WO2020132793A1 - Artificial intelligence medical symptom recognition system based on span searching - Google Patents
Artificial intelligence medical symptom recognition system based on span searching Download PDFInfo
- Publication number
- WO2020132793A1 WO2020132793A1 PCT/CN2018/123074 CN2018123074W WO2020132793A1 WO 2020132793 A1 WO2020132793 A1 WO 2020132793A1 CN 2018123074 W CN2018123074 W CN 2018123074W WO 2020132793 A1 WO2020132793 A1 WO 2020132793A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- span
- patient
- artificial intelligence
- word
- processor
- Prior art date
Links
Images
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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
-
- 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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Chemical & Material Sciences (AREA)
- Pathology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Medicinal Chemistry (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
Embodiments of the disclosure provide artificial intelligence systems and methods for recognizing a medical symptom from a patient description. An exemplary artificial intelligence system includes a patient interaction interface configured to receive the patient description. The system further includes a storage device configured to store a plurality of entities corresponding to known medical symptoms. The system also includes a processor. The processor is configured to identify a plurality of spans from the patient description, and determine matching values between the plurality of spans and the plurality of entities. The processor is further configured to identify at least one pair of a span and a matched entity with the associated matching value higher than a threshold, and determine the medical symptom based on the matched entity.
Description
The present disclosure relates to artificial intelligence (AI) systems and methods for recognizing a patient’s medical symptoms, and more particularly to, AI systems and methods for medical symptom recognition from the patient’s descriptions using span searching.
Pre-diagnosis is usually performed in hospitals to preliminarily determine the illnesses of patients before sending them to the right doctors. Pre-diagnosis is typically based on symptoms described by the patient. For example, if the patient says she has a fever and a running nose, she will be pre-diagnosed as having a cold or a flu and be sent to an internal medicine doctor. If the patient says that she has itchy rashes on her skin, she will be pre-diagnosed as having skin allergies and be sent to a dermatologist.
Pre-diagnosis is typically performed by medical practitioners, such as physicians or nurses. For example, hospitals usually have pre-diagnosis personnel available at the check-in desk to determine where the patient should be sent to. However, having practitioners perform the pre-diagnosis wastes valuable resources. Automated pre-diagnosis methods are used to improve the efficiency. For example, diagnosis robots are being developed to perform the pre-diagnosis. These automated methods provide a preliminary diagnosis based on patient’s described symptoms, e.g., based on preprogramed mappings between diseases and known symptoms.
Patient descriptions are, however, not accurate or clear. For example, the patient may be under the influence of the illness or medicine and could not express herself accurately. In addition, patients are not practitioners and are therefore not familiar with medical terminologies for describing symptoms. Indeed, patients, especially when describing symptoms orally, may use informal language while medical terminologies are usually formal. As a result, existing automated methods could not readily recognize medical symptoms from patient descriptions.
Embodiments of the disclosure address the above problems by providing improved artificial intelligence systems and methods for recognizing medical symptoms from patient’s descriptions using span searching.
SUMMARY
Embodiments of the disclosure provide an artificial intelligence system for for recognizing a medical symptom from a patient description. The artificial intelligence system includes a patient interaction interface configured to receive the patient description. The system further includes a storage device configured to store a plurality of entities corresponding to known medical symptoms. The system also includes a processor. The processor is configured to identify a plurality of spans from the patient description, and determine matching values between the plurality of spans and the plurality of entities. The processor is further configured to identify at least one pair of a span and a matched entity with the associated matching value higher than a threshold, and determine the medical symptom based on the matched entity.
Embodiments of the disclosure also provide an artificial intelligence method for recognizing a medical symptom from a patient description. The artificial intelligence method includes receiving, by a patient interaction interface, the patient description. The method further includes identifying, by a processor, a plurality of spans from the patient description. The method also includes determining, by the processor, matching values between the plurality of spans and a plurality of entities corresponding to known medical symptoms. The method additional includes identifying, by the processor, at least one pair of a span and a matched entity with the associated matching value higher than a threshold, and determining, by the processor, the medical symptom based on the matched entity.
Embodiments of the disclosure further provide a non-transitory computer-readable medium having instructions stored thereon that, when executed by a processor, causes the processor to perform an artificial intelligence method for recognizing a medical symptom from a patient description. The artificial intelligence method includes receiving the patient description. The method further includes identifying a plurality of spans from the patient description. The method also includes determining matching values between the plurality of spans and a plurality of entities corresponding to known medical symptoms. The method additional includes identifying at least one pair of a span and a matched entity with the associated matching value higher than a threshold, and determining the medical symptom based on the matched entity.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
FIG. 1 illustrates a schematic diagram of an exemplary AI system for recognizing a medical symptom from a patient description, according to embodiments of the disclosure.
FIG. 2 illustrates a flowchart of an exemplary method for recognizing a medical symptom from a patient description, according to embodiments of the disclosure.
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. Wherever possible, the same reference numbers will be used throughout the drawings to refer to the same or like parts.
FIG. 1 illustrates a block diagram of an exemplary AI system 100 for recognizing a medical symptom from a patient description, according to embodiments of the disclosure. Consistent with the present disclosure, AI system 100 may receive patient description 103 from a patient terminal 120. For example, patient terminal 120 may be a mobile phone, a desktop computer, a laptop, a PDA, a robot, a kiosk, etc. Patient terminal 120 may include a patient interaction interface configured to receive patent description 103 provided by patient 130. In some embodiments, patient terminal 120 may include a keyboard, hard or soft, for patient 130 to type in patient description 103. Patient terminal 120 may additionally or alternatively include a touch screen for patient 130 to handwrite patient description 103. Accordingly, patient terminal 120 may record patient description 103 as texts. If the input is handwriting, patient terminal 120 may automatically recognize the handwriting and convert it to text information. In some other embodiments, patient terminal 120 may include a microphone, for recording patient description 103 provided by patient 130 orally. Patient terminal 120 may automatically transcribe the recorded audio data into texts. In some alternative embodiments, AI system 100 may receive patient description 103 in its original format as captured by patient terminal 120, and the handwriting recognition and audio transcription may be performed automatically by AI system 100.
In some embodiments, as shown in FIG. 1, AI system 100 may include a communication interface 102, a processor 104, a memory 106, and a storage 108. In some embodiments, AI system 100 may have different modules in a single device, such as an integrated circuit (IC) chip (e.g., implemented as an application-specific integrated circuit (ASIC) or a field-programmable gate array (FPGA) ) , or separate devices with dedicated functions. In some embodiments, one or more components of AI system 100 may be located in a cloud, or may be alternatively in a single location (such as inside a mobile device) or distributed locations. Components of AI system 100 may be in an integrated device, or distributed at different locations but communicate with each other through a network (not shown) . Consistent with the president disclosure, AI system 100 may be configured to automatically recognize medical symptoms from patient description 103.
Consistent with some embodiments, communication interface 102 may receive data such as patient description 103 from patient terminal 120. Patient description 103 may be received as texts or in its original format as acquired by patient terminal 120, such as an audio or in handwriting. Patient description 103 may include one sentence or multiple sentences that describe the symptoms and feelings of patient 130. For example, patient 130 may describe her symptom as “I am having a recurring pain in the head, also feeling a bit dizzy, and my nose seems running too. ” When patient description 103 is originally provided by patient 130 orally, the description may additionally contain various spoken language words, such as, hmm, well, all right, you know, okay, so, etc. Communication interface 102 may further provide the received data to memory 106 and/or storage 108 for storage or to processor 104 for processing.
In some embodiments, memory 106 and/or storage 108 may also store intermediate data such as the word segments and spans in patient description 103, and matching values between the spans and the entities, etc. Memory 106 and/or storage 108 may additionally store various learning models including their model parameters, such as a sentence segmentation model, a span-entity matching model, etc. that will be described. The various types of data may be stored permanently, removed periodically, or disregarded immediately after the data is processed.
As shown in FIG. 1, processor 104 may include multiple modules, such as a segmentation unit 140, a span-entity matching unit 142, a mention detection unit 144, a diagnosis unit 146, and the like. These modules (and any corresponding sub-modules or sub-units) can be hardware units (e.g., portions of an integrated circuit) of processor 104 designed for use with other components or software units implemented by processor 104 through executing at least part of a program. The program may be stored on a computer-readable medium, and when executed by processor 104, it may perform one or more functions. Although FIG. 1 shows units 140-146 all within one processor 104, it is contemplated that these units may be distributed among multiple processors located closely or remotely with each other.
I //am having //a //recurring //pain //in //the //head//, also //feeling //a bit //dizzy, and //my //nose //seems //running //too. ”
In some alternative embodiments, when patient description 103 contains multiple sentences, segmentation unit 140 may first divide patient description 103 into different sentences before segmenting each of the sentences into word segments. For example, the above description may be divided into three sentences and then segmented into word segments as follows:
I //am having //a //recurring //pain //in //the //head.
Also //feeling //a bit //dizzy.
And //my //nose //seems //running //too.
In some embodiments, segmentation unit 140 may be further configured to label each word segment as either a substantive word or a non-substantive word. Consistent with present disclosure, a “substantive word” is a word that has substantive meaning indicating or otherwise related to medical symptoms. A “non-substantive word” is any word that is not a substantive word.
In some embodiments, segmentation unit 140 may first determine whether a word segment is a notional word that has substantive meanings or a relational word that merely expresses a grammatical relationship between notional words to express the meanings. In some embodiments, a notional word may denote a person or thing, an act, or a quality. Grammatically, notional words can make up a sentence with meanings. For example, notional words may include nouns, verbs, adjectives, numerals, qualifiers, pronouns, etc. In contrast, a relational word does not have independent meanings and it must be attached to a notional word to express a substantive meaning. Grammatically, relational words, by themselves, cannot make up a sentence. For example, relational words may include adverbs, articles, prepositions, conjunctions, particles, exclamations, etc. If segmentation unit 140 determines a word segment as a relational word, it automatically labels the word segment as “non-substantive. ”
For those word segments remaining from the above distinction (between notional and relational words) , segmentation unit 140 then determines whether they are related to medical symptoms. Accordingly, segmentation unit 140 may further label certain notional words, such as nouns used as the subject, e.g., “I, ” “we, ” “you, ” “it” as non-substantive, and verbs and adjectives that do not meaningfully describe a symptom, e.g., “have, ” “seem, ”
“look, ” “feel, ” and “alittle bit. ”
Using the exemplary patient description above, the following labels may be applied to the word segments, as shown in Table 1A-1C:
Table 1A
Table 1B
Table 1C
Based on the labeled word segments, segmentation unit 140 may identify spans from patient description 103. Consistent with the present disclosure, a “span” is a phrase containing all word segments between two substantive words. Therefore, a span starts with a first substantive word and ends with a second substantive word. The first and second substantive words may be the same or different. For example, in the first sentence of the exemplary description above, “recurring pain, ” “pain in the head, ” and “recurring pain in the head” may be identified as spans. In the second sentence, “dizzy” may be identified as a span by itself. In the third sentence, “nose seems running” may be identified as a span.
Span-entity matching unit 142 may be configured to match the identified spans with the entities associated with known symptoms stored in memory 106/storage 108. In some embodiments, for each span, span-entity matching unit 142 may traverse all the entities, and calculate matching values between the span and each entity. Span-entity matching unit 142 then identify the entity with the highest matching value as the “mention” of the span. In some embodiments, the matching value between a span and an entity may indicate the semantic similarity between the two. In some embodiments, the matching value may be determined using a learning network trained with sample spans and their associated mentions. In some embodiments, the matching value may be a probability value between 0-100%. For example, when a span, e.g., “headache” matches an existing entity, e.g., “headache” entirely, the matching value is 100%. As another example, the span “pain in the head” may be matched to entity “headache” at a 90%matching value.
In some embodiments, Span-entity matching unit 142 may create a table to record the matching values and matched entities. In some embodiments, the rows and columns may contain the word segments. Therefore, if there are N word segments in the sentence, the table may be (N+1) x (N+1) in size. Table 2 shows an exemplary table using the word segments in the sentence “I am having a recurring pain in my head” as an example. Since there are 8 word segments in the sentence, the table is 9x9 in size.
Table 2
The “substantive words” are marked as bold in Table 2. For example, Table 2 contains the substantive words “recurring, ” “pain, ” and “head. ” To identify the spans, the first substantive word that starts the span is selected from the first column of Table 2, and the second substantive word that ends the span is selected from the first row of Table 2. For example, the spans identified according to Table 2 include “recurring pain, ” “recurring pain in the head, ” “pain, ” and “pain in the head. ” For each identified span, span-entity matching unit 412 may traverse all the entities in the database and compute matching values between the span and the entities.
In some embodiments, span-entity matching unit 412 may record the highest matching value for a span in the table cell corresponding to the starting word and the ending word of the span. For example, matching value Pa is recorded for span “recurring pain” in the table cell corresponding to “recurring” in the column and “pain” in the row. Similarly, matching values Pb, Pc, and Pd may be recorded for spans “recurring pain in the head, ” “pain in the head, ” and “pain. ” In some embodiments, in addition to the matching value, the table cell may also record the respective matched entity. For example, entity “migraine” may be recorded in the same table cells that record matching value Pa and matching value Pb. Entity “headache” may be recorded in the same table cells that record matching value Pc and matching value Pd. In some embodiments, span-entity matching unit 142 may set remaining table cells to a preset value, such as 0 or a negative value.
Mention detection unit 144 may be configured to determine a mention for each span. In some embodiments, mention detection unit 144 may compare the recorded matching values to a threshold, such as 95%, 90%, 80%, etc. If a matching value exceeds the threshold, the respective matched entity will be assigned to the span as its mention.
In some alternative embodiments, for each span, span-entity matching unit 412 may first determine if it contains another span that already has a matched entity (i.e., a mention) . If a mention is already matched for any span contained in the current span, the matching value is automatically set to a preset value, such as 0 or a negative value. For example, if “recurring pain” is already matched to an entity “migraine, ” span-entity matching unit 412 will not search the entities for “recurring pain in the head, ” but automatically set the matching value of “recurring pain in the head” to the preset value. Similarly, in some embodiments, span-entity matching unit 412 may set the matching value of a span to the preset value if the span is contained by another span that already has a matched entity. For example, if “recurring pain in the head” is already matched to an entity “migraine, ” span-entity matching unit 412 will automatically set the matching value of “recurring pain” to the preset value.
For example, FIG. 2 illustrates a flowchart of an exemplary method 200 for recognizing a medical symptom from a patient description, according to embodiments of the disclosure. Method 200 may be implemented by AI system 100 and particularly processor 104 or a separate processor not shown in FIG. 1. Method 200 may include steps S202-S224 as described below. It is to be appreciated that some of the steps may be optional to perform the disclosure provided herein. Further, some of the steps may be performed simultaneously, or in a different order than shown in FIG. 2.
In step S202, AI system 100 may receive a patient description. Patient description 103 may be received as texts or in its original format as acquired by patient terminal 120, such as an audio or in handwriting. If received as an audio, patient description 103 may be transcribed into texts. If received in handwriting, patient description 103 may be automatically recognized and convert into texts. Patient description 103 may include one sentence or multiple sentences that describe the symptoms of patient 130. For example, patient 130 may describe her symptom as “I am having a recurring pain in the head, also feeling a bit dizzy, and my nose seems running too. ”
In step S204, AI system 100 may segment patient description 103 into multiple word segments. In some embodiments, when patient description 103 contains multiple sentences, segmentation unit 140 may first divide patient description 103 into different sentences. For example, the above exemplary description may be divided into three sentences: “I am having a recurring pain in the head. ” “Also feeling a bit dizzy. ” and “And my nose seems running too. ” AI system 100 may further segment each of the sentences into word segments. In some embodiments, AI system 100 may apply a sentence segmentation model trained using sample sentences and known word segments of those sentences. The exemplary description above can be segmented as:
I //am having //a //recurring //pain //in //the //head.
Also //feeling //a bit //dizzy.
And //my //nose //seems //running //too.
In step S206, AI system 100 may label the word segments as substantive words or non-substantive words. In some embodiments, segmentation unit 140 may first determine whether a word segment is a notional word that has substantive meanings or a relational word that merely expresses a grammatical relationship between notional words to express the meanings. If segmentation unit 140 determines a word segment as a relational word, such as an adverb, an article, a preposition, a conjunction, a particle, or an exclamation, it automatically labels the word segment as “non-substantive. ”
For those word segments remaining from the above distinction (between notional and relational words) , AI system 100 then determines whether they are related to medical symptoms. Accordingly, AI system 100 may further label certain notional words, such as nouns used as the subject, e.g., “I, ” “we, ” “you, ” “it” as non-substantive, and verbs and adjectives that do not meaningfully describe a symptom, e.g., “have, ” “seem, ” “look, ” “feel, ” and “alittle bit. ” For example, Table 1A-1C show labels assigned to the word segments in the exemplary patient description above.
In step S208, AI system 100 may generate a table using the word segments. In some embodiments, the first row and first column of the table may contain the word segments. Table 2 shows an exemplary table using the word segments in the sentence “I am having a recurring pain in my head” as an example. If there are N word segments in the sentence, the table may be (N+1) x (N+1) in size. As shown in Table 2, as there are 8 word segments in the sentence, the table is 9x9 in size. The table is to record matching values and matched entities of each span.
In step S210, AI system 100 identifies a span between two substantive words. In some embodiments, AI system 100 may select a first substantive word and a second substantive word and identify all the word segments between the two substantive words as a span. The first and second substantive words may be the same or different. For example, in the first sentence of the exemplary description above, “recurring pain, ” “pain in the head, ” and “recurring pain in the head” may be identified as spans. In the second sentence, “dizzy” may be identified as a span by itself. In the third sentence, “nose seems running” may be identified as a span.
In some embodiments, AI system 100 may select the first substantive word that starts the span from the first column of Table 2, and the second substantive word that ends the span from the first row of Table 2. For example, the spans identified according to Table 2 include “recurring pain, ” “recurring pain in the head, ” “pain, ” and “pain in the head. ”
In step S212, AI system 100 determines if it contains another span that already has a matched entity. If any span contained in the current span is already matched with an entity (S212: yes) , in step S214, the matching value is automatically set to a preset value, such as 0 or a negative value. For example, if “recurring pain” is already matched to an entity “migraine, ” AI system 100 will automatically set the matching value of “recurring pain in the head” to the preset value. After S214, method 200 proceeds to step S222. Otherwise, if no span contained in the current span is already matched with an entity (S212: no) , method 200 proceeds to step S216 to calculate the matching value.
In some alternative embodiments, as part of step S212, AI system 100 may determine if the current span is contained in any span that already has a matched entity. AI system 100 may set the matching value of the current span to the preset value if the span is contained by another span that already has a matched entity (S212: yes) . For example, if “recurring pain in the head” is already matched to an entity “migraine, ” AI system 100 will automatically set the matching value of “recurring pain” to the preset value. Otherwise, if no span containing the current span is already matched with an entity (S212: no) , method 200 proceeds to step S216 to calculate the matching value.
In step S218, AI system 100 may be configured to match the span with the entities associated with known symptoms stored in memory 106/storage 108 and calculate matching values between the span and each entity. In some embodiments, AI system 100 may traverse all the entities to calculate the matching values.
In some embodiments, AI system 100 may identify the entity with the highest matching value as the “mention” of the span. In step S218, AI system 100 compare the highest matching value with a threshold, such as 95%, 90%, 80%, etc. If the highest matching value exceeds the threshold (S218: yes) , the respective matched entity will be assigned to the span as its mention. Accordingly, in step S220, AI system 100 records the highest matching value and the respective matched entity for the span in the table cell corresponding to the starting word and the ending word of the span. For example, in Table 2, matching value Pa and matched entity “migraine” are recorded for span “recurring pain” in the table cell corresponding to “recurring” in the column and “pain” in the row. As another example, matching value Pc and matched entity “headache” may be recorded for span “pain in the head. ” If the highest matching value does not exceed the threshold (S218: no) , method 200 proceeds directly to step S222.
In step S222, AI system 100 may determine if all span have been identified and matched with the entities. If not all spans are accounted for (S222: no) , method 200 returns to step S210 to identify another span. Otherwise, if all spans are accounted for (S222: yes) , method 200 proceeds to step S224, where AI system 100 makes a pre-diagnosis based on symptoms described by the matched entities. For example, medical symptoms detected from patient description 103 “I am having a recurring pain in the head, also feeling a bit dizzy, and my nose seems running too” may include “headache, ” “migraine, ” “faint, ” and “running nose. ” Based on the symptoms, AI system 100 may predict that the patient likely has a flu. In some embodiments, AI system 100 may use a learning model to predict the illness based on the symptoms. The learning model may be trained with sample symptoms of patients and the final diagnosis of the patients made by physicians.
Another aspect of the disclosure is directed to a non-transitory computer-readable medium storing instructions which, when executed, cause one or more processors to perform the methods, as discussed above. The computer-readable medium may include volatile or non-volatile, magnetic, semiconductor, tape, optical, removable, non-removable, or other types of computer-readable medium or computer-readable storage devices. For example, the computer-readable medium may be the storage device or the memory module having the computer instructions stored thereon, as disclosed. In some embodiments, the computer-readable medium may be a disc or a flash drive having the computer instructions stored thereon.
It will be apparent to those skilled in the art that various modifications and variations can be made to the disclosed system and related methods. Other embodiments will be apparent to those skilled in the art from consideration of the specification and practice of the disclosed system and related methods.
It is intended that the specification and examples be considered as exemplary only, with a true scope being indicated by the following claims and their equivalents.
Claims (19)
- An artificial intelligence system for recognizing a medical symptom from a patient description, comprising:a patient interaction interface configured to receive the patient description;a storage device configured to store a plurality of entities corresponding to known medical symptoms; anda processor configured to:identify a plurality of spans from the patient description;determine matching values between the plurality of spans and the plurality of entities;identify at least one pair of a span and a matched entity with the associated matching value higher than a threshold; anddetermine the medical symptom based on the matched entity.
- The artificial intelligence system of claim 1, wherein to identify the plurality of spans, the processor is further configured to:segment the patient description into word segments;label each word segment as a substantive word or a non-substantive word; andidentify the word segments between two substantive words as a span.
- The artificial intelligence system of claim 1, wherein the processor is further configured to traverse the plurality of entities for each span and compute the matching values between each entity and the span.
- The artificial intelligence system of claim 1, wherein the processor is further configured to:select spans that include the span in the identified pair; andautomatically set the matching values associated with selected spans to a preset value.
- The artificial intelligence system of claim 4, wherein the preset value is 0.
- The artificial intelligence system of claim 2, wherein the storage device is further configured to store a table, wherein each cell of the table records the entity having the highest matching value with the span between the two substantive words corresponding to the cell and the matching value.
- The artificial intelligence system of claim 6, wherein the table is (N+1) by (N+1) in size, where N is a number of the word segments in the patient description.
- The artificial intelligence system of claim 6, wherein the processor is further configured to:detect that the highest matching value recorded by a selected cell exceeds the threshold; anddetermine the entity recorded by the selected cell to be a mention of the span between the two substantive words corresponding to the selected cell.
- The artificial intelligence system of claim 1, wherein the patient interaction interface is a keyboard configured to receive the patient description in the form of a text.
- The artificial intelligence system of claim 1, wherein the patient interaction interface is a microphone configured to receive the patient description in the form of an audio, wherein the processor is further configured to transcribe the audio to a text.
- An artificial intelligence method for recognizing a medical symptom from a patient description, comprising:receiving, by a patient interaction interface, the patient description;identifying, by a processor, a plurality of spans from the patient description;determining, by the processor, matching values between the plurality of spans and a plurality of entities corresponding to known medical symptoms;identifying, by the processor, at least one pair of a span and a matched entity with the associated matching value higher than a threshold; anddetermining, by the processor, the medical symptom based on the matched entity.
- The artificial intelligence method of claim 11, wherein identifying the plurality of spans further comprises:segmenting the patient description into word segments;labeling each word segment as a substantive word or a non-substantive word; andidentifying the word segments between two substantive words as a span.
- The artificial intelligence method of claim 11, further comprising:select spans that include the span in the identified pair; andautomatically set the matching values associated with selected spans to a preset value.
- The artificial intelligence method of claim 12, further comprising: recording the entity having the highest matching value with the span in a table cell corresponding to the two substantive words defining the span.
- The artificial intelligence method of claim 15, further comprising:detecting that the highest matching value recorded by a selected cell exceeds the threshold; anddetermining the entity recorded by the selected cell to be a mention of the span between the two substantive words corresponding to the selected cell.
- The artificial intelligence method of claim 11, wherein the patient interaction interface is a keyboard and the patient description is received in the form of a text.
- The artificial intelligence method of claim 11, wherein the patient interaction interface is a microphone and the patient description is received in the form of an audio, wherein method further comprises transcribing the audio to a text.
- Anon-transitory computer-readable medium having instructions stored thereon that, when executed by a processor, causes the processor to perform an artificial intelligence method for recognizing a medical symptom from a patient description, the artificial intelligence methods comprising:receiving the patient description;identifying a plurality of spans from the patient description;determining matching values between the plurality of spans and a plurality of entities corresponding to known medical symptoms;identifying at least one pair of a span and a matched entity with the associated matching value higher than a threshold; anddetermining the medical symptom based on the matched entity.
- The non-transitory computer-readable medium of claim 19, wherein the artificial intelligence method further comprises:segmenting the patient description into word segments;labeling each word segment as a substantive word or a non-substantive word; and identifying the word segments between two substantive words as a span.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201880038947.8A CN111615697A (en) | 2018-12-24 | 2018-12-24 | Artificial intelligence medical symptom recognition system based on text segment search |
PCT/CN2018/123074 WO2020132793A1 (en) | 2018-12-24 | 2018-12-24 | Artificial intelligence medical symptom recognition system based on span searching |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2018/123074 WO2020132793A1 (en) | 2018-12-24 | 2018-12-24 | Artificial intelligence medical symptom recognition system based on span searching |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2020132793A1 true WO2020132793A1 (en) | 2020-07-02 |
Family
ID=71126765
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2018/123074 WO2020132793A1 (en) | 2018-12-24 | 2018-12-24 | Artificial intelligence medical symptom recognition system based on span searching |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN111615697A (en) |
WO (1) | WO2020132793A1 (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102243626A (en) * | 2011-07-22 | 2011-11-16 | 中国科学院计算技术研究所 | Translation rule extraction method and translation method based on dependency syntax tree |
US8077984B2 (en) * | 2008-01-04 | 2011-12-13 | Xerox Corporation | Method for computing similarity between text spans using factored word sequence kernels |
CN107563120A (en) * | 2017-09-13 | 2018-01-09 | 青岛海信医疗设备股份有限公司 | Recommend method and device for the doctor of patient |
CN107887036A (en) * | 2017-11-09 | 2018-04-06 | 北京纽伦智能科技有限公司 | Construction method, device and the clinical decision accessory system of clinical decision accessory system |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080228769A1 (en) * | 2007-03-15 | 2008-09-18 | Siemens Medical Solutions Usa, Inc. | Medical Entity Extraction From Patient Data |
CN106897559B (en) * | 2017-02-24 | 2019-09-17 | 黑龙江特士信息技术有限公司 | A kind of symptom and sign class entity recognition method and device towards multi-data source |
CN108877921B (en) * | 2017-05-12 | 2021-10-19 | 京东方科技集团股份有限公司 | Medical intelligent triage method and medical intelligent triage system |
CN108320808A (en) * | 2018-01-24 | 2018-07-24 | 龙马智芯(珠海横琴)科技有限公司 | Analysis of medical record method and apparatus, equipment, computer readable storage medium |
CN108614885B (en) * | 2018-05-03 | 2019-04-30 | 杭州认识科技有限公司 | Knowledge mapping analysis method and device based on medical information |
-
2018
- 2018-12-24 CN CN201880038947.8A patent/CN111615697A/en active Pending
- 2018-12-24 WO PCT/CN2018/123074 patent/WO2020132793A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8077984B2 (en) * | 2008-01-04 | 2011-12-13 | Xerox Corporation | Method for computing similarity between text spans using factored word sequence kernels |
CN102243626A (en) * | 2011-07-22 | 2011-11-16 | 中国科学院计算技术研究所 | Translation rule extraction method and translation method based on dependency syntax tree |
CN107563120A (en) * | 2017-09-13 | 2018-01-09 | 青岛海信医疗设备股份有限公司 | Recommend method and device for the doctor of patient |
CN107887036A (en) * | 2017-11-09 | 2018-04-06 | 北京纽伦智能科技有限公司 | Construction method, device and the clinical decision accessory system of clinical decision accessory system |
Also Published As
Publication number | Publication date |
---|---|
CN111615697A (en) | 2020-09-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10665226B2 (en) | System and method for data-driven socially customized models for language generation | |
US10740561B1 (en) | Identifying entities in electronic medical records | |
CN108597519B (en) | Call bill classification method, device, server and storage medium | |
US10318623B2 (en) | Device for extracting information from a dialog | |
US10067924B2 (en) | Method of improving NLP processing of real-world forms via element-level template correlation | |
US20180075368A1 (en) | System and Method of Advising Human Verification of Often-Confused Class Predictions | |
US10169703B2 (en) | System and method for analogy detection and analysis in a natural language question and answering system | |
WO2021000497A1 (en) | Retrieval method and apparatus, and computer device and storage medium | |
US20180068221A1 (en) | System and Method of Advising Human Verification of Machine-Annotated Ground Truth - High Entropy Focus | |
WO2021030915A1 (en) | Systems and methods for extracting information from a dialogue | |
US9703773B2 (en) | Pattern identification and correction of document misinterpretations in a natural language processing system | |
US20230089308A1 (en) | Speaker-Turn-Based Online Speaker Diarization with Constrained Spectral Clustering | |
WO2021063089A1 (en) | Rule matching method, rule matching apparatus, storage medium and electronic device | |
US10552461B2 (en) | System and method for scoring the geographic relevance of answers in a deep question answering system based on geographic context of a candidate answer | |
US10902342B2 (en) | System and method for scoring the geographic relevance of answers in a deep question answering system based on geographic context of an input question | |
CN111460175A (en) | SNOMED-CT-based medical noun dictionary construction and expansion method | |
US20200273555A1 (en) | Intelligent reminding method, device and electronic apparatus | |
WO2020113544A1 (en) | Artificial intelligence medical symptom recognition system based on end-to-end learning | |
WO2021012225A1 (en) | Artificial intelligence system for medical diagnosis based on machine learning | |
WO2020132793A1 (en) | Artificial intelligence medical symptom recognition system based on span searching | |
CN111552780B (en) | Medical scene search processing method and device, storage medium and electronic equipment | |
CN114020888A (en) | Text generation method, device, equipment and storage medium | |
WO2021151323A1 (en) | Method and apparatus for drug recommendation, device, and medium | |
WO2021012222A1 (en) | Artificial intelligence system for processing patient descriptions | |
CN114528851A (en) | Reply statement determination method and device, electronic equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 18944504 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 18944504 Country of ref document: EP Kind code of ref document: A1 |