CA2247896C - A method for generating text from selected medical findings - Google Patents
A method for generating text from selected medical findings Download PDFInfo
- Publication number
- CA2247896C CA2247896C CA002247896A CA2247896A CA2247896C CA 2247896 C CA2247896 C CA 2247896C CA 002247896 A CA002247896 A CA 002247896A CA 2247896 A CA2247896 A CA 2247896A CA 2247896 C CA2247896 C CA 2247896C
- Authority
- CA
- Canada
- Prior art keywords
- medical
- phrase
- descriptive
- findings
- phrases
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/131—Fragmentation of text files, e.g. creating reusable text-blocks; Linking to fragments, e.g. using XInclude; Namespaces
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
A method for generating sentences of text for selected medical findings in an electronic medical diagnostic system (10) is disclosed. First, a descriptive phrase for each medical finding is created. Each descriptive phrase is then analyzed to determine possible truncation points for modifying the descriptive phrase of one medical finding if another medical finding is also selected. A code at each possible truncation point is then entered into the phrase. Language to be inserted at each of the truncation points is then created and the descriptive phrase and modifying language are stored in database file (20) and knowledge base file (22).
Finally, the stored descriptive phrases and modifying language are then combined to form a readable text on display (12) for the medical findings selected from the databases.
Finally, the stored descriptive phrases and modifying language are then combined to form a readable text on display (12) for the medical findings selected from the databases.
Description
-1_ ._ .:A METHOD FOR GENERATING TENT -~ -..__ ..._. ... ...
FROM SELECTED MEDICAL FINDINGS
FIELD OF THE IlWENTION
The present invention relates to a method and apparatus for producing a readable and coherent narrative from a plurality of findings stored in a hierarchial database.
BACKGROUND OF TI3E IN~ENTIOf~1 While many aspects of the operation and administration at hospitals and other healthcare facilities have been computerized over the past years, one of the most important aspects, the generation of patient charts, the updating of these charts and the generation of care plans by healthcare professionals such as doctors, nurses, therapists, and the Iike, is still performed largely by hand. As a result, while a patient chart of some type is normally generated shortly after a patient is admitted to the healthcare facility for a particular service, for example, an intensive care unit, cardiac surgery unit, or the like, the chart may not always be updated to reflect actual progress by the patient.
Even after a diagnosis has been made and a care plan has been devised, the patient chart may not be referred to when the healthcare professional is preparing progress notes on the patient. Thus, there is no check to assure that the original treatments have in fact been followed, or that proposed resolution dates in the chart have been met. or updated. When changes in the chart are made as a result of changes in the status of a patient, such changes are frequently not entered in the original chart.
Thus, good archival records are not generally maintained for changes in treatment.
The professional notes for a particular patient frequently do not include an updated version of the patient's chart. Further, even though a form may be available for progress notes, the form does not take into account the unique problems of the individual patent, and does not give the healthcare professional a checklist of items to be investigated for such problems or suggested interventions or resolution dates for the particular patient problem. When changes are made or expected outcomes are not WO 97!32272 PCT/US97/02786 achieved, the reasons for such occurrences are seldom provided, making any further review far more difficult. Again, a good archival record of what has been done for ' the particular patient is not readily available. Because of the absence of good archival records, and the absence of reasons for changes or deviations, tracking a problem for quality control, Legal or other reasons is difficult, and it is difficult to research the relative effectiveness of various interventions or to perform other research from the records.
The lack of a complete archival record can also cause significant problems for healthcare professionals who must adequately document the examination and treatment IO of patients whose medical bills are being paid by insurance companies. If the healthcare professional does not provide proper documentation, the insurance companies will not pay the bil's. Furthermore, healthcare professionals have less time to spend with each patient these days. As a result, the heaithcare professional does not have time to figure out from the original chart and the added progress notes, if they are available, the previous problems of the patient and what treatments were prescribed. Thus, the healthcare professional needs to have an easy way to review charts for each patient.
Even with dictated, free text-based computer patient chart and/or progress note systems, many of the problems indicated above still exist. Such systems also in many instances lack flexibility so as to be configurable by the healthcare professional so as to provide specific help in locating or entering information and for prompting the healthcare professional with Lists of symptoms, questions which should be asked and tests that should be performed in certain circumstances. In addition, they frequently do not give the healtllcare professional the ability to add special instructions or to add items as required. Further, it is generally not possible to obtain either an updated chart or historical chart upon request. Thus, there is a need for a computer medical , system based on coded medical findings in a logical hierarchical database structure which enhances the diagnostic capabilities of a heaithcare provider, provides ' structured patient charts as well as formatted updated or historical care plans.
However, the problem with hierarchical database structures is the display of the medical findings. An indented outline format wastes space. However, due to the hierarchical structure of the medical findings where there are many subsets and subsets of subsets for each medical finding, a straightforward linking of phrases would produce a narrative which is difficult to read. In addition, creating the negative of a phrase can produce gibberish. For example, a subset of trauma includes head, chest, abdomen, etc. A person subjected to chest trauma but not to head trauma would generate the sentence: trauma chest no head. Thus, there is a need for a phrasing structure for producing a coherent narrative display of medical findings.
SIJ1~IVIARY OF THE INVENTION
It is an object of the present invention to overcome the problems cited above by providing a method and apparatus for producing coherent phrasing structure for a narrative based on selected informational findings stored in a hierarchical database.
According to one embodiment of the present invention, a method for generating sentences of text for selected medical findings in an electronic medical diagnostic system is disclosed. First, a descriptive phrase for each medical finding is created. Each descriptive phrase is then analyzed to determine possible truncation points for modifying the descriptive phrase of one medical finding if another medical finding is also selected. A code at each possible truncation point is then entered into the phrase. Language to be inserted at each of the truncation points is then created and the descriptive phrase and modifying language are stored. Finally, the stored descriptive phrases and modifying language are then combined to form a readable text for the medical findings selected from the database.
BRIEF DESCRIPTION OF THE DRAWINGS
These and other features and advantages of the present invention will be readily apparent to one of ordinary skill in the art from the following written description, used in conjunction with the drawings, in which:
Figure 1 illustrates a block diagram of a computer based medical system according to one embodiment of the present invention;
Figure 2 illustrates a flowchart describing the operation of one embodiment of the present invention; and Figure 3 illustrates an example of a stored hierarchical structure for a medical - finding according to one embodiment of the present invention. , DETAILED DESCRIPTION
The present invention can be applied to any situation where a narrative needs to be created for a plurality of findings which are stored in a coded hierarchical database. It will be apparent to one skilled in the art that many fields such as medicine, law, engineering, etc. use hierarchical databases and that the present invention can be used in aII of these fields. The present invention will be explained using a computer based medical system with a hierarchical medical findings database or an example. It will be understood that the present invention is not limited thereto.
A block diagram of the computer based medical system suitable for use in practicing the teachings of the present invention is illustrated in Figure 1. The medical system 10 contains a processor 16 with one or more input devices such as a keyboard 18.
IS The processor 16 also has a database file or memory 20 and a knowledge base file or memory 22. The processor i6 operates a standard display controller I4 which in turn controls a display device 12 at the workstation. The display device 12 can be any standard type of display monitor, attached or wireless. Furthermore, the apparatus 10 can be networked to other such medical systems not illustrated which can be placed around the hospital or healthcare facility. This allows multiple people to use the healthcare system for the same or for multiple patients.
The present invention is based upon medical findings. Medical findings are defined as symptoms, history, physical findings, diagnoses, tests, and therapy which may be present for a particular patient. The database file 20 contains over 50,000 medical findings and is divided into categories such as symptoms, history, physical findings, diagnoses, tests, and therapy. Furthermore, the descriptions of the medical findings stored in the database memory 20 are hierarchical and can have up to 8 levels of description. The first level gives the simplest explanation of a medical fording, for example, a cough. The explanations become more detailed the lower the level.
As noted above, a first level finding may be a cough while a second Level fording may be a brassy cough. Another feature of the database file 20 is that all of the medical findings are coded so as to be distinct from each other. For example, each medical finding can be assigned an internal number which uniquely identifies that particular medical fording. in addition, each medical fording also contains a code which indicates which category within the database file 20 the medical finding is associated with. For example, a medical finding may contain the code SYM to indicate that the medical finding is associated with the symptom section; HIS to indicate that the medical finding is associated with the history section; PHY to indicate that the medical finding is associated with the physical section; DIS to indicate that the medical finding is associated with the diagnoses section; TST to indicate that the medical finding is associated with the test section: and RX to indicate that the medical finding is associated wirh the therapy section.
As noted above, the medical system 10 also contains a knowledge base file 22.
The knowledge base file 22 contains a detailed description of over 2000 diagnoses.
The detailed description of the diagnoses uses the medical finding terms which are stored in the database file 20. For each diagnosis, each medical finding associated with the diagnosis is assigned a numerical value depending on how important such a medical finding may be to the diagnosis. For example, in the detailed description of the diagnosis for coronary artery stenosis, medical findings such as chest pain or discomfort and dyspnea (shortness of breath), which are a strong showing of coronary artery stenosis, will be given high values while a lack of an appetite may not be described in the diagnosis at all or given a very low value. For example, the medical findings can be assigned values between 0 and 20 wherein the value 20 is the highest value that can be given to an important medical finding, however, the invention is not limited thereto. Thus, the values assigned to each medical finding within the detailed description is proportional to how important such a medical fording is to the diagnosis. Furthermore, the values can vary for a given medical fznding depending on a plurality of factors such as age of the patient and timeframe, i.e., when a symptom occurred in relation to other symptoms. For example, a white blood cell count of 18,000 may be given a high value if the patient is an adult while the same medical finding is not Qiven a value at all if the patient is a new-born child because this is normal for a new-born child.
-b-Here again, the medical findings used in the detailed description of the diagnosis are all coded. In addition; 'over 400,000 liiiks~are~provided between~the database file 20 and the knowledge base file 22. In other words, the findings in the database file 20 occur over 400,000 times in the knowledge base file 22.
The detailed description of the diagnoses stored in the knowledge base f le 22 contain Iists of symptoms as well as personal and family history and physical findings that a patient should or may have experienced. In addition, the detailed diagnoses contain lists of tests, possible therapies, and medications which might be prescribed for the patient if the healthcare professional decides that the patient is experiencing a particular illness or problem.
A patient chart is created by selecting various medical findings in the database file 20 which are being displayed by a clinical protocol or a template on the display screen 18. Clinical protocols are a structured combination of coded medical phrases selected from the database file 20 which are related or associated with a particular disease or problem. The creation of patient charts is explained in more detail in U.S.
Patent Application No. 08/609,828, entitled "Creating and Using Protocols to Create a Patient Chart, " which is being filed concurrently herewith .
When it is necessary to generate a patient's chart, the present invention provides a phrasing structure so that a medical chart or care plan created using a medical system 10 can be produced on paper or on the display screen with a coherent text. In other words, rather than simply printing out a chart or care plan with a plurality of indented medical fzndings entered into the various sections of the chart or care plan, the present invention provides a method for changing the entered medical findings into a coherent narrative with sentence and paragraph structure. The phrasing structure according to the present invention includes controls for determining how much of a phrase should be used, where values need to be inserted, and what term or alternate phrase is to be used when the negative of the medical finding is selected .
The phrasing structure of the present invention will now be described in more detail with reference to the flowchart illustrated in Figure 2. As noted above, medical _7_ findings and other terms are stored in the database 20. For each medical finding, a descriptive phrase is written for each te,.~m. If there are to be subsidiary terms, the phrase is analyzed to see where to break the phrase for the combination of the phrase and the subsidiary phrases to read correctly. This is performed by entering one of a plurality of codes at the designated mandatory or conditional truncation point. These descriptive phrases are then stored in a location identified by the internal number code of the medical fording for which the descriptive phrase has been generated.
In one embodiment of the present invention, a plurality of codes are provided to shorten a phrase, make a phrase negative, insert a value into the phrase, change the status of the phrase or a term within the phrase, indicate a test result level, modify the phrase by adding an adjective or adverb, or for deleting and adding terms to the phrase. For example, the code " 'T" can be used to indicate a possible truncation point within a phrase. The code "'C" can be used to indicate a conditional shortening of the phrase. The code "-V" is used to indicate a place within the phrase were a value can be inserted. The codes " 'L" and " 'M" indicate places within the phrase where adverbs or adjectives, respectively, can be added. The code "-S"
is used to indicate the status, i.e., history, family history, etc., of a term in the phrase.
The code " 'R" is used to modify a phrase to indicate whether test results were high, low, abnormal, etc. Finally, the code "'#.# (phrase or word)" can be used to modify a positive phrase, wherein the first number in the code indicates the number of words to skip in the positive phrase, the second number indicates the number of words which are deleted and the word or phrase following the second number in the code are inserted into the positive phrase in place of the deleted words. It will be understood ti~.~tt_~'_7 P P ~.Teyi~~ ~ndP arP 01- PTt (171~V ~ an exa T P of r cihln n sac ni~;nl, L.ilaL ~lvW ~=J ,~~ ~~~ ~J ~~/IV V1 ~J~J1V1W v~~.W rJ ~llll..ll-lrVlild be used in the present invention and the present invention is not limited thereto.
For each hierarchical level of a medical finding, a positive phrase and possibly a negative version of the positive phrase are stored. In this example, the negative version always operates on the positive phrase by either deleting and replacing some words in the phrase or by replacing the entire phrase. Likewise, the positive and negative descriptive phrases at lower levels of the hierarchy operate on the higher level phrases as will be illustrated below in the discussion concerning Figure 3. It WO 97/32272 ' PCT/US97/0278G
_g_ will be understood however, that equivalent files may exist in such a way to allow a sentence to be started or formed for a medical finding na matter what hierarchical Ievei is accessed.
When a medical fording is selected to be included in a patient chart, the medical finding is stored with a plurality of codes. For example, the internal number code which identifies the medical finding is stored with the medical finding along with a code which indicates whether positive or negative has been selected for the medical finding. Thus, when the narrative is produced, the system knows whether to use the positive phrase or the negative modification for each medical finding by looking at the codes.
According to one embodiment of the present invention, the healthcare professional can select different formats in which the narrative is produced.
For example, a technical format can be selected wherein the narrative is produced using technical or medical phrases that will be understood by a healthcare professional but maybe not understood by a lay person. If the narrative is going to be read by a lay person, the healthcare professional can select the non-technical format which produces a narrative in plain and simple to understand terms. Furthermore, either the technical or non-technical format can be selected and be reproduced in a variety of different languages, for example, English, Spanish, French, German, etc. This is accomplished by creating technical and non-technical phrases and sentences for each medical finding in each language desired. Each of the phrases is then stored along with a code which tells the system that the phrase is technical or non-technical as well as a code for indicating the language of that particular phrase. Thus, when the healthcare professional selects the non-technical format in Spanish off of the display screen, the system creates a narrative for all of the selected medical findings using the stored phrases and sentences with the codes that indicate the non-technical format and the selection of the Spanish language.
'Figure 3 illustrates an example of code usage to create readable phrases for medical findings. In this example, the medical finding is for heart sounds.
The medical finding for heart sounds has a plus sign displayed next to it. The plus sign indicates that there are several levels of responses for the general medical finding of _g_ heart sounds. The first level states that "the heart sounds were abnormal. "
The second level states that "the S 1 was abnormal. " Finally, the third level states that "the S 1 was mildly diminished. " Along with each positive recitation of the medical finding is also a coded negative phrase. Thus, if the healthcare professional selects the positive response by pointing at the first three letters in the phrase "heart sounds,"
the phrase reads as is, i.e., "the heart sounds were abnormal." However, if the healthcare professional selects the negative response for the top level, the system looks at the coded message "-5.1 normal" and counts out 5 words as indicated by the 5 and deletes one word as indicated by the 1, thus deleting the word "abnormal" and adds to the sentence "normal. " Thus, the sentence would read: "The heart sounds were normal. " If the healthcare professional decides to use the second level description, and the positive message is selected, the system looks at the coded message "The S 1-T was abnormal. " The coded value " -T" removes all of the level I message and adds the layer 2 phrase. Thus, the phrase will read: "The S 1 was IS abnormal. " Here again, if the negative of the second level is selected, the system looks at the coded message "-4.I normal" and counts out 4 words and removes I
word, thus removing "abnormal" and inserting "normal" into the sentence. The sentence would thus read: "The S 1 was normal. "
If the heaithcare professional uses the level 3 description for heart sounds, the level 2 message is truncated after "S I " and the layer 3 message is added. In this example, there is a code "-L" which indicates that a modifier may be added if selected by the healthcare professional, for example, mildly. In this case, the sentence will read: "The S 1 was mildly diminished. " However, if the negative response for the layer 3 description is selected and no modifier was selected, the system counts out 1 word and adds "not" and then removes the code " "L. " The result would read: "The S I was not diminished. " in all cases, the phrases are printed ' without the codes.
The principles, preferred embodiments and the modes of operation of the present operation have been described in the foregoing specification. However, the invention which is intended to be protected is not to be construed as limited to the particular embodiments disclosed. Further, the embodiments described herein are to be regarded as illustrative rather than restrictive. Variations and changes may be made by others, and equivalents employed, without departing from the spirit of the present invention. Accordingly, it is expressly intended that all such variations, changes, and equivalents which fall within the spirit and scope of the present invention as defined in the claims be embraced thereby.
FROM SELECTED MEDICAL FINDINGS
FIELD OF THE IlWENTION
The present invention relates to a method and apparatus for producing a readable and coherent narrative from a plurality of findings stored in a hierarchial database.
BACKGROUND OF TI3E IN~ENTIOf~1 While many aspects of the operation and administration at hospitals and other healthcare facilities have been computerized over the past years, one of the most important aspects, the generation of patient charts, the updating of these charts and the generation of care plans by healthcare professionals such as doctors, nurses, therapists, and the Iike, is still performed largely by hand. As a result, while a patient chart of some type is normally generated shortly after a patient is admitted to the healthcare facility for a particular service, for example, an intensive care unit, cardiac surgery unit, or the like, the chart may not always be updated to reflect actual progress by the patient.
Even after a diagnosis has been made and a care plan has been devised, the patient chart may not be referred to when the healthcare professional is preparing progress notes on the patient. Thus, there is no check to assure that the original treatments have in fact been followed, or that proposed resolution dates in the chart have been met. or updated. When changes in the chart are made as a result of changes in the status of a patient, such changes are frequently not entered in the original chart.
Thus, good archival records are not generally maintained for changes in treatment.
The professional notes for a particular patient frequently do not include an updated version of the patient's chart. Further, even though a form may be available for progress notes, the form does not take into account the unique problems of the individual patent, and does not give the healthcare professional a checklist of items to be investigated for such problems or suggested interventions or resolution dates for the particular patient problem. When changes are made or expected outcomes are not WO 97!32272 PCT/US97/02786 achieved, the reasons for such occurrences are seldom provided, making any further review far more difficult. Again, a good archival record of what has been done for ' the particular patient is not readily available. Because of the absence of good archival records, and the absence of reasons for changes or deviations, tracking a problem for quality control, Legal or other reasons is difficult, and it is difficult to research the relative effectiveness of various interventions or to perform other research from the records.
The lack of a complete archival record can also cause significant problems for healthcare professionals who must adequately document the examination and treatment IO of patients whose medical bills are being paid by insurance companies. If the healthcare professional does not provide proper documentation, the insurance companies will not pay the bil's. Furthermore, healthcare professionals have less time to spend with each patient these days. As a result, the heaithcare professional does not have time to figure out from the original chart and the added progress notes, if they are available, the previous problems of the patient and what treatments were prescribed. Thus, the healthcare professional needs to have an easy way to review charts for each patient.
Even with dictated, free text-based computer patient chart and/or progress note systems, many of the problems indicated above still exist. Such systems also in many instances lack flexibility so as to be configurable by the healthcare professional so as to provide specific help in locating or entering information and for prompting the healthcare professional with Lists of symptoms, questions which should be asked and tests that should be performed in certain circumstances. In addition, they frequently do not give the healtllcare professional the ability to add special instructions or to add items as required. Further, it is generally not possible to obtain either an updated chart or historical chart upon request. Thus, there is a need for a computer medical , system based on coded medical findings in a logical hierarchical database structure which enhances the diagnostic capabilities of a heaithcare provider, provides ' structured patient charts as well as formatted updated or historical care plans.
However, the problem with hierarchical database structures is the display of the medical findings. An indented outline format wastes space. However, due to the hierarchical structure of the medical findings where there are many subsets and subsets of subsets for each medical finding, a straightforward linking of phrases would produce a narrative which is difficult to read. In addition, creating the negative of a phrase can produce gibberish. For example, a subset of trauma includes head, chest, abdomen, etc. A person subjected to chest trauma but not to head trauma would generate the sentence: trauma chest no head. Thus, there is a need for a phrasing structure for producing a coherent narrative display of medical findings.
SIJ1~IVIARY OF THE INVENTION
It is an object of the present invention to overcome the problems cited above by providing a method and apparatus for producing coherent phrasing structure for a narrative based on selected informational findings stored in a hierarchical database.
According to one embodiment of the present invention, a method for generating sentences of text for selected medical findings in an electronic medical diagnostic system is disclosed. First, a descriptive phrase for each medical finding is created. Each descriptive phrase is then analyzed to determine possible truncation points for modifying the descriptive phrase of one medical finding if another medical finding is also selected. A code at each possible truncation point is then entered into the phrase. Language to be inserted at each of the truncation points is then created and the descriptive phrase and modifying language are stored. Finally, the stored descriptive phrases and modifying language are then combined to form a readable text for the medical findings selected from the database.
BRIEF DESCRIPTION OF THE DRAWINGS
These and other features and advantages of the present invention will be readily apparent to one of ordinary skill in the art from the following written description, used in conjunction with the drawings, in which:
Figure 1 illustrates a block diagram of a computer based medical system according to one embodiment of the present invention;
Figure 2 illustrates a flowchart describing the operation of one embodiment of the present invention; and Figure 3 illustrates an example of a stored hierarchical structure for a medical - finding according to one embodiment of the present invention. , DETAILED DESCRIPTION
The present invention can be applied to any situation where a narrative needs to be created for a plurality of findings which are stored in a coded hierarchical database. It will be apparent to one skilled in the art that many fields such as medicine, law, engineering, etc. use hierarchical databases and that the present invention can be used in aII of these fields. The present invention will be explained using a computer based medical system with a hierarchical medical findings database or an example. It will be understood that the present invention is not limited thereto.
A block diagram of the computer based medical system suitable for use in practicing the teachings of the present invention is illustrated in Figure 1. The medical system 10 contains a processor 16 with one or more input devices such as a keyboard 18.
IS The processor 16 also has a database file or memory 20 and a knowledge base file or memory 22. The processor i6 operates a standard display controller I4 which in turn controls a display device 12 at the workstation. The display device 12 can be any standard type of display monitor, attached or wireless. Furthermore, the apparatus 10 can be networked to other such medical systems not illustrated which can be placed around the hospital or healthcare facility. This allows multiple people to use the healthcare system for the same or for multiple patients.
The present invention is based upon medical findings. Medical findings are defined as symptoms, history, physical findings, diagnoses, tests, and therapy which may be present for a particular patient. The database file 20 contains over 50,000 medical findings and is divided into categories such as symptoms, history, physical findings, diagnoses, tests, and therapy. Furthermore, the descriptions of the medical findings stored in the database memory 20 are hierarchical and can have up to 8 levels of description. The first level gives the simplest explanation of a medical fording, for example, a cough. The explanations become more detailed the lower the level.
As noted above, a first level finding may be a cough while a second Level fording may be a brassy cough. Another feature of the database file 20 is that all of the medical findings are coded so as to be distinct from each other. For example, each medical finding can be assigned an internal number which uniquely identifies that particular medical fording. in addition, each medical fording also contains a code which indicates which category within the database file 20 the medical finding is associated with. For example, a medical finding may contain the code SYM to indicate that the medical finding is associated with the symptom section; HIS to indicate that the medical finding is associated with the history section; PHY to indicate that the medical finding is associated with the physical section; DIS to indicate that the medical finding is associated with the diagnoses section; TST to indicate that the medical finding is associated with the test section: and RX to indicate that the medical finding is associated wirh the therapy section.
As noted above, the medical system 10 also contains a knowledge base file 22.
The knowledge base file 22 contains a detailed description of over 2000 diagnoses.
The detailed description of the diagnoses uses the medical finding terms which are stored in the database file 20. For each diagnosis, each medical finding associated with the diagnosis is assigned a numerical value depending on how important such a medical finding may be to the diagnosis. For example, in the detailed description of the diagnosis for coronary artery stenosis, medical findings such as chest pain or discomfort and dyspnea (shortness of breath), which are a strong showing of coronary artery stenosis, will be given high values while a lack of an appetite may not be described in the diagnosis at all or given a very low value. For example, the medical findings can be assigned values between 0 and 20 wherein the value 20 is the highest value that can be given to an important medical finding, however, the invention is not limited thereto. Thus, the values assigned to each medical finding within the detailed description is proportional to how important such a medical fording is to the diagnosis. Furthermore, the values can vary for a given medical fznding depending on a plurality of factors such as age of the patient and timeframe, i.e., when a symptom occurred in relation to other symptoms. For example, a white blood cell count of 18,000 may be given a high value if the patient is an adult while the same medical finding is not Qiven a value at all if the patient is a new-born child because this is normal for a new-born child.
-b-Here again, the medical findings used in the detailed description of the diagnosis are all coded. In addition; 'over 400,000 liiiks~are~provided between~the database file 20 and the knowledge base file 22. In other words, the findings in the database file 20 occur over 400,000 times in the knowledge base file 22.
The detailed description of the diagnoses stored in the knowledge base f le 22 contain Iists of symptoms as well as personal and family history and physical findings that a patient should or may have experienced. In addition, the detailed diagnoses contain lists of tests, possible therapies, and medications which might be prescribed for the patient if the healthcare professional decides that the patient is experiencing a particular illness or problem.
A patient chart is created by selecting various medical findings in the database file 20 which are being displayed by a clinical protocol or a template on the display screen 18. Clinical protocols are a structured combination of coded medical phrases selected from the database file 20 which are related or associated with a particular disease or problem. The creation of patient charts is explained in more detail in U.S.
Patent Application No. 08/609,828, entitled "Creating and Using Protocols to Create a Patient Chart, " which is being filed concurrently herewith .
When it is necessary to generate a patient's chart, the present invention provides a phrasing structure so that a medical chart or care plan created using a medical system 10 can be produced on paper or on the display screen with a coherent text. In other words, rather than simply printing out a chart or care plan with a plurality of indented medical fzndings entered into the various sections of the chart or care plan, the present invention provides a method for changing the entered medical findings into a coherent narrative with sentence and paragraph structure. The phrasing structure according to the present invention includes controls for determining how much of a phrase should be used, where values need to be inserted, and what term or alternate phrase is to be used when the negative of the medical finding is selected .
The phrasing structure of the present invention will now be described in more detail with reference to the flowchart illustrated in Figure 2. As noted above, medical _7_ findings and other terms are stored in the database 20. For each medical finding, a descriptive phrase is written for each te,.~m. If there are to be subsidiary terms, the phrase is analyzed to see where to break the phrase for the combination of the phrase and the subsidiary phrases to read correctly. This is performed by entering one of a plurality of codes at the designated mandatory or conditional truncation point. These descriptive phrases are then stored in a location identified by the internal number code of the medical fording for which the descriptive phrase has been generated.
In one embodiment of the present invention, a plurality of codes are provided to shorten a phrase, make a phrase negative, insert a value into the phrase, change the status of the phrase or a term within the phrase, indicate a test result level, modify the phrase by adding an adjective or adverb, or for deleting and adding terms to the phrase. For example, the code " 'T" can be used to indicate a possible truncation point within a phrase. The code "'C" can be used to indicate a conditional shortening of the phrase. The code "-V" is used to indicate a place within the phrase were a value can be inserted. The codes " 'L" and " 'M" indicate places within the phrase where adverbs or adjectives, respectively, can be added. The code "-S"
is used to indicate the status, i.e., history, family history, etc., of a term in the phrase.
The code " 'R" is used to modify a phrase to indicate whether test results were high, low, abnormal, etc. Finally, the code "'#.# (phrase or word)" can be used to modify a positive phrase, wherein the first number in the code indicates the number of words to skip in the positive phrase, the second number indicates the number of words which are deleted and the word or phrase following the second number in the code are inserted into the positive phrase in place of the deleted words. It will be understood ti~.~tt_~'_7 P P ~.Teyi~~ ~ndP arP 01- PTt (171~V ~ an exa T P of r cihln n sac ni~;nl, L.ilaL ~lvW ~=J ,~~ ~~~ ~J ~~/IV V1 ~J~J1V1W v~~.W rJ ~llll..ll-lrVlild be used in the present invention and the present invention is not limited thereto.
For each hierarchical level of a medical finding, a positive phrase and possibly a negative version of the positive phrase are stored. In this example, the negative version always operates on the positive phrase by either deleting and replacing some words in the phrase or by replacing the entire phrase. Likewise, the positive and negative descriptive phrases at lower levels of the hierarchy operate on the higher level phrases as will be illustrated below in the discussion concerning Figure 3. It WO 97/32272 ' PCT/US97/0278G
_g_ will be understood however, that equivalent files may exist in such a way to allow a sentence to be started or formed for a medical finding na matter what hierarchical Ievei is accessed.
When a medical fording is selected to be included in a patient chart, the medical finding is stored with a plurality of codes. For example, the internal number code which identifies the medical finding is stored with the medical finding along with a code which indicates whether positive or negative has been selected for the medical finding. Thus, when the narrative is produced, the system knows whether to use the positive phrase or the negative modification for each medical finding by looking at the codes.
According to one embodiment of the present invention, the healthcare professional can select different formats in which the narrative is produced.
For example, a technical format can be selected wherein the narrative is produced using technical or medical phrases that will be understood by a healthcare professional but maybe not understood by a lay person. If the narrative is going to be read by a lay person, the healthcare professional can select the non-technical format which produces a narrative in plain and simple to understand terms. Furthermore, either the technical or non-technical format can be selected and be reproduced in a variety of different languages, for example, English, Spanish, French, German, etc. This is accomplished by creating technical and non-technical phrases and sentences for each medical finding in each language desired. Each of the phrases is then stored along with a code which tells the system that the phrase is technical or non-technical as well as a code for indicating the language of that particular phrase. Thus, when the healthcare professional selects the non-technical format in Spanish off of the display screen, the system creates a narrative for all of the selected medical findings using the stored phrases and sentences with the codes that indicate the non-technical format and the selection of the Spanish language.
'Figure 3 illustrates an example of code usage to create readable phrases for medical findings. In this example, the medical finding is for heart sounds.
The medical finding for heart sounds has a plus sign displayed next to it. The plus sign indicates that there are several levels of responses for the general medical finding of _g_ heart sounds. The first level states that "the heart sounds were abnormal. "
The second level states that "the S 1 was abnormal. " Finally, the third level states that "the S 1 was mildly diminished. " Along with each positive recitation of the medical finding is also a coded negative phrase. Thus, if the healthcare professional selects the positive response by pointing at the first three letters in the phrase "heart sounds,"
the phrase reads as is, i.e., "the heart sounds were abnormal." However, if the healthcare professional selects the negative response for the top level, the system looks at the coded message "-5.1 normal" and counts out 5 words as indicated by the 5 and deletes one word as indicated by the 1, thus deleting the word "abnormal" and adds to the sentence "normal. " Thus, the sentence would read: "The heart sounds were normal. " If the healthcare professional decides to use the second level description, and the positive message is selected, the system looks at the coded message "The S 1-T was abnormal. " The coded value " -T" removes all of the level I message and adds the layer 2 phrase. Thus, the phrase will read: "The S 1 was IS abnormal. " Here again, if the negative of the second level is selected, the system looks at the coded message "-4.I normal" and counts out 4 words and removes I
word, thus removing "abnormal" and inserting "normal" into the sentence. The sentence would thus read: "The S 1 was normal. "
If the heaithcare professional uses the level 3 description for heart sounds, the level 2 message is truncated after "S I " and the layer 3 message is added. In this example, there is a code "-L" which indicates that a modifier may be added if selected by the healthcare professional, for example, mildly. In this case, the sentence will read: "The S 1 was mildly diminished. " However, if the negative response for the layer 3 description is selected and no modifier was selected, the system counts out 1 word and adds "not" and then removes the code " "L. " The result would read: "The S I was not diminished. " in all cases, the phrases are printed ' without the codes.
The principles, preferred embodiments and the modes of operation of the present operation have been described in the foregoing specification. However, the invention which is intended to be protected is not to be construed as limited to the particular embodiments disclosed. Further, the embodiments described herein are to be regarded as illustrative rather than restrictive. Variations and changes may be made by others, and equivalents employed, without departing from the spirit of the present invention. Accordingly, it is expressly intended that all such variations, changes, and equivalents which fall within the spirit and scope of the present invention as defined in the claims be embraced thereby.
Claims (11)
1. A method for generating sequences of text for medical findings in an electronic medical diagnostic system, comprising:
storing descriptive phrases associated with the medical findings and modifying language in a hierarchical database, wherein the descriptive phrases include embedded codes and wherein lower layered modifying language modifies higher layered phrases;
receiving selections of a) medical findings and b) characteristics of the medical findings; and combining modifying language with the descriptive phrases associated with the selected medical finding according to the codes embedded in the descriptive phrases and the selected characteristics, to form written text from the selected medical findings.
storing descriptive phrases associated with the medical findings and modifying language in a hierarchical database, wherein the descriptive phrases include embedded codes and wherein lower layered modifying language modifies higher layered phrases;
receiving selections of a) medical findings and b) characteristics of the medical findings; and combining modifying language with the descriptive phrases associated with the selected medical finding according to the codes embedded in the descriptive phrases and the selected characteristics, to form written text from the selected medical findings.
2. A method according to claim 1, wherein said descriptive phrases are complete sentences.
3. A method according to claim 1, wherein said modifying language is used to create a negative form of the descriptive phrase.
4. A method according to claim 1, further comprising the step of placing codes in said descriptive phrases wherein numerical values need to be entered into the phrase.
5. A method according to claim 1, wherein hierarchical level numbers can be assigned to each descriptive phrase to determine whether the selected phrase should start a new sentence or paragraph.
6. A method according to claim 1, wherein said medical findings are stored in a database, wherein the database contains a symptoms section, a history section, a physical finds section, a diagnosis section, a test section, and a therapy section.
7. A method according to claim 6, wherein a narrative for selected medical findings in each section of the database can be generated.
8. A method according to claim 1, wherein a number is stored with each descriptive phrase so as to allow substitution of an equivalent descriptive phrase in a different language when requested.
9. The method of claim 1, wherein the selections are provided by a health care professional.
10. The method of claim 1, wherein modifying language is inserted into embedded code locations within the descriptive phrases.
11. The method of claim 1, wherein at least one of the embedded code locations is a possible truncation point for modifying the descriptive phrase of one medical finding if another medical finding is also selected.
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US08/609,835 US5802495A (en) | 1996-03-01 | 1996-03-01 | Phrasing structure for the narrative display of findings |
| US08/609,835 | 1996-03-01 | ||
| PCT/US1997/002786 WO1997032272A1 (en) | 1996-03-01 | 1997-02-25 | A method for generating text from selected medical findings |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CA2247896A1 CA2247896A1 (en) | 1997-09-04 |
| CA2247896C true CA2247896C (en) | 2005-04-26 |
Family
ID=24442537
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CA002247896A Expired - Fee Related CA2247896C (en) | 1996-03-01 | 1997-02-25 | A method for generating text from selected medical findings |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US5802495A (en) |
| EP (1) | EP0892959A4 (en) |
| CA (1) | CA2247896C (en) |
| WO (1) | WO1997032272A1 (en) |
Families Citing this family (73)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| USRE43433E1 (en) | 1993-12-29 | 2012-05-29 | Clinical Decision Support, Llc | Computerized medical diagnostic and treatment advice system |
| US6206829B1 (en) | 1996-07-12 | 2001-03-27 | First Opinion Corporation | Computerized medical diagnostic and treatment advice system including network access |
| US5660176A (en) | 1993-12-29 | 1997-08-26 | First Opinion Corporation | Computerized medical diagnostic and treatment advice system |
| US5935060A (en) * | 1996-07-12 | 1999-08-10 | First Opinion Corporation | Computerized medical diagnostic and treatment advice system including list based processing |
| US6003007A (en) * | 1996-03-28 | 1999-12-14 | Dirienzo; Andrew L. | Attachment integrated claims system and operating method therefor |
| US7076436B1 (en) * | 1996-07-08 | 2006-07-11 | Rlis, Inc. | Medical records, documentation, tracking and order entry system |
| US5956667A (en) * | 1996-11-08 | 1999-09-21 | Research Foundation Of State University Of New York | System and methods for frame-based augmentative communication |
| IL131873A0 (en) | 1997-03-13 | 2001-03-19 | First Opinion Corp | Disease management system |
| US6192345B1 (en) * | 1997-03-21 | 2001-02-20 | Marc Edward Chicorel | Computer keyboard-generated medical progress notes via a coded diagnosis-based language |
| US6289316B1 (en) * | 1997-03-25 | 2001-09-11 | International Business Machines Corporation | Progress notes model in a clinical information system |
| US7801740B1 (en) | 1998-09-22 | 2010-09-21 | Ronald Peter Lesser | Software device to facilitate creation of medical records, medical letters, and medical information for billing purposes |
| US7647234B1 (en) | 1999-03-24 | 2010-01-12 | Berkeley Heartlab, Inc. | Cardiovascular healthcare management system and method |
| UA73967C2 (en) | 2000-02-14 | 2005-10-17 | First Opinion Corp | Structure-based automatic processing for diagnostics (variants) |
| US6607482B1 (en) | 2000-11-28 | 2003-08-19 | Jacob Teitelbaum | Automated questionnaire for assisting in the diagnosis and treatment of medical problems and for data gathering, analysis and organization to make a complete medical history and illness record |
| US20030208108A1 (en) * | 2000-12-01 | 2003-11-06 | Shewmake David T. | Cardiovascular healthcare management system and method |
| US20020103811A1 (en) * | 2001-01-26 | 2002-08-01 | Fankhauser Karl Erich | Method and apparatus for locating and exchanging clinical information |
| JP2002269114A (en) * | 2001-03-14 | 2002-09-20 | Kousaku Ookubo | Knowledge database, and method for constructing knowledge database |
| US20020188896A1 (en) * | 2001-06-07 | 2002-12-12 | Filteau Sheila B. | System and method for generating multi-lingual reports |
| AU2002315143A1 (en) * | 2001-06-13 | 2002-12-23 | American Cardiovascular Research Institute | System and method for managing data and documents |
| US20040078221A1 (en) * | 2002-07-16 | 2004-04-22 | Yi-Yun Chen | MediCAD Chinese medical system |
| CA2502887A1 (en) * | 2002-10-21 | 2004-05-06 | Medvance Solutions Inc. | Method and system for medical communications |
| EP1567941A2 (en) * | 2002-11-28 | 2005-08-31 | Koninklijke Philips Electronics N.V. | Method to assign word class information |
| US20040168119A1 (en) * | 2003-02-24 | 2004-08-26 | David Liu | method and apparatus for creating a report |
| US7780595B2 (en) | 2003-05-15 | 2010-08-24 | Clinical Decision Support, Llc | Panel diagnostic method and system |
| US20050240440A1 (en) * | 2004-04-20 | 2005-10-27 | Frank Seidelmann | Lexicon model and method |
| US20070043589A1 (en) * | 2004-05-06 | 2007-02-22 | Humana Inc. | Pharmacy benefits design |
| US9081879B2 (en) | 2004-10-22 | 2015-07-14 | Clinical Decision Support, Llc | Matrix interface for medical diagnostic and treatment advice system and method |
| US20070093369A1 (en) * | 2005-10-21 | 2007-04-26 | Bocchicchio Vincent J | Resistance exercise method and system |
| US20080249761A1 (en) * | 2007-04-04 | 2008-10-09 | Easterly Orville E | System and method for the automatic generation of grammatically correct electronic medical records |
| US8959012B2 (en) * | 2007-04-04 | 2015-02-17 | Orville E. Easterly | System and method for the automatic generation of patient-specific and grammatically correct electronic medical records |
| US20090204421A1 (en) * | 2007-10-29 | 2009-08-13 | Alert Life Sciences Computing S.A. | Electronic health record touch screen form entry method |
| US9864838B2 (en) * | 2008-02-20 | 2018-01-09 | Medicomp Systems, Inc. | Clinically intelligent parsing |
| US8675221B1 (en) | 2009-03-12 | 2014-03-18 | Sanah, Inc. | System and method for processing and distribution of unsructured documents |
| US8688434B1 (en) | 2010-05-13 | 2014-04-01 | Narrative Science Inc. | System and method for using data to automatically generate a narrative story |
| US8355903B1 (en) | 2010-05-13 | 2013-01-15 | Northwestern University | System and method for using data and angles to automatically generate a narrative story |
| US8374848B1 (en) | 2010-05-13 | 2013-02-12 | Northwestern University | System and method for using data and derived features to automatically generate a narrative story |
| US9208147B1 (en) | 2011-01-07 | 2015-12-08 | Narrative Science Inc. | Method and apparatus for triggering the automatic generation of narratives |
| US8630844B1 (en) | 2011-01-07 | 2014-01-14 | Narrative Science Inc. | Configurable and portable method, apparatus, and computer program product for generating narratives using content blocks, angels and blueprints sets |
| US9720899B1 (en) | 2011-01-07 | 2017-08-01 | Narrative Science, Inc. | Automatic generation of narratives from data using communication goals and narrative analytics |
| US9697197B1 (en) | 2011-01-07 | 2017-07-04 | Narrative Science Inc. | Automatic generation of narratives from data using communication goals and narrative analytics |
| US9697178B1 (en) | 2011-01-07 | 2017-07-04 | Narrative Science Inc. | Use of tools and abstraction in a configurable and portable system for generating narratives |
| US10657201B1 (en) | 2011-01-07 | 2020-05-19 | Narrative Science Inc. | Configurable and portable system for generating narratives |
| US8775161B1 (en) | 2011-01-07 | 2014-07-08 | Narrative Science Inc. | Method and apparatus for triggering the automatic generation of narratives |
| US8892417B1 (en) | 2011-01-07 | 2014-11-18 | Narrative Science, Inc. | Method and apparatus for triggering the automatic generation of narratives |
| US9576009B1 (en) | 2011-01-07 | 2017-02-21 | Narrative Science Inc. | Automatic generation of narratives from data using communication goals and narrative analytics |
| US8886520B1 (en) | 2011-01-07 | 2014-11-11 | Narrative Science Inc. | Method and apparatus for triggering the automatic generation of narratives |
| US10185477B1 (en) | 2013-03-15 | 2019-01-22 | Narrative Science Inc. | Method and system for configuring automatic generation of narratives from data |
| US20130013616A1 (en) * | 2011-07-08 | 2013-01-10 | Jochen Lothar Leidner | Systems and Methods for Natural Language Searching of Structured Data |
| EP2750759B1 (en) * | 2011-08-29 | 2016-12-21 | Cardiac Pacemakers, Inc. | Algorithm for narrative generation |
| US10540430B2 (en) | 2011-12-28 | 2020-01-21 | Cbs Interactive Inc. | Techniques for providing a natural language narrative |
| US10592596B2 (en) | 2011-12-28 | 2020-03-17 | Cbs Interactive Inc. | Techniques for providing a narrative summary for fantasy games |
| JP5967968B2 (en) * | 2012-02-14 | 2016-08-10 | キヤノン株式会社 | Medical diagnosis support system, medical diagnosis support device, information processing method, and program |
| US8821271B2 (en) * | 2012-07-30 | 2014-09-02 | Cbs Interactive, Inc. | Techniques for providing narrative content for competitive gaming events |
| US10504198B1 (en) * | 2013-03-15 | 2019-12-10 | Reward Health Sciences, Inc. | Longitudinal multi-author care planning and management system with user-tailored care plan hierarchy that propagates based on care responsibility information |
| US11238090B1 (en) | 2015-11-02 | 2022-02-01 | Narrative Science Inc. | Applied artificial intelligence technology for using narrative analytics to automatically generate narratives from visualization data |
| US11922344B2 (en) | 2014-10-22 | 2024-03-05 | Narrative Science Llc | Automatic generation of narratives from data using communication goals and narrative analytics |
| US11475076B2 (en) | 2014-10-22 | 2022-10-18 | Narrative Science Inc. | Interactive and conversational data exploration |
| US10747823B1 (en) | 2014-10-22 | 2020-08-18 | Narrative Science Inc. | Interactive and conversational data exploration |
| US11232268B1 (en) | 2015-11-02 | 2022-01-25 | Narrative Science Inc. | Applied artificial intelligence technology for using narrative analytics to automatically generate narratives from line charts |
| US11188588B1 (en) | 2015-11-02 | 2021-11-30 | Narrative Science Inc. | Applied artificial intelligence technology for using narrative analytics to interactively generate narratives from visualization data |
| US11222184B1 (en) | 2015-11-02 | 2022-01-11 | Narrative Science Inc. | Applied artificial intelligence technology for using narrative analytics to automatically generate narratives from bar charts |
| US10853583B1 (en) | 2016-08-31 | 2020-12-01 | Narrative Science Inc. | Applied artificial intelligence technology for selective control over narrative generation from visualizations of data |
| US11568148B1 (en) | 2017-02-17 | 2023-01-31 | Narrative Science Inc. | Applied artificial intelligence technology for narrative generation based on explanation communication goals |
| US11068661B1 (en) | 2017-02-17 | 2021-07-20 | Narrative Science Inc. | Applied artificial intelligence technology for narrative generation based on smart attributes |
| US10699079B1 (en) | 2017-02-17 | 2020-06-30 | Narrative Science Inc. | Applied artificial intelligence technology for narrative generation based on analysis communication goals |
| US10943069B1 (en) | 2017-02-17 | 2021-03-09 | Narrative Science Inc. | Applied artificial intelligence technology for narrative generation based on a conditional outcome framework |
| US11954445B2 (en) | 2017-02-17 | 2024-04-09 | Narrative Science Llc | Applied artificial intelligence technology for narrative generation based on explanation communication goals |
| US10572606B1 (en) | 2017-02-17 | 2020-02-25 | Narrative Science Inc. | Applied artificial intelligence technology for runtime computation of story outlines to support natural language generation (NLG) |
| US11042709B1 (en) | 2018-01-02 | 2021-06-22 | Narrative Science Inc. | Context saliency-based deictic parser for natural language processing |
| US11561986B1 (en) | 2018-01-17 | 2023-01-24 | Narrative Science Inc. | Applied artificial intelligence technology for narrative generation using an invocable analysis service |
| US11030408B1 (en) | 2018-02-19 | 2021-06-08 | Narrative Science Inc. | Applied artificial intelligence technology for conversational inferencing using named entity reduction |
| US11042713B1 (en) | 2018-06-28 | 2021-06-22 | Narrative Scienc Inc. | Applied artificial intelligence technology for using natural language processing to train a natural language generation system |
| US10990767B1 (en) | 2019-01-28 | 2021-04-27 | Narrative Science Inc. | Applied artificial intelligence technology for adaptive natural language understanding |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US3566370A (en) * | 1969-06-10 | 1971-02-23 | Searle Medidata Inc | Automated medical history taking system |
| US4428733A (en) * | 1981-07-13 | 1984-01-31 | Kumar Misir Victor | Information gathering system |
| US4503426A (en) * | 1982-04-30 | 1985-03-05 | Mikulski Walter J | Visual communication device |
| US4839822A (en) * | 1987-08-13 | 1989-06-13 | 501 Synthes (U.S.A.) | Computer system and method for suggesting treatments for physical trauma |
| US4878175A (en) * | 1987-11-03 | 1989-10-31 | Emtek Health Care Systems | Method for generating patient-specific flowsheets by adding/deleting parameters |
| US5023785A (en) * | 1987-11-16 | 1991-06-11 | Becton & Dickinson Co. | Hematology - diagnosis apparatus employing expert system technology |
| US4869531A (en) * | 1988-04-01 | 1989-09-26 | Rees Michael K | Apparatus and method for documenting physical examinations |
| JPH03111068A (en) * | 1989-09-08 | 1991-05-10 | Jr Richard L Brown | Physical exercise-instructing method, system therefor and kit therefor |
| US5296688A (en) * | 1989-12-04 | 1994-03-22 | Hamilton David W | Apparatus and method for recording progress notes |
| US5089978A (en) * | 1990-02-09 | 1992-02-18 | Westinghouse Electric Corp. | Automatic plant state diagnosis system including a display selection system for selecting displays responsive to the diagnosis |
| US5265010A (en) * | 1990-05-15 | 1993-11-23 | Hewlett-Packard Company | Method and apparatus for performing patient documentation |
| US5305205A (en) * | 1990-10-23 | 1994-04-19 | Weber Maria L | Computer-assisted transcription apparatus |
| US5262943A (en) * | 1991-10-15 | 1993-11-16 | National Computer Systems, Inc. | System and process for information management and reporting |
| US5327341A (en) * | 1991-10-28 | 1994-07-05 | Whalen Edward J | Computerized file maintenance system for managing medical records including narrative reports |
-
1996
- 1996-03-01 US US08/609,835 patent/US5802495A/en not_active Expired - Lifetime
-
1997
- 1997-02-25 WO PCT/US1997/002786 patent/WO1997032272A1/en active Application Filing
- 1997-02-25 EP EP97907783A patent/EP0892959A4/en not_active Withdrawn
- 1997-02-25 CA CA002247896A patent/CA2247896C/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| US5802495A (en) | 1998-09-01 |
| CA2247896A1 (en) | 1997-09-04 |
| EP0892959A1 (en) | 1999-01-27 |
| WO1997032272A1 (en) | 1997-09-04 |
| EP0892959A4 (en) | 2009-11-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA2247896C (en) | A method for generating text from selected medical findings | |
| WO1997032272A9 (en) | A method for generating text from selected medical findings | |
| US5823949A (en) | Intelligent prompting | |
| US5794208A (en) | Creating and using protocols to create and review a patient chart | |
| Butcher et al. | Nursing Interventions Classification (NIC)-E-Book: Nursing Interventions Classification (NIC)-E-Book | |
| US7076436B1 (en) | Medical records, documentation, tracking and order entry system | |
| US7949544B2 (en) | Integrated system for generation and retention of medical records | |
| US5823948A (en) | Medical records, documentation, tracking and order entry system | |
| US20050171762A1 (en) | Creating records of patients using a browser based hand-held assistant | |
| US20020082868A1 (en) | Systems, methods and computer program products for creating and maintaining electronic medical records | |
| US20030220819A1 (en) | Medical management intranet software | |
| Gell | AURA: Routine documentation of medical texts | |
| US20080109739A1 (en) | Automated documentation system and method | |
| Pryor et al. | The HELP system development tools | |
| Brunjes | An anamnestic matrix toward a medical language | |
| US20050004816A1 (en) | Method and apparatus for processing and outputting a version change for a data record which includes medical therapeutic advice items | |
| Boon et al. | The role of AIDA in a primary care information system | |
| Van Brunt et al. | Current status of a medical information system | |
| Gertner | Ongoing critiquing during trauma management | |
| Handler | Computers in medicine: augmenting medical care in pediatric patients with chronic illnesses | |
| US20060060648A1 (en) | Method and apparatus for storing and reading medical records from a magnetic card | |
| Gender | Developing and computerizing a patient classification system in a rehabilitation nursing setting | |
| Knots et al. | PACS in practice: on-line communications in daily routine | |
| Beesley | Computer generation of a patient specific clinical summary for radiology | |
| Dickey | Responsibility for Interpreting Laboratory Studies |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| EEER | Examination request | ||
| MKLA | Lapsed |