information, the patient record being from a healthcare provider, the mining including extracting at least one of multiple pieces of information related to each of multiple variables;(b) creating, probabilistically by the processor, structured clinical data for each of the variables from the extracted multiple pieces of information, including the at least one piece of the unstructured patient information mined from the unstructured data source, the structured clinical data being stored for answering a question regarding patients;(c) providing (a) as a service to the healthcare provider; and(d) mining from the structured clinical data as a function of the question. 28. The method of claim 27 wherein (a) comprises mining the patient records of the healthcare provider and another healthcare provider and wherein (c) comprises providing the mining of (a) as a service to the healthcare provider and the other healthcare provider. 29. The method of claim 27 wherein (c) comprises providing the service by a third party service provider. 30. The method of claim 27 wherein (b) comprises: (b1) combining a set of probabilistic assertions into one or more unified probabilistic assertions; and(b2) inferring a patient state from the one or more unified probabilistic assertions; andwherein (c) comprises communicating the patient state. 31. The method of claim 27 wherein one or both of (a) or (b) is performed as a function of domain-specific criteria, the domain-specific criteria comprising knowledge of a disease. 32. The method of claim 31 wherein the domain-specific criteria for mining comprises institution-specific domain knowledge of the healthcare provider. 33. The method of claim 32 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. 34. The method of claim 27 wherein (a) comprises mining the at least one unstructured data source comprising one or more of medical information, financial information, demographic information or combinations thereof, wherein the medical information includes two or more of: the free text information, medical image information, laboratory information, prescription drug information, waveform information or combinations thereof. 35. The method of claim 27 further comprising: (e) assigning probability values to the structured clinical data;wherein (c) comprises communicating a probability as a function of the probability values. 36. The method of claim 27 further comprising: (e) storing the created structured clinical information in a database maintained by a service provider, the service provider being different than the healthcare provider, wherein the service provider performs (c). 37. The method of claim 27 wherein (a) comprises mining the at least one unstructured data source comprising the unstructured patient information, the unstructured patient information comprising one or more of: ASCII text strings, image information in DICOM format, text documents or combinations thereof. 38. The method of claim 27 wherein (c) comprises accessing the created structured clinical information using the Internet. 39. The method of claim 27 wherein (a) comprises running the data mining using the Internet. 40. The method of claim 27 wherein (c) comprises communicating a diagnosis. 41. The method of claim 27 wherein (c) comprises communicating corrected information related to the patient record. 42. The system of claim 1 wherein the multiple pieces of information related to the variable for the patient are represented as probabilistic assertions related to the variable about the patient at a particular time, and wherein the value of the variable for the patient is a unified probabilistic assertion related to the variable about the patient at the particular time, the unified probabilistic assertion formed from the probabilistic assertions. 43. A system for producing structured clinical information from patient records, comprising: a patient record comprising at least unstructured data and structured data; anda probabilistic data miner machine configured to (a) extract multiple pieces of information from the structured data and the unstructured data of the patient record of a patient, the extracting from the at least unstructured data comprising mining unstructured free text information, the multiple pieces indicating different first values for a same variable recorded for the patient, and configured to (b) combine the extracted multiple pieces of information into a second value of the variable representing the patient, the second value being a function of the first values recorded for the patient;wherein one or both of (a) and (b) are performed as a function of domain-specific criteria; andwherein the probabilistic data miner is configured to repeat (a) and (b) for a different variable, the repetition searching for different pieces of information relevant to the different variable and combining the different pieces of information into a value for the different variable, the variable and the different variable representing the patient at a given time. 44. The system of claim 43 wherein the probabilistic data miner is configured to perform (a) as a function of the domain-specific criteria. 45. The system of claim 43 wherein the probabilistic data miner is configured to combine in (b) as a function of the domain-specific criteria, the domain-specific criteria comprising knowledge of a disease. 46. The system of claim 43 wherein the probabilistic data miner is configured to output a probabilistic assertion representative of each of the different first values for the same variable for (a), and to combine in (b) the probabilistic assertions into a unified probabilistic assertion for the variable. 47. The system of claim 43 wherein the probabilistic data miner is configured to (c) infer a patient state as a function of the combined pieces of information. 48. The system of claim 47 wherein the probabilistic data miner is configured to infer in (c) the patient state as a function of probabilities associated with the combined pieces of information. 49. The system of claim 47 wherein the probabilistic data miner is configured to infer in (c) as a function of a statistical model of a pattern of evolution of a disease across a patient population and the relationship between a patient's disease and observed variables. 50. The system of claim 43 wherein the probabilistic data miner is configured to extract in (a) from one or more of: medical information, financial information, demographic information or combinations thereof, the at least one unstructured data source including two or more of: the free text information, medical image information, laboratory information, prescription drug information, waveform information or combinations thereof. 51. The system of claim 43 wherein the probabilistic data miner is configured to extract in (a) key phrases from the at least one unstructured data source, the at least one unstructured data source comprising free text treatment notes, the key phrases comprising at least part of the domain-specific criteria. 52. The system of claim 43 wherein the probabilistic data miner is configured to (c) output structured clinical information with probability information. 53. The system of claim 43 wherein the probabilistic data miner is configured to perform (a) and/or (b) with the domain-specific criteria including institution-specific domain knowledge, disease-specific domain knowledge, or combinations thereof. 54. The system of claim 43 wherein the free text comprises ASCII text strings, text documents or combinations thereof partitioned based on domain knowledge.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (88)
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.
Paik Woojin ; Liddy Elizabeth D. ; Liddy Jennifer Heverin ; Niles Ian Harcourt ; Allen Eileen E., Information extraction system and method using concept relation concept (CRC) triples.
Camarda, Leonard T.; Wilbur, Curtis S.; Schectman, Stephen B.; Hanson, Gregory K., Method and apparatus for improving patient compliance with prescriptions.
Lombardo,Joseph S.; Pineda,Fernando J.; Burkom,Howard S.; Newhall,Bruce K.; Chotani,Rashid A.; Wojcik,Richard A.; Loschen,Wayne A., Method and system for bio-surveillance detection and alerting.
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.
Colon Michael ; Marks Ronald G. ; Pepine Carl J. ; Handberg-Thurmond Eileen M. ; Cooper-DeHoff Rhonda M. ; Padgett Phillip, Method and system for interactive prescription and distribution of prescriptions in conducting clinical studies.
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.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.