HK40040596B

HK40040596B - Detection method, device, computer system and storage medium of diagnostic data anomaly

Info

Publication number: HK40040596B
Application number: HK42021030231.1A
Authority: HK
Inventors: 唐蕊
Original assignee: 平安科技（深圳）有限公司
Filing date: 2021-04-30
Publication date: 2023-08-04

Description

Diagnostic data abnormality detection method, diagnostic data abnormality detection device, computer device, and storage medium

Technical Field

The present invention relates to the field of intelligent medical technology, and in particular, to a diagnostic data anomaly detection method, apparatus, computer device, and storage medium.

Background

Misdiagnosis refers to a doctor giving a false diagnosis to a patient for various reasons. Misdiagnosis is very common, and investigation data shows that the misdiagnosis rate of diseases is usually about 30%. Misdiagnosis can lead to serious consequences such as incorrect treatment regimens, delays in patient treatment. Therefore, timely detection of misdiagnosis is necessary.

The existing misdiagnosis detection method is based on that doctors write medical rules for each disease according to medical knowledge to carry out misdiagnosis detection on diagnosis of patients, whether the disease diagnosed at the time meets the medical rules corresponding to the disease is judged, and if the disease does not meet the rules, misdiagnosis exists in the diagnosis. However, existing misdiagnosis detection methods exist: the medical rules are obtained by the doctor according to medical knowledge, and the problems of high energy consumption, high time cost, low flexibility, low precision of misdiagnosis detection and the like are solved.

Disclosure of Invention

Aiming at the problems of poor flexibility and low detection precision of the existing misdiagnosis detection method, the device, the computer equipment and the storage medium for detecting the abnormal diagnosis data are provided, which aim to improve the flexibility and the detection precision of the misdiagnosis detection.

In order to achieve the above object, the present invention provides a diagnostic data abnormality detection method, comprising:

obtaining diagnostic data of a target patient;

matching the diagnosis data with a preset medical rule to obtain first candidate information;

matching the diagnosis data with a medical mining rule to obtain second candidate information;

fusing the first candidate information and the second candidate information to generate third candidate information;

identifying the diagnosis data by adopting a disease identification model to obtain fourth candidate information;

and fusing the third candidate information and the fourth candidate information to obtain suspected disease information, and judging whether the diagnosis data is abnormal according to the suspected disease information.

Optionally, obtaining diagnostic data of the target patient includes:

receiving medical data of a target patient sent by a user terminal, wherein the medical data comprises: basic information of the target patient, the target disease type, and a plurality of medical entities;

extracting the medical entity in the medical data, generating the diagnostic data.

Optionally, the preset medical rule is a rule preset according to medical knowledge, including a plurality of medical rules, each medical rule includes at least one medical entity, and each medical rule corresponds to a disease type;

matching the diagnosis data with a preset medical rule to obtain first candidate information, wherein the first candidate information comprises:

matching a plurality of medical entities in the diagnosis data with each of the medical rules in the preset medical rules respectively to obtain the matching degree of the disease types matched with the diagnosis data;

and extracting matching degrees of all disease types matched with the diagnosis data, and generating the first candidate information.

Optionally, matching the diagnostic data with a medical mining rule to obtain second candidate information, and before the step of obtaining the second candidate information further includes:

generating the medical mining rule according to historical sample data:

the historical sample data includes a plurality of pieces of historical medical data, each piece of the historical medical data including a disease type of a historical patient and a plurality of the medical entities;

the medical mining rules comprise a plurality of mining rules, each mining rule comprises at least one medical entity, and each mining rule corresponds to one disease type;

classifying the historical medical data in the historical sample data according to the disease types to generate a disease type set;

and screening the historical medical data in the disease type set by adopting a frequent set mining algorithm to generate mining rules corresponding to the disease types.

Optionally, matching the diagnostic data with a medical mining rule to obtain second candidate information, including:

matching a plurality of medical entities in the diagnostic data with each of the mining rules in the medical mining rules respectively to obtain a matching degree of a disease type matched with the diagnostic data;

and extracting matching degrees of all disease types matched with the diagnosis data, and generating the second candidate information.

Optionally, fusing the first candidate information and the second candidate information to generate third candidate information, including:

and calculating a matching average value of the matching degree of the same disease type corresponding to the first candidate information and the matching degree corresponding to the second candidate information according to the disease type in the first candidate information and the disease type in the second candidate information, and generating the third candidate information comprising the disease type matching average value.

Optionally, the fourth candidate information includes a matching value of a disease type;

fusing the third candidate information and the fourth candidate information to obtain suspected disease information, and judging whether the diagnosis data is abnormal according to the suspected disease information, wherein the method comprises the following steps:

calculating a suspected value for a matching average value corresponding to the same disease type in the third candidate information and a matching value corresponding to the fourth candidate information;

extracting the disease type of which the suspected value meets a preset condition, and generating the suspected disease information;

and matching the target disease type in the diagnosis data with the disease type in the suspected disease information, if so, indicating that the diagnosis data is normal, and if not, indicating that the diagnosis data is abnormal.

In order to achieve the above object, the present invention also provides a diagnostic data abnormality detection apparatus comprising:

an acquisition unit configured to acquire diagnostic data of a target patient;

the first matching unit is used for matching the diagnosis data with a preset medical rule to obtain first candidate information;

the second matching unit is used for matching the diagnosis data with the medical mining rules to obtain second candidate information;

the fusion unit is used for fusing the first candidate information and the second candidate information to generate third candidate information;

the identification unit is used for identifying the diagnosis data by adopting a disease identification model to obtain fourth candidate information;

a processing unit for fusing the third candidate information and the fourth candidate information to obtain suspected disease information, and judging whether the diagnostic data is abnormal according to the suspected disease information

To achieve the above object, the present invention also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the above method when executing the computer program.

To achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the above method.

The diagnostic data abnormality detection method, the diagnostic data abnormality detection device, the diagnostic data abnormality detection computer and the diagnostic data storage medium can respectively match the diagnostic data of the target patient with two rules of a preset medical rule and a medical mining rule to obtain two candidate information, and the two candidate information is fused to obtain multi-dimensional third candidate information combined with the medical rule and the medical mining rule; the disease identification model is adopted to identify the diagnosis data to obtain fourth candidate information, so that the flexibility of identifying the diagnosis data is improved, and the identification speed is high; the suspected disease information of the target patient is determined by combining the fourth candidate information and the third candidate information, so that whether the diagnosis data is abnormal or not can be judged according to the suspected disease information, and the purpose of quickly and effectively confirming misdiagnosis is achieved.

Drawings

FIG. 1 is a flow chart of one embodiment of a diagnostic data anomaly detection method according to the present invention;

FIG. 2 is a flow chart of one embodiment of the present invention for obtaining diagnostic data of a subject patient;

FIG. 3 is a flow chart of one embodiment of the present invention for obtaining first candidate information;

FIG. 4 is a flow chart of one embodiment of the present invention for generating the medical mining rules from historical sample data;

FIG. 5 is a flow chart of one embodiment of the present invention for obtaining second candidate information;

FIG. 6 is a flow chart of one embodiment of fusing third candidate information and fourth candidate information to obtain suspected disease information;

FIG. 7 is a block diagram of an embodiment of a diagnostic data anomaly detection device according to the present invention;

FIG. 8 is a hardware architecture diagram of one embodiment of a computer device of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.

It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other.

The diagnostic data anomaly detection method, the diagnostic data anomaly detection device, the computer equipment and the storage medium are suitable for the field of intelligent medical service. According to the invention, the diagnosis data of the target patient can be respectively matched with two rules of a preset medical rule and a medical mining rule to obtain two candidate information, and the two candidate information is fused to obtain multi-dimensional third candidate information combined with the medical rule and the medical mining rule; the disease identification model is adopted to identify the diagnosis data to obtain fourth candidate information, so that the flexibility of identifying the diagnosis data is improved, and the identification speed is high; determining suspected disease information of the target patient by combining the fourth candidate information and the third candidate information so as to judge whether the suspected disease information contains the disease type in the diagnosis data, namely whether the diagnosis data is abnormal or not, if so, indicating that the diagnosis data is normal; if not, the abnormal diagnosis of the diagnosis data is indicated, so that the purpose of quickly and effectively confirming the misdiagnosis is achieved.

Example 1

Referring to fig. 1, a diagnostic data anomaly detection method of the present embodiment includes the following steps:

s1, acquiring diagnosis data of a target patient.

Further, the step S1 shown in fig. 2 may include the following steps:

s11, receiving medical data of a target patient sent by a user terminal, wherein the medical data comprises: basic information of the target patient, the target disease type, and a plurality of medical entities.

Wherein, the basic information of the target patient can include: the number for identifying the identity of the target patient (such as an identity card, a medical insurance card number and the like), information of age, gender, main complaints, current medical history, family history and the like; the target disease type may be a disease class number; the medical entity may be a number of the test item, for example: blood test items (such as blood pressure, hemoglobin, and platelets), urine test items (such as protein, ketone body, and glucose), and the like.

S12, extracting the medical entity in the medical data, and generating the diagnosis data.

In this embodiment, the diagnostic data consists of the number (ID) of the medical entity, such as: [ medical entity X1, medical entity X2, medical entity X3, … … ], X in the medical entity representing the ID of the medical entity.

S2, matching the diagnosis data with a preset medical rule to obtain first candidate information.

The preset medical rules are preset rules obtained by medical knowledge (medical knowledge is organized by doctors) and comprise a plurality of medical rules, each medical rule comprises at least one medical entity, and each medical rule corresponds to one disease type.

By way of example and not limitation, the presentation of medical rules is generally, for example, disease 1→ (medical entity 1, medical entity 3): representing that the simultaneous occurrence of medical entity 1 and medical entity 3 in the diagnostic data may add disease 1 to the first candidate information of the target patient; disease 2→ (medical entity 1, medical entity 5, medical entity 10): representing the simultaneous presence of medical entity 1, medical entity 5 and medical entity 10 in the diagnostic data, the disease 2 may be added to the first candidate information of the target patient.

Further, the step S2 shown in fig. 3 may include the following steps:

s21, matching the medical entities in the diagnosis data with each medical rule in the preset medical rules respectively to obtain the matching degree of the disease types matched with the diagnosis data.

In this embodiment, when the medical rule is matched, all the medical entities in the diagnostic data are respectively matched with all the entities in each medical rule, if all the entities in the medical rule are matched with all or part of the entities in the diagnostic data, it can be confirmed that the diagnostic data are matched with the disease types corresponding to the medical rule, and if part of the entities in the medical rule are matched with all or part of the entities in the diagnostic data, it indicates that the diagnostic data are not matched with the disease types corresponding to the medical rule.

For example: the diagnostic data of the target patient (comprising a plurality of medical entities) is matched into preset medical rules, resulting in the following results. Assuming a total of 5 rules, see table 1 for 3 disease types:

TABLE 1

Medical rules	Disease type	Rule matching results	Degree of matching
				Rule 1	Disease 1	Matching	1
Rule 2	Disease 1	Mismatch of	0
				Rule 3	Disease 2	Mismatch of	0
Rule 4	Disease 2	Mismatch of	0
				Rule 5	Disease 3	Matching	1

And in the preset medical rule, setting the matching degree of the disease type corresponding to the matched medical rule to be 1. If there are multiple medical rules for a disease type, the degree of matching of diagnostic data to the disease is set to 1 as long as the diagnostic data matches any one of the rules, e.g., rule 1 and rule 2 in the table above correspond to disease 1, and although the diagnostic data matches only rule 1, the degree of matching of the diagnostic data to disease 1 is set to 1.

S22, extracting matching degrees of all disease types matched with the diagnosis data, and generating the first candidate information.

In combination with the table 1, the disease type with a matching degree of 1 is extracted, and the first candidate information is: { disease 1:1, disease 3:1}.

In an embodiment, before performing step S3, the method may further include: and generating the medical mining rule according to the historical sample data.

It should be noted that: the historical sample data includes a plurality of pieces of historical medical data, each piece of the historical medical data including a disease type of a historical patient and a plurality of the medical entities. The medical mining rules include a plurality of mining rules, each mining rule including at least one of the medical entities, each mining rule corresponding to a disease type.

Further, referring to fig. 4, generating the medical mining rule according to the historical sample data includes the following steps:

A1. classifying the historical medical data in the historical sample data according to the disease types to generate a disease type set.

In particular, calculating a weight value for each of said medical entities and corresponding said disease types; and extracting medical entities with weight values greater than or equal to the weight threshold value in the historical sample data one by one.

The historical medical data is classified according to disease types, and a weight value is calculated for each medical entity in the historical medical data corresponding to each disease type. Medical entities having weight values less than the weight threshold (weight threshold between 0 and 1, [0,1 ]) are filtered out. The purpose of filtering the medical entities of each disease type is to reduce interference, remove frequently occurring but less differentiated and less important medical entities, and improve the quality of the data.

Wherein, the calculation formula of the weight value: weight [ medical entity i, disease j ] = (number of times medical entity i appears in disease j)/(how many diseases medical entity i appears in). i represents an ID of the medical entity; j represents the ID of the medical entity. If weight [ medical entity i, disease j ] < threshold, remove the medical entity.

A2. And screening the historical medical data in the disease type set by adopting a frequent set mining algorithm to generate mining rules corresponding to the disease types.

The frequent set mining algorithm is adopted to screen a plurality of pieces of historical sample data corresponding to each disease type after filtering based on two thresholds of a preset support degree (min_support) and a preset confidence degree (min_confidence), so as to obtain mining rules corresponding to each disease type, for example: for disease 1, 3 data-based rules were obtained after two thresholds were met, namely: { [ medical entity 1, medical entity 3, medical entity 9], [ medical entity 1, medical entity 3, medical entity 5, medical entity 7], [ medical entity 1, medical entity 5, medical entity 7, medical entity 9, medical entity 10] }. And excavating rules corresponding to each disease type, and arranging the mining rules from large to small according to the support degree.

The Frequent-Pattern Growth (FP-Growth) algorithm is an iterative method called layer-by-layer search, for example: the k-term set is employed for exploring the (k+1) -term set. First, find a set of frequent 1-item sets, record the set as L ₁ Employing set L ₁ Set L for finding frequent 2-item sets ₂ Then adopt the set L ₂ For finding L ₃ And so on until no frequent k-term sets can be found, where each L is found _k One database scan is required. S3, matching the diagnosis data with the medical mining rule to obtain second candidate information.

Further, the step S3 shown in fig. 5 may include the following steps:

s31, matching a plurality of medical entities in the diagnosis data with each mining rule in the medical mining rules respectively so as to obtain the matching degree of the disease type matched with the diagnosis data.

Matching the diagnosis data with all mining rules respectively, and for a disease type, if a certain rule of the disease type is matched, taking the support degree corresponding to the rule as the matching degree of the data for the disease; if no rule is matched to the disease type, the degree of matching of the historical medical data to this disease type is set to 0. And similarly, obtaining a probability list of the diagnosis data for all disease types, and sequencing the disease types in the list from large to small according to the matching degree. Note that if one piece of data matches to a plurality of rules of one disease, the rule with the highest matching degree is taken.

For example: for disease 1, the support threshold is set to 0.7, corresponding to 3 mining rules in table 2, and the support corresponding to each mining rule is as follows:

TABLE 2

When the diagnostic data contains 4 medical entities: [ medical entity 1, medical entity 2, medical entity 3, medical entity 9] the diagnostic data corresponds to rule 1 in table 2 for disease 1 (the piece of data contains all three medical entities in rule 1), i.e. the probability that the diagnostic data corresponds to disease 1 is 0.80.

S32, extracting matching degrees of all disease types matched with the diagnosis data, and generating the second candidate information.

Take 10 disease types as an example: matching the diagnostic data to mining rules corresponding to all disease types, as shown in table 3:

TABLE 3 Table 3

Numbering device	Rule matching results	Support degree
			Disease 1	Match to a certain rule	0.80
Disease 2	Without matching to any rule	0
			Disease 3	Without matching to any rule	0
Disease 4	Match to a certain rule	0.85
			Disease 5	Without matching to any rule	0
Disease 6	Without matching to any rule	0
			Disease 7	Match to a certain rule	0.70
Disease 8	Without matching to any rule	0
			Disease 9	Without matching to any rule	0
Disease 10	Without matching to any rule	0

Obtaining 3 disease types, extracting the supporting degree (matching degree) of each matched disease type, wherein the second candidate information is as follows: { disease 1:0.82, disease 4:0.85, disease 7:0.70}.

It is emphasized that the preset medical rules and medical mining rules may also be stored in nodes of a blockchain in order to further ensure privacy and security of the preset medical rules and medical mining rules. The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.

S4, fusing the first candidate information and the second candidate information to generate third candidate information.

Further, step S4 may include: and calculating a matching average value of the matching degree of the same disease type corresponding to the first candidate information and the matching degree corresponding to the second candidate information according to the disease type in the first candidate information and the disease type in the second candidate information, and generating the third candidate information comprising the disease type matching average value.

In an embodiment, the matching degree in the first candidate information and the second candidate information is subjected to weight fusion to obtain fused third candidate information, for example, third candidate information L corresponding to the diagnostic data _rule = { disease 4:0.95, disease 2:0.90, disease 1:0.5, … … }.

S5, identifying the diagnosis data by using a disease identification model to obtain fourth candidate information.

Wherein the fourth candidate information includes a matching value for a disease type.

In this embodiment, the disease recognition model adopts a BERT (Bidirectional Encoder Representations from Transformers) model, the BERT is input as diagnostic data, and the BERT is output as fourth candidate information.

The BERT model is a language model in the field of natural language processing, and can directly process natural language without conversion. However, the patient's visit data contains not only unstructured data, i.e. free text data, but also a large amount of structured data, whereas the BERT model can only process free text data. In order to enable the BERT model to process both structured and unstructured data, the present embodiment improves on the BERT model. The unstructured data and the structured data are spliced and then input into a BERT model, wherein each word (w) of the unstructured data is correspondingly input into one token, and each code (c) of the structured data is correspondingly input into one token. The BERT model is improved, an original segment embedding layer in the BERT model is removed, and an original positioning layer is improved. Unstructured data, i.e., text, is ordered so that the token of the corresponding positioning of unstructured data has an embedded representation of the position. However, the structured data is unordered, and all the token's placement for all structured data are put into the same embedded expression.

Based on the Chinese pre-trained BERT model, the structured data is added into a dictionary for expansion. Based on the Chinese pre-training model, pre-training (pre-training) is performed to update the embedded expression of the structured data and the parameters of the model. On the basis of the pre-training model, performing fine-tuning (fine-tuning) on the model by a downstream task for suspected disease judgment, wherein FC is a full-connection layer (full-connection layer), and output is a suspected disease list, for example: fourth candidate information L _deep = { disease 2:0.98, disease 4:0.80, disease 1:0.2, … … }.

S6, fusing the third candidate information and the fourth candidate information to obtain suspected disease information, and judging whether the diagnosis data is abnormal according to the suspected disease information.

Further, the step S6 shown in fig. 6 may include the following steps:

s61, extracting the disease type of which the suspected value meets a preset condition, and generating the suspected disease information.

S62, matching the target disease type in the diagnosis data with the disease type in the suspected disease information, if so, indicating that the diagnosis data is normal, and if not, indicating that the diagnosis data is abnormal.

Will third candidate information L _rule And fourth candidate information L _deep Weight fusion is carried out, and the formula is suspected disease information L=w _rule ×L _rule +w _deep ×L _deep Wherein w is _rule And w _deep For a preset coefficient, w _rule +w _deep =1. For example: l (L) _rule Has a value of 0.8, L _deep The value of (2) is 0.5, then the value of this disease in L is w _rule ×0.8+w _deep X 0.5. Taking the top K (positive integer) disease types with highest probability values to form suspected disease information of the target patient. If the target disease type (actual disease type) of the target patient is not in the suspected disease information, misdiagnosis of the diagnostic data of the target patient is indicated.

In this embodiment, the diagnostic data anomaly detection method may match the diagnostic data of the target patient with two rules of a preset medical rule and a medical mining rule, so as to obtain two candidate information, and fuse the two candidate information to obtain a third candidate information with multiple dimensions combined with the medical rule and the medical mining rule; the disease identification model is adopted to identify the diagnosis data to obtain fourth candidate information, so that the flexibility of identifying the diagnosis data is improved, and the identification speed is high; the suspected disease information of the target patient is determined by combining the fourth candidate information and the third candidate information, so that whether the diagnosis data is abnormal or not can be judged according to the suspected disease information, and the purpose of quickly and effectively confirming misdiagnosis is achieved.

Example two

Referring to fig. 7, a diagnostic data abnormality detection apparatus 1 of the present embodiment includes: an acquisition unit 11, a first matching unit 12, a second matching unit 13, a fusion unit 14, an identification unit 15, and a processing unit 16.

An acquisition unit 11 for acquiring diagnostic data of the target patient.

Further, the acquiring unit 11 is configured to receive medical data of the target patient sent by the user terminal, where the medical data includes: basic information of the target patient, the target disease type, and a plurality of medical entities.

The acquisition unit 11 is further adapted to extract the medical entity of the medical data, generating the diagnostic data.

The first matching unit 12 is configured to match the diagnostic data with a preset medical rule, and obtain first candidate information.

Further, the first matching unit 12 is configured to match a plurality of the medical entities in the diagnostic data with each of the medical rules in the preset medical rules, so as to obtain a matching degree of a disease type matched with the diagnostic data. The first matching unit 12 is further configured to extract matching degrees of all disease types matching with the diagnostic data, and generate the first candidate information.

And a second matching unit 13, configured to match the diagnosis data with a medical mining rule, and obtain second candidate information.

Further, the second matching unit 13 is configured to match a plurality of the medical entities in the diagnostic data with each of the mining rules in the medical mining rules, so as to obtain a matching degree of a disease type matched with the diagnostic data; the second matching unit 13 is further configured to extract matching degrees of all disease types matching with the diagnostic data, and generate the second candidate information.

In this embodiment, the medical mining rule is specifically obtained according to the historical sample data (see fig. 4):

And a fusion unit 14, configured to fuse the first candidate information and the second candidate information to generate third candidate information.

Further, the fusion unit 14 may calculate a matching average value for the matching degree of the same disease type corresponding to the first candidate information and the matching degree corresponding to the second candidate information according to the disease type in the first candidate information and the disease type in the second candidate information, and generate the third candidate information including the disease type matching average value.

And the identifying unit 15 is used for identifying the diagnosis data by adopting a disease identification model to acquire fourth candidate information.

And a processing unit 16, configured to fuse the third candidate information and the fourth candidate information to obtain suspected disease information, and determine whether the diagnostic data is abnormal according to the suspected disease information.

Further, the processing unit 16 extracts the disease type of which the suspected value meets the preset condition, and generates the suspected disease information; and matching the target disease type in the diagnosis data with the disease type in the suspected disease information, if so, indicating that the diagnosis data is normal, and if not, indicating that the diagnosis data is abnormal.

In the present embodiment, the diagnostic data abnormality detection apparatus 1 matches the diagnostic data of the target patient with the preset medical rule by the first matching unit 12, matches the diagnostic data of the target patient with the two rules of the medical mining rule by the second matching unit 13, so as to obtain two kinds of candidate information; fusing the two candidate information by adopting a fusion unit 14 to obtain multi-dimensional third candidate information combined with the medical rule and the medical mining rule; the disease identification model in the identification unit 15 is adopted to identify the diagnosis data to obtain fourth candidate information, so that the flexibility of identifying the diagnosis data is improved, and the identification speed is high; the processing unit 16 combines the fourth candidate information and the third candidate information to determine the suspected disease information of the target patient, so as to judge whether the diagnosis data is abnormal according to the suspected disease information, thereby achieving the purpose of quickly and effectively confirming misdiagnosis.

Example III

In order to achieve the above objective, the present invention further provides a computer device 2, where the computer device 2 includes a plurality of computer devices 2, and the components of the diagnostic data anomaly detection apparatus 1 of the second embodiment may be dispersed in different computer devices 2, and the computer device 2 may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack-mounted server, a blade server, a tower server, or a rack-mounted server (including a stand-alone server, or a server cluster formed by a plurality of servers), etc. The computer device 2 of the present embodiment includes at least, but is not limited to: the memory 21, the processor 23, the network interface 22, and the diagnostic data abnormality detection device 1 (refer to fig. 8) which can be communicatively connected to each other through a system bus. It should be noted that fig. 8 only shows a computer device 2 having components, but it should be understood that not all of the illustrated components are required to be implemented, and that more or fewer components may be implemented instead.

In this embodiment, the memory 21 includes at least one type of computer readable storage medium, including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 21 may be an internal storage unit of the computer device 2, such as a hard disk or a memory of the computer device 2. In other embodiments, the memory 21 may also be an external storage device of the computer device 2, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the computer device 2. Of course, the memory 21 may also comprise both an internal memory unit of the computer device 2 and an external memory device. In the present embodiment, the memory 21 is generally used for storing an operating system and various types of application software installed in the computer device 2, for example, program codes of the diagnostic data abnormality detection method of the first embodiment, and the like. Further, the memory 21 may be used to temporarily store various types of data that have been output or are to be output.

The processor 23 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 23 is typically used to control the overall operation of the computer device 2, e.g. to perform control and processing related to data interaction or communication with said computer device 2, etc. In the present embodiment, the processor 23 is configured to execute the program code or the processing data stored in the memory 21, for example, to execute the diagnostic data abnormality detection apparatus 1 and the like.

The network interface 22 may comprise a wireless network interface or a wired network interface, which network interface 22 is typically used to establish a communication connection between the computer device 2 and other computer devices 2. For example, the network interface 22 is used to connect the computer device 2 to an external terminal through a network, establish a data transmission channel and a communication connection between the computer device 2 and the external terminal, and the like. The network may be an Intranet (Intranet), the Internet (Internet), a global system for mobile communications (Global System of Mobile communication, GSM), wideband code division multiple access (Wideband Code Division Multiple Access, WCDMA), a 4G network, a 5G network, bluetooth (Bluetooth), wi-Fi, or other wireless or wired network.

It is noted that fig. 8 only shows a computer device 2 having components 21-23, but it is understood that not all of the illustrated components are required to be implemented, and that more or fewer components may alternatively be implemented.

In the present embodiment, the diagnostic data abnormality detection apparatus 1 stored in the memory 21 may also be divided into one or more program modules that are stored in the memory 21 and executed by one or more processors (the processor 23 in the present embodiment) to complete the present invention.

Example IV

To achieve the above object, the present invention also provides a computer-readable storage medium including a plurality of storage media such as a flash memory, a hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application store, etc., on which a computer program is stored, which when executed by the processor 23, performs the corresponding functions. The computer-readable storage medium of the present embodiment is for storing the diagnostic data abnormality detection apparatus 1, and implements the diagnostic data abnormality detection method of the first embodiment when executed by the processor 23.

The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment.

The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.

Claims

1. A diagnostic data anomaly detection method, comprising:

obtaining diagnostic data of a target patient;

2. The diagnostic data abnormality detection method according to claim 1, characterized in that obtaining diagnostic data of a target patient includes:

3. The diagnostic data anomaly detection method of claim 2, wherein the preset medical rules are rules preset according to medical knowledge, and include a plurality of medical rules, each medical rule including at least one medical entity, each medical rule corresponding to a disease type;

4. The diagnostic data anomaly detection method of claim 3, wherein matching the diagnostic data with a medical mining rule to obtain second candidate information further comprises:

generating the medical mining rule according to historical sample data:

5. The diagnostic data anomaly detection method of claim 4, wherein matching the diagnostic data with a medical mining rule to obtain second candidate information comprises:

6. The diagnostic data anomaly detection method of claim 5, wherein fusing the first candidate information and the second candidate information to generate third candidate information comprises:

7. The diagnostic data abnormality detection method according to claim 5, characterized in that said fourth candidate information includes a matching value of a disease type;

8. A diagnostic data abnormality detection apparatus, comprising:

an acquisition unit configured to acquire diagnostic data of a target patient;

and the processing unit is used for fusing the third candidate information and the fourth candidate information to acquire suspected disease information, and judging whether the diagnosis data is abnormal or not according to the suspected disease information.

9. A computer device, characterized in that it comprises a memory, a processor and a computer program stored on the memory and executable on the processor, which processor implements the steps of the method according to any one of claims 1 to 7 when the computer program is executed.

10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 7.