CN114283925A - Intelligent prescription recommendation method and storage medium - Google Patents
Intelligent prescription recommendation method and storage medium Download PDFInfo
- Publication number
- CN114283925A CN114283925A CN202111527972.2A CN202111527972A CN114283925A CN 114283925 A CN114283925 A CN 114283925A CN 202111527972 A CN202111527972 A CN 202111527972A CN 114283925 A CN114283925 A CN 114283925A
- Authority
- CN
- China
- Prior art keywords
- information
- prescription
- syndrome
- diagnosis
- evidence
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000003860 storage Methods 0.000 title claims abstract description 26
- 208000011580 syndromic disease Diseases 0.000 claims abstract description 165
- 238000003745 diagnosis Methods 0.000 claims abstract description 76
- 230000004069 differentiation Effects 0.000 claims abstract description 44
- 238000012216 screening Methods 0.000 claims abstract description 17
- 238000004590 computer program Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 7
- 208000024891 symptom Diseases 0.000 claims description 7
- 230000008569 process Effects 0.000 abstract description 13
- 239000003795 chemical substances by application Substances 0.000 description 11
- 238000010586 diagram Methods 0.000 description 11
- 239000003814 drug Substances 0.000 description 11
- 230000006870 function Effects 0.000 description 7
- 201000010099 disease Diseases 0.000 description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 6
- 230000014509 gene expression Effects 0.000 description 6
- 230000009471 action Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 239000009792 yinqiao Substances 0.000 description 3
- 241000218671 Ephedra Species 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 206010013789 Dry throat Diseases 0.000 description 1
- 206010013954 Dysphoria Diseases 0.000 description 1
- 241000238631 Hexapoda Species 0.000 description 1
- 208000022569 Hypohidrotic ectodermal dysplasia-hypothyroidism-ciliary dyskinesia syndrome Diseases 0.000 description 1
- 206010062717 Increased upper airway secretion Diseases 0.000 description 1
- 206010037660 Pyrexia Diseases 0.000 description 1
- 208000032023 Signs and Symptoms Diseases 0.000 description 1
- 208000031975 Yang Deficiency Diseases 0.000 description 1
- 208000031971 Yin Deficiency Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 208000035850 clinical syndrome Diseases 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 239000008563 guizhi decoction Substances 0.000 description 1
- 210000002216 heart Anatomy 0.000 description 1
- 235000008216 herbs Nutrition 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 208000026435 phlegm Diseases 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 210000000952 spleen Anatomy 0.000 description 1
- 210000004243 sweat Anatomy 0.000 description 1
- 230000035922 thirst Effects 0.000 description 1
- 229940126680 traditional chinese medicines Drugs 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- 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
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides an intelligent prescription recommendation method and a storage medium, wherein the method comprises the following steps: s1: obtaining patient information to carry out syndrome differentiation to obtain a diagnosis information set; the diagnostic information set comprises a set of diagnostic provenances; s3: acquiring a plurality of pieces of first prescription information from a prescription database, and screening the first prescription information according to a diagnosis information set to obtain second prescription information; the second prescription information comprises a second necessary evidence information set and a second or evidence information set; s4: determining candidate prescription information according to the corresponding relation among the second necessary evidence information set, the second or evidence information set and the diagnosis evidence set; s5: and scoring all the candidate prescription information according to a preset rule, and determining a final recommended prescription according to a scoring result. According to the method and the system, the prescription is compared and determined according to the corresponding syndrome and the diagnosis syndrome set in the prescription recommending process, so that the finally recommended prescription is more accurate.
Description
Technical Field
The invention relates to the field of traditional Chinese medicine diagnosis and treatment, in particular to an intelligent prescription recommendation method and a storage medium.
Background
Traditional Chinese medicine is a part of Chinese national characteristic culture and is also an important branch of medicine. The compound has an important function of being not worn out in the process of resisting new crown epidemic situation in 2019, and is widely concerned and accepted by the society. However, at present, the number of traditional Chinese medical doctors in China is too small to meet the inquiry requirements of the people on traditional Chinese medicines, the period for cultivating traditional Chinese medical doctors is too long, the traditional Chinese medical doctors can not be completed from common traditional Chinese medical doctors to excellent traditional Chinese medical doctors with rich experience all the time, and the problem that people feel difficult to relieve far water and have near fire exists. Fortunately, the rise of artificial intelligence has created a desire to alleviate this supply and demand pressure.
In the field of traditional Chinese medicine, "syndrome" refers to the pathological general condition of disease location, disease nature, etc. at a certain stage in the disease process, is a unique diagnostic unit in traditional Chinese medicine, and can reveal the essence of disease; the syndrome refers to the general term of symptoms and signs. The syndrome-treating elements refer to the essential elements of syndrome, including both syndrome-treating elements and disease-causing syndrome-treating elements, and the clinical syndrome is usually composed of a plurality of syndrome-treating elements. The existing prescription recommendation algorithm usually focuses on the similarity between the symptoms of a patient and the indication symptoms of the prescription, and ignores the diagnosis with the most traditional Chinese medicine characteristics, namely 'syndrome'. In clinical practice, syndrome is a variable combination of Chinese herbs and is difficult to be included in intelligent prescription recommendation calculation. Fortunately, the smaller diagnostic unit of the syndrome is limited, and the process of combining the syndrome accords with the reductive thinking of small-granularity recombination, so that the intelligent recommendation calculation of the traditional Chinese medicine prescription based on the syndrome becomes possible. Therefore, if an intelligent recommendation method of traditional Chinese medicine formulas based on syndrome elements can be provided, the method is beneficial to both the nation and the people.
Disclosure of Invention
Therefore, an intelligent prescription recommendation method and a storage medium are needed to be provided for solving the problem that the accuracy of a recommended prescription is low due to the fact that prescription certificates are ignored in the existing intelligent prescription recommendation method.
In a first aspect, the invention provides a method for recommending an intelligent prescription, comprising the following steps:
s1: obtaining patient information to carry out syndrome differentiation to obtain a diagnosis information set; the diagnostic information set comprises a set of diagnostic provenances;
s2: acquiring a plurality of pieces of first prescription information from a prescription database, and screening the first prescription information according to a diagnosis information set to obtain second prescription information; the second prescription information comprises a second necessary evidence information set and a second or evidence information set;
s3: determining candidate prescription information according to the corresponding relation among the second necessary evidence information set, the second or evidence information set and the diagnosis evidence set;
s4: and scoring all the candidate prescription information according to a preset rule, and determining a final recommended prescription according to a scoring result.
Scoring all of the candidate formula information according to a predetermined rule is an optional embodiment, the first formula information comprising a first set of necessary provenance information, a first set of or provenance information, and a first set of negative provenance information;
screening the first agent information against the set of diagnostic information comprises:
rejecting the first agent information when it is determined that the first requisite credential information set is not a subset of the diagnostic credential set;
and/or rejecting the first prescription information when it is determined that the first negative prescription intersects the diagnostic prescription.
As an alternative embodiment, the diagnosis information set further includes a diagnosis syndrome set, and the first agent information includes first negative syndrome information;
screening the first agent information against the set of diagnostic information comprises:
and when the intersection of the first negative syndrome information and the diagnosis syndrome set is judged, rejecting the first prescription information.
As an alternative embodiment, step S4 includes:
s31: a second necessary evidence information set and a second or evidence information set corresponding to each second prescription information are subjected to union collection to obtain a first union combination;
s32: sequentially judging whether each first collection combination completely contains the diagnosis certificate collection;
if yes, go to step S321: determining second prescription information corresponding to the first collective combination as candidate prescription information;
otherwise, go to step S322: sequentially overlapping prescriptions in the plurality of pieces of second prescription information to perform a prescription combination, judging whether a union set of a first union set of the plurality of prescriptions after the prescription combination completely contains the diagnosis syndrome set, and if so, executing the step S3221: and determining the information of the second prescriptions corresponding to the union of the first set combination as the information of the candidate prescriptions after superposition.
As an alternative example, the information on the candidate prescriptions includes syndrome differentiation key element;
scoring all of the candidate formula information according to a predetermined rule includes:
and judging whether each syndrome differentiation key syndrome element is contained in the syndrome element set or not, and if so, adding a first numerical value to the score of the corresponding candidate prescription information.
As an alternative embodiment, the candidate prescription information includes a third set of required provenance information and third or provenance information;
scoring all of the candidate formula information according to a predetermined rule includes:
a third necessary evidence information set and a third or evidence information set corresponding to each candidate prescription information are subjected to union collection to obtain a second union set;
calculating the cross-over ratio of the second union set combination and the diagnosis certificate set, and adding a second numerical value to the score of the corresponding candidate prescription according to the cross-over ratio obtained by calculation; the magnitude of the second value is proportional to the magnitude of the calculated intersection ratio.
As an alternative example, the information of the candidate prescriptions includes the syndrome differentiation key point syndrome and the indication syndrome of the prescription; the diagnosis information set comprises a diagnosis syndrome set;
scoring all of the candidate formula information according to a predetermined rule includes:
judging whether each syndrome differentiation key point syndrome is contained in the diagnosis syndrome set, if so, adding a third numerical value to the score of the corresponding candidate prescription;
and/or calculating the similarity of the main treatment syndrome of each prescription and the diagnosis syndrome set, and adding a fourth numerical value to the score of the corresponding candidate prescription according to the calculated similarity; the magnitude of the fourth value is proportional to the magnitude of the similarity obtained by calculation.
As an alternative embodiment, the determination of the final recommended prescription based on the scoring results includes:
and screening a plurality of pieces of recommended prescription information with the top grade as final recommended prescriptions.
As an alternative embodiment, the method further comprises:
obtaining syndrome differentiation key point conditions corresponding to information of each recommended prescription in the final recommended prescription, judging whether the diagnosis information set meets the syndrome differentiation key point conditions, if not, removing the information of the recommended prescription from the final recommended prescription, and selecting information of the recommended prescription with the next grade size for judging again until the number of the information of the recommended prescription contained in the final recommended prescription meets the preset requirement.
In a second aspect, the present invention provides a storage medium storing a computer program which, when executed by a processor, performs the method steps according to the first aspect of the present invention.
Different from the prior art, the invention provides an intelligent prescription recommendation method and a storage medium, wherein the method comprises the following steps: s1: obtaining patient information to carry out syndrome differentiation to obtain a diagnosis information set; the diagnostic information set comprises a set of diagnostic provenances; s3: acquiring a plurality of pieces of first prescription information from a prescription database, and screening the first prescription information according to a diagnosis information set to obtain second prescription information; the second prescription information comprises a second necessary evidence information set and a second or evidence information set; s4: determining candidate prescription information according to the corresponding relation among the second necessary evidence information set, the second or evidence information set and the diagnosis evidence set; s5: and scoring all the candidate prescription information according to a preset rule, and determining a final recommended prescription according to a scoring result.
The prescription recommendation method is judged by taking the syndrome of the patient information as a diagnosis starting point, and is gradually determined by comparing the syndrome corresponding to the prescription with a diagnosis syndrome set in the prescription recommendation process, so that the finally recommended prescription has more representativeness and accuracy.
Drawings
FIG. 1 is a flow chart of a method for intelligent prescription recommendation in accordance with one embodiment of the present invention;
fig. 2 is a flowchart of an intelligent prescription recommendation method according to another embodiment of the present invention.
Fig. 3 is a schematic diagram of an intelligent prescription recommendation method according to another embodiment of the present invention.
Fig. 4 is a schematic diagram of an intelligent prescription recommendation method according to an embodiment of the present invention.
Fig. 5 is a schematic diagram of an electronic device according to an embodiment of the invention.
Reference numerals:
1. an electronic device;
10. a storage medium; 20. a processor.
Detailed Description
In order to explain in detail possible application scenarios, technical principles, practical embodiments, and the like of the present application, the following detailed description is given with reference to the accompanying drawings in conjunction with the listed embodiments. The embodiments described herein are merely for more clearly illustrating the technical solutions of the present application, and therefore, the embodiments are only used as examples, and the scope of the present application is not limited thereby.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase "an embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or related to other embodiments specifically defined. In principle, in the present application, the technical features mentioned in the embodiments can be combined in any manner to form a corresponding implementable technical solution as long as there is no technical contradiction or conflict.
Unless defined otherwise, technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the use of relational terms herein is intended only to describe particular embodiments and is not intended to limit the present application.
In the description of the present application, the term "and/or" is a expression for describing a logical relationship between objects, meaning that three relationships may exist, for example a and/or B, meaning: there are three cases of A, B, and both A and B. In addition, the character "/" herein generally indicates that the former and latter associated objects are in a logical relationship of "or".
In this application, terms such as "first" and "second" are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
Without further limitation, in this application, the use of "including," "comprising," "having," or other similar expressions in phrases and expressions of "including," "comprising," or "having," is intended to cover a non-exclusive inclusion, and such expressions do not exclude the presence of additional elements in a process, method, or article that includes an element, such that a process, method, or article that includes a list of elements may include not only those elements but also other elements not expressly listed or inherent to such process, method, or article.
As is understood in the examination of the guidelines, the terms "greater than", "less than", "more than" and the like in this application are to be understood as excluding the number; the expressions "above", "below", "within" and the like are understood to include the present numbers. In addition, in the description of the embodiments of the present application, "a plurality" means two or more (including two), and expressions related to "a plurality" similar thereto are also understood, for example, "a plurality of groups", "a plurality of times", and the like, unless specifically defined otherwise.
As shown in fig. 1, in a first aspect, the present application provides a method for recommending an intelligent prescription, the method comprising the steps of:
s1: obtaining patient information to carry out syndrome differentiation to obtain a diagnosis information set; the diagnostic information set comprises a set of diagnostic provenances;
s2: acquiring a plurality of pieces of first prescription information from a prescription database, and screening the first prescription information according to a diagnosis information set to obtain second prescription information; the second prescription information comprises a second necessary evidence information set and a second or evidence information set;
s3: determining candidate prescription information according to the corresponding relation among the second necessary evidence information set, the second or evidence information set and the diagnosis evidence set;
s4: and scoring all the candidate prescription information according to a preset rule, and determining a final recommended prescription according to a scoring result.
In the application, the patient information can be determined through the past medical record of the patient or the real-time diagnosis information, in the traditional Chinese medicine diagnosis process, the syndrome differentiation can be carried out on the patient information through the means of looking after, asking and cutting and the like, and the syndrome differentiation is recorded to form a diagnosis information set. The syndrome elements include wind, cold, summer-heat, dampness, dryness, fire, phlegm, dampness, food, insect, qi, blood, yin deficiency, yang deficiency, heart, spleen, lung, etc. Different patients have different symptoms, and corresponding affected parts have different syndromes.
The prescription database is a database in which a plurality of prescription information are stored in advance, each prescription information can be composed of one or more medicines, and the prescription information preferably comprises information such as a prescription number, a name, a contained medicine name, a necessary evidence element corresponding to the prescription, or an evidence element.
The prescription recommendation method is judged by taking the syndrome of the patient information as a diagnosis starting point, and is gradually determined by comparing the syndrome corresponding to the prescription with a diagnosis syndrome set in the prescription recommendation process, so that the finally recommended prescription has more representativeness and accuracy.
In certain embodiments, the first agent information comprises a first set of required witness information, a first or witness information set, and a first negative witness set; screening the first agent information against the set of diagnostic information comprises: rejecting the first agent information when it is determined that the first requisite credential information set is not a subset of the diagnostic credential set; and/or rejecting the first prescription information when it is determined that the first negative prescription intersects the diagnostic prescription.
"must have evidence" means that the patient's information must show evidence when using a certain formula, i.e. the formula must have the evidence. Therefore, if the first diagnostic syndrome set (i.e., the combination of the syndromes determined according to the current diagnostic information of the patient) does not belong to the subset of the diagnostic syndrome set, it is indicated that the necessary syndrome in a certain prescription contains the syndrome that does not appear in the current patient, i.e., the prescription does not meet the use condition of the syndrome that appears in the current patient, and therefore the information of the first prescription can be removed, so as to improve the accuracy of the final recommended prescription.
"negative evidence" refers to evidence that must not be present in the patient information when a prescription is used, i.e., the prescription can only be used if the negative evidence is not present in the patient's diagnosis. Therefore, if an intersection exists between the first negative evidence collection and the diagnosis evidence collection (namely evidence combination determined according to the current diagnosis information of the patient), the fact that the negative evidence of a certain prescription appears in the diagnosis evidence collection of the patient is indicated, namely the prescription does not accord with the evidence use condition appearing in the current patient, so that the information of the first prescription can be removed, and the accuracy of the final prescription recommendation is improved.
In certain embodiments, the set of diagnostic information further comprises a set of diagnostic syndromes, the first agent information comprising first negative syndrome information; screening the first agent information against the set of diagnostic information comprises: and when the intersection of the first negative syndrome information and the diagnosis syndrome set is judged, rejecting the first prescription information.
When the patient is diagnosed, besides the syndrome set of the patient, the syndrome information of the patient, such as fever, dysphoria, dry throat, thirst, profuse sweat, etc., can be determined. By comparing the syndrome information corresponding to the prescription with the diagnosis syndrome set of the patient, the matched prescription can be more accurate and can be administered according to the symptom.
The term "negative syndrome information" refers to a syndrome that must not be present in the patient's information when a certain prescription is used, i.e., the prescription can be used only when the patient's diagnosis does not show the negative syndrome. Therefore, if an intersection exists between the first negative syndrome information and the diagnosis syndrome set (namely the syndrome combination determined according to the current diagnosis information of the patient), the condition that a certain prescription is negative appears in the diagnosis syndrome set of the patient is indicated, namely the prescription does not accord with the syndrome use condition appearing in the current patient, so that the first prescription information can be removed, and the accuracy of the final prescription recommendation is improved.
Referring to fig. 2, step S4 includes:
s31: a second necessary evidence information set and a second or evidence information set corresponding to each second prescription information are subjected to union collection to obtain a first union combination;
s32: sequentially judging whether each first collection combination completely contains the diagnosis certificate collection;
if yes, go to step S321: determining second prescription information corresponding to the first collective combination as candidate prescription information;
otherwise, go to step S322: sequentially overlapping prescriptions in the plurality of pieces of second prescription information to perform a prescription combination, judging whether a union set of a first union set of the plurality of prescriptions after the prescription combination completely contains the diagnosis syndrome set, and if so, executing the step S3221: and determining the information of the second prescriptions corresponding to the union of the first set combination as the information of the candidate prescriptions after superposition.
In the present application, a diagnostic syndrome is a syndrome diagnosed from a patient. After the preliminary screening, the number of the second prescription information may be one or more. For each second prescription information, it may contain only one prescription (e.g. "Zhenwu decoction") or multiple prescriptions (e.g. "Ma Huang decoction" in combination with "Gui Zhi decoction" in combination with "Zhu Shi Gao decoction"). However, whether one or more prescriptions are included in the second prescription information, the necessary evidence and/or the evidence-containing collection in the second prescription information must be completely included in the diagnosis evidence set (i.e., the diagnosis evidence set is included in the set of evidence mapped by the screened prescriptions), and thus the second prescription information can be determined as candidate prescription information.
The elimination of the prescription which does not contain the necessary evidence is mainly considered by taking the prescription as a center, and the reason that the prescription must have the evidence is that the prescription can be used only after the evidence of the prescription appears, so that the prescription is called as the necessary evidence and the information of the corresponding prescription is not eliminated. In the application, the accuracy of the final recommended prescription is improved by setting the screening condition, namely, the syndrome diagnosed according to the disease condition (namely, the diagnosis syndrome set) is required to be combined by the union set of 'must-have-syndrome' and 'or-have-syndrome' of the prescription completely.
In some embodiments, the candidate prescription information includes a syndrome differentiation element; scoring all of the candidate formula information according to a predetermined rule includes: and judging whether each syndrome differentiation key syndrome element is contained in the syndrome element set or not, and if so, adding a first numerical value to the score of the corresponding candidate prescription information.
The key points of syndrome differentiation are the more disordered information about the formula, which may be the syndrome, or the syndrome (i.e., symptoms), or some more specific rules, such as the diagnosed syndrome score must be higher than another syndrome score to meet the syndrome differentiation key points, and the formula is preferably used. By judging whether each syndrome differentiation key element is contained in the syndrome differentiation element set, the candidate prescriptions corresponding to the candidate prescription information can be further screened, and the accuracy of the final recommended prescriptions is improved.
In certain embodiments, the candidate prescription information includes a third set of required provenance information and third or provenance information; as shown in fig. 3, scoring all the candidate prescription information according to a predetermined rule includes:
s41: a third necessary evidence information set and a third or evidence information set corresponding to each candidate prescription information are subjected to union collection to obtain a second union set;
s42: calculating the cross-over ratio of the second union set combination and the diagnosis certificate set, and adding a second numerical value to the score of the corresponding candidate prescription according to the cross-over ratio obtained by calculation; the magnitude of the second value is proportional to the magnitude of the calculated intersection ratio.
The cross-over ratio refers to a prescription candidate set, a union set of 'or evidence-containing' and 'necessary evidence-containing' in the prescriptions (the prescription combination in the candidate set may be 1 prescription or a second union set combination obtained by taking and combining a plurality of prescriptions), and then the union set is intersected with the diagnosis evidence set, and the obtained result is divided by the union set of 'or evidence-containing' and 'necessary evidence-containing' in the square preparation and the union set between the 'diagnosis evidence set'. Thus, the obtained cross-over ratio is less than or equal to 1, and the higher the cross-over ratio is, the closer to 1 is, the smaller the difference between the corresponding syndrome and the diagnosis syndrome set of the recommended prescription is, namely, the more accurate the recommended prescription is.
In some embodiments, the information about candidate prescriptions includes syndrome differentiation key point syndrome and prescription indication syndrome; the diagnosis information set comprises a diagnosis syndrome set; scoring all of the candidate formula information according to a predetermined rule includes: judging whether each syndrome differentiation key point syndrome is contained in the diagnosis syndrome set, if so, adding a third numerical value to the score of the corresponding candidate prescription information; and/or calculating the similarity of the main treatment syndrome of each prescription and the diagnosis syndrome set, and adding a fourth numerical value to the score of the corresponding candidate prescription according to the calculated similarity; the magnitude of the fourth value is proportional to the magnitude of the similarity obtained by calculation.
The similarity between the main syndrome of the formula and the diagnostic syndrome set can be determined according to the number of the commonly appeared syndromes, and the more the number of the commonly appeared syndromes is, the higher the similarity between the main syndrome of the formula and the diagnostic syndrome set is. The accuracy of the recommended prescription can be effectively improved by further judging the information of the candidate prescription by taking the key point syndrome and the main treatment syndrome of the prescription as the scoring factors of the prescription.
In some embodiments, determining the final recommended prescription based on the scoring results includes: and screening a plurality of pieces of recommended prescription information with the top grade as final recommended prescriptions. After the finally recommended prescriptions are screened out, the attending physician can screen out the prescriptions which are beneficial to the current patient from the finally recommended prescriptions according to the clinical experience of the attending physician, and because the prescriptions are recommended and generated according to the diagnosis certification information of the patient step by step, the diagnosis and treatment efficiency is greatly improved.
In certain embodiments, the method further comprises: obtaining syndrome differentiation key point conditions corresponding to information of each recommended prescription in the final recommended prescription, judging whether the diagnosis information set meets the syndrome differentiation key point conditions, if not, removing the information of the recommended prescription from the final recommended prescription, and selecting information of the recommended prescription with the next grade size for judging again until the number of the information of the recommended prescription contained in the final recommended prescription meets the preset requirement. The syndrome differentiation key point condition herein refers to a specific rule that a certain prescription needs to satisfy, for example, the syndrome differentiation key point condition of yin qiao xue tang is that "wet syndrome element score > heat 30 minutes" and if the final recommended prescription determined according to the scoring result contains the prescription of yin qiao xue tang, it is found by judgment that the wet syndrome element score in the current patient's diagnosis information set is less than heat 30 minutes, in which case the prescription containing yin qiao xue tang may be excluded from the final recommended prescription and the next scored recommended prescription information is selected to continue the judgment until the number of the recommended prescription information contained in the final recommended prescription satisfies the predetermined requirement.
In a second aspect, the present application provides a storage medium 10, the storage medium 10 storing a computer program, which when executed by a processor, performs the method steps as in the first aspect of the present application.
In a third aspect, as shown in fig. 5, the present application provides an electronic device 1, comprising a processor 20 and a storage medium 10, where the storage medium 10 is the storage medium of the second aspect, and the processor 20 is configured to execute the computer program stored in the storage medium. Preferably, the electronic device is a computer device.
Storage media includes both computer storage media and communication media including any medium that can be enabled to transfer a computer program from one place to another. A storage media may be any available media that can be accessed by a computer. By way of example, and not limitation, non-transitory media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that may be used to store desired program code in the form of instructions or data structures and that may be accessed by a computer. Also, any connection is properly termed a computer-readable medium. Disk and disc, as used herein, includes Compact Disc (CD), laser disc, optical disc, Digital Versatile Disc (DVD), floppy disk and blu-ray disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media. Additionally, the operations of a method or algorithm may reside as any one or any combination or set of codes and instructions on a machine-readable medium or computer-readable medium, which may be incorporated into a computer program product.
The processor includes a general purpose single-or multi-chip processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor or any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. In some implementations, certain processes and methods may be performed by circuitry that is specific to a given function.
In order for the reader to more intuitively understand certain embodiments of the present application, the following examples are also provided for the reader's reference.
As shown in fig. 4, the present application provides an intelligent prescription recommendation method, which specifically comprises the following steps:
s11: establishing a database according to the known prescriptions, and labeling each prescription, wherein the labeling content comprises: it must have the syndrome differentiation, or have the syndrome differentiation, negative syndrome differentiation, key point syndrome differentiation, principal indication of the recipe, and key point condition of syndrome differentiation. The specific sample information is shown as follows:
TABLE 1
S21: obtaining patient information, carrying out syndrome differentiation, and obtaining a 'diagnostician' set A ═ a1，a2，...，anThe set of "diagnosis syndromes" B ═ B1，b2，...，bn}；
S3.1: all prescriptions in the prescription database are used as a set C ═ C of' first prescription information1，c2，...，cnAnd fifthly, screening.
S3.2: the contents of the specific prescriptions in the "first prescription information" set C are sequentially judged and screened according to the following modes:
s3.2.1: when the must-have-Certification set C of the first-party information set CbyzsWhen not a subset of the "diagnostic provenance" set A, i.e.
The prescription information is deleted from the "first prescription information" set.
S3.2.2: : set C of "negative Certification" when set C of "first agent informationfdzsWhen there is an intersection with the "diagnostic syndrome" set A, i.e.
The prescription information is deleted from the "first prescription information" set C.
S3.2.3: set C of "negative symptoms" when set C of "first agent informationfdzhWhen there is an intersection with the "diagnostic syndrome" set B, i.e.
The prescription information is deleted from the "first prescription information" set C.
S3.2.4: tong (Chinese character of 'tong')After being screened in the steps of S3.2.1-S3.2.3, the screened first prescription information is used as a second prescription information set C for forming the prescription combinationbasicSo that the "must have evidence element" set C of the second prescription informationbyzsAnd "Or Certification element" set ChyzsUnion of (C)byzs∪ChyzsContains a set A of "diagnostic markers".
S4.1.1: according to the formula, the collection of essential evidentials and the union C of essential evidentialsbyzs∪ChyzsThe lengths are sorted from large to small.
S4.1.2: creating an empty stack S, and adding a 'candidate prescription' set C in sequencebasicThe prescription of (1).
S4.1.3: when the "must-have-syndrome" set and the "or-syndrome" set combination of combinations of prescriptions in the stack comprise a "diagnostic syndrome" set, that is
The combination in the stack is added to the second prescription information.
S4.1.4: if the queue in S4.1.3 satisfies the second prescription information requirement, the top element of the stack is popped and the subsequent prescriptions continue to be added to the queue.
S4.1.5: when the stack is empty, the next one of the last retrieved formulas in the stack is added to the stack and step S4.1.3 is performed.
For example, the last prescription matching is "ma huang, Gui Zhi, gan Cao", and the sequence of exiting from the stack is gan Cao, Gui Zhi, ma huang, then the next prescription refers to Gui Zhi, and the beginning of Gui Zhi is regularly matched with the subsequent prescriptions.
S5: when all prescriptions are judged, a set D ═ D of candidate prescription combinations is obtained1，d2，...，dn}。
S6: : the candidate prescription combinations were voted for in the following 4 aspects, and the best prescription was selected from the candidate prescription combinations.
S7.1: the syndrome differentiation key point syndrome element rule judges whether the syndrome elements of the syndrome differentiation key points corresponding to the prescription are contained in the syndrome differentiation element set, and if the syndrome elements are in accordance with the syndrome differentiation element rule, 0.5 point is added;
s7.2: "syndrome differentiation key point syndrome rule" to determine whether the syndrome of syndrome differentiation key point corresponding to the prescription is included in the "diagnosis syndrome" set, and if yes, 0.5 point is added;
s7.3: the rule of the indication syndrome of the prescription is used for calculating the similarity between the indication syndrome and the diagnosis syndrome of the prescription and linearly ordering the result R ═ R1，r2，...，Ti，...，rnAnd assigning values from large to small, wherein the highest score is 1, the lowest score is 0.1, and the result is
For voting;
s7.4: the 'cross-over ratio rule' calculates the cross-over ratio of the union set of 'or evidence element' and 'must evidence element' in the prescription and the 'diagnosis evidence element' set, and carries out linear ordering on the results, wherein R is { R ═ R }1，r2，...，ri，...，rnAnd assigning values from large to small, wherein the highest score is 0.75, the lowest score is 0.1, and the result is
For voting.
S8: the first three prescriptions with the highest calculated score are combined and taken out.
S9: the prescriptions which do not meet the key condition of syndrome differentiation in the first three prescription combinations with the highest scores are removed and ranked smoothly, and the first three groups of prescriptions which are finally recommended are obtained for reference.
As will be appreciated by one skilled in the art, the above-described embodiments may be provided as a method, apparatus, or computer program product. These embodiments may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. All or part of the steps of the methods related to the above embodiments may be implemented by a program instructing related hardware, and the program may be stored in a storage medium readable by a computer device and used for executing all or part of the steps of the methods related to the above embodiments. Computer devices including, but not limited to: personal computers, servers, general-purpose computers, special-purpose computers, network devices, embedded devices, programmable devices, intelligent mobile terminals, intelligent home devices, wearable intelligent devices, vehicle-mounted intelligent devices, and the like; storage media including, but not limited to: RAM, ROM, magnetic disk, magnetic tape, optical disk, flash memory, U disk, removable hard disk, memory card, memory stick, network server storage, network cloud storage, etc.
The various embodiments described above are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a computer apparatus to produce a machine, such that the instructions, which execute via the processor of the computer apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer device to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer apparatus to cause a series of operational steps to be performed on the computer apparatus to produce a computer implemented process such that the instructions which execute on the computer apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Although the embodiments have been described, once the basic inventive concept is obtained, other variations and modifications of these embodiments can be made by those skilled in the art, so that these embodiments are only examples of the present invention, and not intended to limit the scope of the present invention, and all equivalent structures or equivalent processes that can be used in the present specification and drawings, or used directly or indirectly in other related fields are encompassed by the present invention.
Claims (10)
1. An intelligent prescription recommendation method is characterized by comprising the following steps:
s1: obtaining patient information to carry out syndrome differentiation to obtain a diagnosis information set; the set of diagnostic information comprises a set of diagnostic witnesses;
s2: acquiring a plurality of pieces of first prescription information from a prescription database, and screening the first prescription information according to the diagnosis information set to obtain second prescription information; the second prescription information comprises a second necessary evidence information set and a second or evidence information set;
s3: determining candidate prescription information according to the corresponding relation among the second necessary evidence information set, the second or evidence information set and the diagnosis evidence set;
s4: and scoring all the candidate prescription information according to a preset rule, and determining a final recommended prescription according to a scoring result.
2. The intelligent agent recommendation method of claim 1, wherein the first agent information comprises a first set of required witness information, a first set of or witness information, and a first set of negative witness information;
said screening said first agent information according to said set of diagnostic information comprises:
culling the first party agent information when it is determined that the first requisite evidence set is not a subset of the diagnostic evidence set;
and/or culling the first party agent information when it is determined that there is an intersection between the first negative syndrome set and the diagnostic syndrome set.
3. The intelligent agent recommendation method of claim 1, wherein the diagnostic information set further comprises a diagnostic syndrome set, the first agent information comprises first negative syndrome information;
said screening said first agent information according to said set of diagnostic information comprises:
and when the first negative syndrome information and the diagnosis syndrome set are judged to have intersection, rejecting the first prescription information.
4. The intelligent prescription recommendation method of claim 1, wherein step S4 comprises:
s31: a second necessary evidence information set and a second or evidence information set corresponding to each second prescription information are subjected to union collection to obtain a first union combination;
s32: sequentially judging whether each first collection combination completely contains the diagnosis certificate collection;
if yes, go to step S321: determining second prescription information corresponding to the first collective combination as candidate prescription information;
otherwise, go to step S322: sequentially overlapping prescriptions in the plurality of pieces of second prescription information to perform a prescription combination, judging whether a union set of a first union set of the plurality of prescriptions after the prescription combination completely contains the diagnosis syndrome set, and if so, executing the step S3221: and determining the information of the second prescriptions corresponding to the union of the first set combination as the information of the candidate prescriptions after superposition.
5. The intelligent prescription recommendation method of claim 1, wherein the candidate prescription information comprises a syndrome differentiation element;
the scoring of all the candidate prescription information according to a predetermined rule comprises:
and judging whether each syndrome differentiation key syndrome element is contained in the syndrome element set or not, and if so, adding a first numerical value to the score of the corresponding candidate prescription information.
6. The intelligent prescription recommendation method of claim 1, wherein the candidate prescription information comprises a third set of required provenance information and third or provenance information;
the scoring of all the candidate prescription information according to a predetermined rule comprises:
a third necessary evidence information set and a third or evidence information set corresponding to each candidate prescription information are subjected to union collection to obtain a second union set;
calculating the cross-over ratio of the second union set combination and the diagnosis syndrome set, and adding a second numerical value to the score of the corresponding candidate prescription according to the calculated cross-over ratio; the magnitude of the second numerical value is in direct proportion to the magnitude of the calculated intersection ratio.
7. The intelligent prescription recommendation method of claim 1, wherein the candidate prescription information comprises a syndrome differentiation key point syndrome and a prescription indication syndrome; the diagnosis information set comprises a diagnosis syndrome set;
the scoring of all the candidate prescription information according to a predetermined rule comprises:
judging whether each syndrome differentiation key point syndrome is contained in the diagnosis syndrome set, and if so, adding a third numerical value to the score of the corresponding candidate prescription;
and/or calculating the similarity of the main symptoms of each prescription and the diagnosis syndrome set, and adding a fourth numerical value to the score of the corresponding candidate prescription according to the calculated similarity; and the magnitude of the fourth numerical value is in direct proportion to the magnitude of the similarity obtained by calculation.
8. The intelligent formula recommendation method of claim 1, wherein determining the final recommended formula based on the scoring comprises:
and screening a plurality of pieces of recommended prescription information with the top grade as final recommended prescriptions.
9. The intelligent prescription recommendation method of claim 8, further comprising:
obtaining syndrome differentiation key point conditions corresponding to information of each recommended prescription in the final recommended prescription, judging whether the diagnosis information set meets the syndrome differentiation key point conditions, if not, eliminating the information of the recommended prescription from the final recommended prescription, and selecting information of the recommended prescription with the next grade for judgment again until the number of the information of the recommended prescription contained in the final recommended prescription meets the preset requirement.
10. A storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, carries out the method steps of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111527972.2A CN114283925B (en) | 2022-01-17 | 2022-01-17 | Intelligent prescription recommendation method and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111527972.2A CN114283925B (en) | 2022-01-17 | 2022-01-17 | Intelligent prescription recommendation method and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114283925A true CN114283925A (en) | 2022-04-05 |
| CN114283925B CN114283925B (en) | 2024-08-20 |
Family
ID=80872070
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111527972.2A Active CN114283925B (en) | 2022-01-17 | 2022-01-17 | Intelligent prescription recommendation method and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114283925B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110929511A (en) * | 2018-09-04 | 2020-03-27 | 清华大学 | Intelligent matching method for personalized traditional Chinese medicine diagnosis and treatment information and traditional Chinese medicine information based on semantic similarity |
| CN111191020A (en) * | 2019-12-27 | 2020-05-22 | 江苏省人民医院（南京医科大学第一附属医院） | Prescription recommendation method and system based on machine learning and knowledge graph |
| CN111312359A (en) * | 2020-02-03 | 2020-06-19 | 广东省第二人民医院（广东省卫生应急医院） | Intelligent recommendation method and device for medication scheme |
| CN112992378A (en) * | 2021-04-25 | 2021-06-18 | 南京大经中医药信息技术有限公司 | Multi-dimensional traditional Chinese medicine prescription recommendation method and recommendation system |
-
2022
- 2022-01-17 CN CN202111527972.2A patent/CN114283925B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110929511A (en) * | 2018-09-04 | 2020-03-27 | 清华大学 | Intelligent matching method for personalized traditional Chinese medicine diagnosis and treatment information and traditional Chinese medicine information based on semantic similarity |
| CN111191020A (en) * | 2019-12-27 | 2020-05-22 | 江苏省人民医院（南京医科大学第一附属医院） | Prescription recommendation method and system based on machine learning and knowledge graph |
| CN111312359A (en) * | 2020-02-03 | 2020-06-19 | 广东省第二人民医院（广东省卫生应急医院） | Intelligent recommendation method and device for medication scheme |
| CN112992378A (en) * | 2021-04-25 | 2021-06-18 | 南京大经中医药信息技术有限公司 | Multi-dimensional traditional Chinese medicine prescription recommendation method and recommendation system |
Non-Patent Citations (2)
| Title |
|---|
| 徐佳君;罗志明;赵文;雷黄伟;周常恩;李绍滋;李灿东;: "基于人工智能算法的中医状态辨识规则", 中医杂志, no. 03, 2 February 2020 (2020-02-02) * |
| 赵晖;王大伟;姜幼明;薛飞飞;李淳;: "亚健康中医证候量化诊断标准研究思路探析", 北京中医药大学学报, no. 04, 30 April 2016 (2016-04-30) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114283925B (en) | 2024-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111191020B (en) | Prescription recommendation method and system based on machine learning and knowledge graph | |
| US7917377B2 (en) | Patient data mining for automated compliance | |
| CN108461110B (en) | Medical information processing method, device and equipment | |
| JP2004288047A (en) | Medical examination support system and medical examination support program | |
| CN114283947B (en) | Health management method and system suitable for surgical patients | |
| CN110674244B (en) | Structured processing method and device for medical text | |
| TW201040756A (en) | Chinese medicine intelligent formulary system | |
| CN114416967A (en) | Method, device and equipment for intelligently recommending doctors and storage medium | |
| CN114023423A (en) | Intelligent shift switching method, device and equipment | |
| WO2019196211A1 (en) | Method for filtering medical records, terminal device, and computer readable storage medium | |
| CN103559675B (en) | Case history input device and case history input method | |
| CN111967540B (en) | Maxillofacial fracture identification method and device based on CT database and terminal equipment | |
| CN114283925A (en) | Intelligent prescription recommendation method and storage medium | |
| CN115881259A (en) | Medical record data processing method, device, equipment and storage medium | |
| CN116313076A (en) | Information processing method based on intelligent main examination program of physical examination system | |
| CN115374113A (en) | Patient main index data generation method, system and device | |
| Bacak et al. | Computerized hybrid decision-making system for hormone replacement therapy in menopausal women | |
| CN113674827A (en) | Electronic medical record generation method and device, electronic equipment and computer readable medium | |
| Mardian et al. | Forward Chaining and Certainly Factor Method Optimization for Lung Disease Expert System | |
| Hunt et al. | Costs associated with anesthesia-related adverse events during labor and delivery in New York State, 2010 | |
| Iwai et al. | Prediction of post-induction hypotension using stacking method | |
| JP4808063B2 (en) | Critical path generation method and apparatus | |
| CN108198626A (en) | The method for building up and system of traditional Chinese medical science diabetes intelligence interrogation list | |
| CN118588315B (en) | Method for constructing traditional Chinese medicine acupuncture point curative effect database | |
| CN118609801B (en) | Surgical anesthesia information early warning method and system based on clinical auxiliary decision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |