JP5832726B2 - Order system and program - Google Patents

Description

  The present invention relates to an order system and a program.

  Conventionally, various techniques for preventing an order mistake have been proposed. For example, Patent Document 1 describes a technique of storing a history of past medication errors and displaying it when a doctor gives a medication instruction. Patent Document 2 describes a technique for storing precautions for medication to a patient and displaying a warning when an inappropriate medication instruction is given.

  As for abnormal data (outlier value), as described in Non-Patent Document 1, various methods for detecting data that does not occur so much have been proposed.

JP 2004-118588 A Japanese Patent Laid-Open No. 8-315040

Kenji Yamanishi, “Anomaly Detection by Data Mining”, Kyoritsu Shuppan, May 23, 2009, p60-62

  By the way, in a radiology examination, for example, several parts to be examined are instructed from a plurality of parts of the human body, and examination (imaging) is performed on the designated part. At this time, the inspecting engineer, etc., inspects the part where the order is generated by looking at the inspection order information, but the combination of the part where the order occurs in the inspection order information is similar to the combination that appears frequently There is a possibility that the combination is not a frequent combination, but a combination that appears frequently. For example, when the combination of lumbar vertebra A → P and the lumbar vertebra side is a common pattern, the combination of lumbar vertebra A-P and thoracolumbar vertebrae is ordered in combination, but the combination of lumbar vertebra A → P and lumbar vertebra side is assumed. there is a possibility.

  However, in the above-described conventional techniques, any warning or prohibition matter is warned in any case, and no misunderstanding on the side of the instruction receiver is pointed out.

  An object of the present invention is to prevent mistakes due to assumptions when order information that is likely to be mistaken is generated.

In order to solve the above-mentioned problem, the invention described in claim 1
An order system that receives order information including a combination of a plurality of items generated by an order generation device via a network, and outputs order information including the received combination of the plurality of items ,
Storage means for storing order information generated in the past;
Order information obtained by extracting a combination of items having a high coincidence frequency according to a predetermined criterion based on past order information stored in the storage means and changing a part of the extracted combination of items. Extraction means for extracting, as order information that is likely to be mistaken, order information having a frequency of occurrence lower than a predetermined reference with respect to the order information composed of the extracted combinations;
Output means for determining whether or not the order information received from the order generation device corresponds to the order information that is likely to be mistaken, and outputs a warning if applicable;
Is provided.

The invention according to claim 2 is the invention according to claim 1,
The output means outputs the combination of items having a high frequency of simultaneous occurrence together with the order information that is more likely to be mistaken.

The invention according to claim 3 is the invention according to claim 1 or 2,
The extraction unit reads the order information generated in the past from the storage unit, generates a histogram indicating the frequency of combination of items in the order information generated in the past, and based on the generated histogram, Extract combinations of frequently occurring items.

The invention according to claim 4 is the invention according to claim 1 or 2,
The extraction means analyzes the order information generated in the past stored in the storage means and infers the occurrence frequency of the combination of items of each order information, so that the combination of items having a high simultaneous occurrence frequency is obtained. Extract.

The invention according to claim 5 is the invention according to claim 4,
The extraction means performs the data analysis by a statistical method.

The invention according to claim 6 is the invention according to claim 5,
The extraction means performs the data analysis using a learning algorithm.

The invention according to claim 7 is the invention according to claim 6,
The extraction means extracts the occurrence frequency by a mixed Bernoulli distribution model using a variational Bayesian method.

The invention according to claim 8 is the invention according to any one of claims 1 to 7,
The order information composed of the plurality of items is any one or a combination of examination order information, medication information, treatment order information.

The invention according to claim 9 is the invention according to any one of claims 1 to 8, wherein the order system has a console for receiving and displaying the order information transmitted from the order generating device, The console includes the storage unit, the extraction unit, and the output unit.
The program of the invention according to claim 10 is:
A computer used for an order system that receives order information including a combination of a plurality of items generated by an order generation device via a network and outputs the received order information including the combination of the plurality of items .
Order information obtained by extracting a combination of items having a high coincidence frequency according to a predetermined criterion based on past order information stored in the storage means, and changing a part of the extracted combination of items, Extraction means for extracting, as order information that is likely to be mistaken, order information that is less frequently generated than the predetermined reference for the order information that is composed of the extracted combinations;
An output means for determining whether or not the order information received from the order generation device corresponds to the order information that is likely to be mistaken, and to output a warning if applicable;
To function as.

  According to the present invention, it is possible to prevent mistakes due to assumptions when order information that is likely to be mistaken is generated.

It is a figure showing the whole order system composition in an embodiment of the invention. It is a block diagram which shows the functional structure of the order production | generation apparatus of FIG. It is a flowchart which shows the order extraction process easy to be performed performed by the control part of FIG. It is a figure which shows the data structural example of inspection order information. It is a flowchart which shows the order display process performed by the control part of FIG. It is a figure which shows an example of the order selection screen displayed on the display part of FIG. It is a figure which shows the other example of the order selection screen displayed on the display part of FIG. It is a flowchart which shows the order extraction process B which is easy to be mistaken performed by the control part of FIG. It is a figure which shows the other example of an order system.

[First Embodiment]
Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. However, the scope of the invention is not limited to the illustrated examples. In the present embodiment, an order system used for radiology in a medical facility will be described as an example. However, the present invention is not limited to this.

FIG. 1 shows an example of the overall configuration of an order system 100 in the present embodiment.
As shown in FIG. 1, an order system 100 includes an order generation device 1 and a console 2 that are connected to a HIS (Hospital Information System) via a communication network N such as a LAN (Local Area Network) or a WAN (Wide Area Network). )), RIS radiology information system (Radiology Information System) is used to be able to send and receive data to each other. An X-ray imaging apparatus 3 is connected to the console 2. The number of each device is not particularly limited.

Hereinafter, each device constituting the order system 100 will be described.
The order generation device 1 generates inspection order information in response to a registration operation by the operator, and transmits the generated inspection order information to the console 2.

  The console 2 receives and displays the examination order information transmitted from the order generation apparatus 1, and controls the X-ray imaging apparatus 3 based on the examination order information selected by the operator's operation. In addition, the medical image transmitted from the X-ray imaging apparatus 3 is subjected to image processing and displayed, and the examination order information and the medical image are stored in association with each other.

  The X-ray imaging apparatus 3 includes an X-ray irradiation unit, and performs imaging by irradiating X-rays from the X-ray irradiation unit according to instructions input from the console 2. A medical image obtained by imaging is transmitted to the console 2.

FIG. 2 shows a functional configuration example of the console 2.
As shown in FIG. 2, the console 2 includes a control unit 21, a RAM 22, a storage unit 23, an operation unit 24, a display unit 25, a communication unit 26, an I / F 27, and the like. It is connected.

The control unit 21 is configured by a CPU (Central Processing Unit) or the like, and reads various programs such as a system program and a processing program stored in the storage unit 23 and develops them in a RAM (Random Access Memory) 22. Various processes including an order extraction process and an order display process, which will be described later, are executed according to the program.

  The RAM 22 temporarily stores a work area for temporarily storing various programs, input or output data, parameters, and the like that can be executed by the control unit 21 read from the storage unit 23 in various processes controlled by the control unit 21. Form.

The storage unit 23 includes an HDD (Hard Disk Drive), a semiconductor nonvolatile memory, or the like. The storage unit 23 stores various programs as described above.
In addition, the storage unit 23 stores an order DB (Data Base) 231 for storing examination order information transmitted from the order generation device 1.
Further, the storage unit 23 stores an extraction result file 232 for storing an extraction result of an order extraction process that is likely to be mistaken, which will be described later.

  The operation unit 24 includes a keyboard having cursor keys, numeric input keys, various function keys, and the like, and a pointing device such as a mouse, and includes a key pressing signal pressed by the keyboard and an operation signal by the mouse. Is output to the control unit 21 as an input signal.

  The display unit 25 includes a monitor such as a CRT (Cathode Ray Tube) or an LCD (Liquid Crystal Display), for example, and displays various screens according to instructions of display signals input from the control unit 21. For example, the display unit 25 displays examination order information and medical images in accordance with instructions from the control unit 21.

  The communication unit 26 is configured by a LAN card or the like, and transmits / receives data to / from the order generation device 1 connected to the communication network N.

  The I / F 27 is an interface for performing data transmission / reception with the X-ray imaging apparatus 3 via a communication cable or the like.

Next, the operation of the console 2 will be described.
In the present embodiment, the console 2 periodically performs an error-prone order extraction process shown in FIG. 3, extracts erroneous test order information from the test order information stored in the order DB 231, and extracts the extraction results into an extraction result file Stored in H.232. Then, when displaying the inspection order information transmitted from the order generating device 1, the extraction result file 232 is referred to, and it is determined whether or not the inspection order information to be displayed is easily inaccurate. A warning is displayed when the inspection order information is easy.

Here, as shown in FIG. 4, the examination order information includes a plurality of N items (N is a positive integer), specifically, N portion items, and the portion where the order is generated is indicated by “ 1 ”, binary data indicating a portion where no order is generated by 0.
In the case of order information consisting of combinations of orders for multiple items, such as inspection order information, only some items fall under the combination that occurs at a relatively high frequency at the same time, and that order is generated at a high frequency. It is easy to make mistakes that make you think of a different combination. For example, when an order combining a lumbar spine A → P (front) and a lumbar spine side surface is generated at a relatively high frequency at the same time as an examination site, an operator such as a radiographer adds “ When “lumbar spine A → P” is found, it is easy to make a mistake in thinking that the combination is not a combination of “lumbar AP” and “side of lumbar spine”.

  Therefore, in the console 2, the inspection order information is “a combination of orders with a low occurrence frequency or an order that has never occurred in the past, and the same combination with a high occurrence frequency by changing a part of the combination. If it is a “combination”, the test order information is extracted as test order information that is likely to be mistaken.

Hereinafter, the flow of order extraction processing that is likely to be mistaken will be described with reference to FIG.
First, inspection order information stored in the order DB 231 is read, and clustering of past inspection order information is performed (step S1). Here, a method using clustering by the mixed Bernoulli distribution is given. Moreover, the case where the variational Bayes method (Variational Bayes Method) is used as the reasoning method is given as an example below. As a method for estimating the mixed distribution, for example, a method based on the maximum likelihood estimation method such as the EM algorithm, or MCMC that is a solution method based on sampling by the Bayes method may be used. By this clustering, a plurality of examination order information stored in the order DB 231 is classified into a subset (component) in which combinations having a high frequency of simultaneous occurrence are collected.

Here, the Bernoulli distribution will be described.
The mixed Bernoulli distribution is known as a distribution used for latent class analysis, and is widely used for applications such as binary data clustering and recommendation systems. Furthermore, since the prior distribution of Bernoulli distribution is one hyperparameter as will be described later, it is easy to experiment and analyze. The probability density function of Bernoulli distribution is given by the following equation (1).

Here, x = (x ₁ ,..., X _M ) ^T is data, and μ = (μ ₁ ,..., Μ _M ) ^T and M are the dimensions of parameters and data, respectively. At this time, the mixed Bernoulli distribution is defined by the following equation (2).

（a，b） は事前分布ｐ（π）、ｐ（θ）のパラメータでハイパーパラメータと呼ばれる。 Here, π represents the mixing ratio of B (x | x _k ), and K represents the number of components. Next, a hidden variable for data x is introduced. The hidden variable z is represented as a competitive vector z = (0,..., 1,..., 0) indicating from which distribution the data x originated. In this case, Dirichlet and beta distribution using the Z = a conjugated prior distribution as prior distribution of the distribution of the latent variable z and the data _{x (z 1, ..., z} N), X = (z 1, ..., z N ), Π and θ are given by the following equations (3) to (6), respectively.

(A, b) are parameters of prior distributions p (π) and p (θ) and are called hyperparameters.

  The hyper parameter a is a parameter of the Dirichlet distribution and determines the mixing ratio of the prior distribution. The hyper parameter b is a parameter of the beta distribution, and determines the magnitude of the variance value of the distribution mixed in the prior distribution.

Next, the variational Bayes method will be described.
In this section, Y represents all hidden variables including parameters, and X represents all observable variables. At this time, Equation (7) holds for an arbitrary probability distribution q (Y) and posterior distribution p (Y | X).

ここでＣ１，Ｃ２は正規化定数である。上式は互いの分布による平均値の計算を含んでいる。したがって、変分ベイズ法による学習は（７）および（８）の逐次的繰り返し演算により実行される。

Here, C1 and C2 are normalization constants. The above equation includes the calculation of the mean value from each other's distribution. Therefore, learning by the variational Bayes method is executed by the sequential iterative operations of (7) and (8).

Next, the variational Bayes method of the mixed Bernoulli distribution will be described.
By calculating the general update equations (14) and (15) of the variational Bayes method derived in the previous section under the setting in the description of the mixed Bernoulli distribution described above, the following variational Bayesian learning algorithm VB e of the mixed Bernoulli distribution is given. -step and VB m-step are obtained.
The following formulas (16) and (17) represent VB e-step. The following formulas (18) to (20) represent VB m-step.

以上、式（１６）〜（２２）によるアルゴリズムを実行することで事後分布が得られる。事後分布は、以下の式（２３）、（２４）によって得られる。

Here, it is set as the following formula | equation (21). However, ψ is called a digamma function, and Equation (22) holds.

As described above, the posterior distribution is obtained by executing the algorithm according to the equations (16) to (22). The posterior distribution is obtained by the following equations (23) and (24).

  Note that “learning” refers to arithmetic processing using VB e-step and VB m-step provided by an algorithm such as variational Bayes method. In this example, learning is performed by determining the prior distribution based on the hyperparameters (a, b) that are parameters of the prior distributions p (π) and p (θ).

  Regarding the setting of the hyper parameter, generally, when the hyper parameter a takes a large value, a posterior distribution including more components (for example, sample data) is formed, and the hyper parameter a has a small value. In this case, the number of components for configuring the posterior distribution is narrowed down. As an example of a case where the hyper parameter a takes a small value, the number of components can be narrowed down by making the hyper parameter a less than or equal to the value obtained by adding 1 to the dimension (M) divided by 2. Has been obtained.

  On the other hand, if the hyper parameter b is reduced, a small component can be found by constructing a group of more probabilistic certainty. If the hyper parameter b is increased, the smaller component is reversed. There is a tendency that a large tendency can be seen without detection.

Based on the algorithm shown in the above example, the console 2 performs clustering processing based on the contents of the order DB 231.
In the step S1, for example, the inspection parameters stored in the order DB 231 with a = b = 0.0001 for the hyper parameters a and b are learned, and the parts with high frequency of occurrence are classified into components.

  Next, a part having a predetermined threshold, for example, a probability of 80% or more is extracted from all components (step S2). Note that the process of this step may be performed only for components having a large mixing ratio of components.

  Next, it is determined whether or not a part having a probability of 80% or more in each component is equal to or less than a predetermined reference number (for example, 4), and if it is determined that the part is equal to or less than a predetermined reference number, The part having the probability of 80% or more is set as a frequent part (step S3). Since step S3 is performed to simplify the calculation, it can be omitted.

  Next, the number of examination order information in which orders of frequently occurring parts are simultaneously generated from the order DB 231 (all of the frequently appearing parts are “1”) is acquired and set to CNT_OK (step S4). Next, the number of pieces of examination order information obtained by changing a part (here, one) of combinations of frequent parts to another part is calculated based on the order DB 231 and set to CNT_NG (step S5). Note that the number of items to be changed to another part can be changed according to the reference number.

  Next, it is determined whether the occurrence frequency of CNT_NG for CNT_OK is lower than a predetermined reference. Specifically, it is determined whether 0 <CNT_NG / CNT_OK <0.05. Here, it is preferable to apply the condition “0 <” because it is possible to extract only combinations in which errors have actually occurred in the past. However, CNT_NG / CNT_OK <0.05 may be used. If it is determined that 0 <CNT_NG / CNT_OK <0.05, the examination order information obtained by changing one of the above frequent parts to another part is acquired as examination order information that is likely to be erroneous (step S6). Then, the acquired test order information that is easy to be mistaken and the combination of frequently appearing parts are stored in the extraction result file 232 (step S7), and the order extraction process that is easy to make mistakes ends.

  Next, when the examination order information is received from the order generation device 1 by the communication unit 26 in the console 2, the order display process executed by the cooperation of the control unit 21 and the program stored in the storage unit 23. explain. FIG. 5 shows the flow of the order display process.

  First, the received inspection order information is stored in the order DB 231 (step S11), and the inspection order information is displayed on the order selection screen 251 (see FIG. 6) of the display unit 25 (step S12).

  Next, the extraction result file 232 is referred to, and it is determined whether or not the received inspection order information corresponds to the inspection order information that is likely to be mistaken (step S13). If it is determined that the received examination order information does not correspond to the examination order information that is likely to be mistaken (step S13; NO), the order display process ends.

  On the other hand, if it is determined that the received examination order information corresponds to the examination order information that is likely to be mistaken (step S13; YES), the received examination order information is likely to be mistaken in the vicinity of the displayed examination order information. Is displayed (step S14), and the process ends.

  FIG. 6 is a diagram showing an example of the warning message 251a displayed on the order selection screen 251 in step S14. The order selection screen 251 is a screen for displaying examination order information to be photographed and for selection by the photographing engineer. The imaging engineer confirms a part to be imaged on the order selection screen 251 and performs imaging. Here, if the combination of the lumbar front (A → P) and the lumbar side is a common order, this time the lumbar front (A → P) and the thoracolumbar side are combined in a different order. P) and lumbar vertebra side may be assumed and this combination photography may be performed. Therefore, as shown in FIG. 6, by displaying a warning message 251a such as “Lumbar vertebra front-thoracolumbar vertebral pair. Be careful (incidence rate 0.1%).” can do.

  Note that, as shown in FIG. 7, together with the warning message 251a, examination order information 251b consisting of a common combination pattern similar to the warning message 251a (examination order information consisting of a combination of frequent parts) may be displayed together. In this way, it is possible to easily recognize what inspection order information displayed by a user such as an imaging technician is likely to be mistaken for. In addition, as shown in FIG. 7, operation buttons for instructing to change to the inspection order information are arranged together with the inspection order information 251b of the common pattern so that the user can change the information after confirming the correct inspection order information. It may be.

[Second Embodiment]
Next, a second embodiment of the present invention will be described.
Since the order system 100 in the second embodiment is the same as that described in the first embodiment, the description is incorporated herein. In the second embodiment, since the order extraction process that is easy to make mistakes is different, the order extraction process that is easy to make mistake in the second embodiment (referred to as order extraction process B that is easy to make mistakes) will be described below.

FIG. 8 is a flowchart showing the flow of order extraction processing B that is likely to be mistaken in the control unit 21.
First, all examination order information stored in the order DB 231 is read out, and a histogram showing the frequency of order combinations occurring simultaneously in the examination order information (parts where “1” is generated) is created. (Step S31). Here, when there are N items (that is, the number of parts) of the inspection order information, there are 2 ^ N orders that may occur in the inspection order information.

  Next, a combination of the top K orders with the highest occurrence frequency is extracted (step S32), and in each of the extracted K combinations, the number of parts included in the combination is equal to or less than a predetermined reference number (for example, It is determined whether or not there are 4 sites or less. If it is determined that the number is equal to or less than a predetermined reference number, the combination is a combination of frequent parts (step S33). Since step S3 is performed to simplify the calculation, it can be omitted.

  Next, the number of pieces of examination order information in which orders for frequently appearing parts are simultaneously generated is acquired and set to CNT_OK (step S34). Next, the number of pieces of examination order information obtained by changing a part (here, one) of combinations of the frequent parts to another part is acquired and set in CNT_NG (step S35). Note that the number to be changed to another part can be varied according to the reference number described above.

  Next, it is determined whether the occurrence frequency of CNT_NG for CNT_OK is lower than a predetermined reference. Specifically, it is determined whether 0 <CNT_NG / CNT_OK <0.05. Here, the condition “0 <” is preferable because it is possible to extract only combinations in which errors have actually occurred in the past, but CNT_NG / CNT_OK <0.05 may be used. If it is determined that 0 <CNT_NG / CNT_OK <0.05, the examination order information including a combination obtained by changing one of the combinations of the above frequent parts to another part is acquired as examination order information that is likely to be erroneous (step S36). ). The acquired test order information that is easy to be mistaken and the combination of the above frequent occurrences are stored in the extraction result file 232 (step S37), and the order extraction process that is easy to make mistakes ends.

  Since the order display process executed when the inspection order information is transmitted from the order generation device 1 is the same as that described in the first embodiment, the description is used.

In the first embodiment, frequent combinations are estimated by a mixed Bernoulli distribution model using a variational Bayesian method. Therefore, it is possible to predict inspection order information that is likely to occur even if it has not yet occurred. Further, since not all past data is required as in the case of using a histogram, the database storage capacity and processing load can be reduced.
On the other hand, in the second embodiment, based on the examination order information stored in the order DB 231, a histogram is generated that indicates the frequency of combinations of parts that are simultaneously ordered in the examination order information. Based on the above, frequent combinations are extracted. Therefore, since the test order information that is likely to be mistaken is extracted based on the test order information that has actually occurred in the past, the test order information that is likely to be mistaken is extracted according to the tendency of the test order information in the medical facility, and a warning can be given. .

  As described above, according to the console 2, a combination of items (that is, parts) having a high frequency of simultaneous occurrence is extracted based on past examination order information stored in the order DB 231 and a part of the extracted combinations The inspection order information whose occurrence frequency is lower than a predetermined standard with respect to the extracted combination of inspection order information is extracted as erroneous inspection order information and stored in the extraction result file 232 To do. Then, when the inspection order information is received, it is determined whether or not the inspection order information corresponds to the inspection order information that is likely to be mistaken.

  Therefore, when inspection order information with a low occurrence frequency is generated by changing a part of a combination with a high occurrence frequency, an operator such as a radiographer is an inspection order information composed of a combination of parts with a high occurrence frequency at the same time. It is possible to prevent mistakes that occur due to the assumption.

  In addition, by displaying a combination of parts having a high frequency of occurrence together with examination order information that is likely to be mistaken, an operator such as a radiographer can confirm and pay attention to how easy it is to make an error.

  In addition, by generating a histogram that shows the combination of the parts where the order has occurred in the examination order information that occurred in the past, and extracting the combination with the high frequency of simultaneous occurrence based on the generated histogram, the tendency of the examination order information in the medical facility It is possible to extract inspection order information that is easy to make mistakes and to give a warning.

  In addition, by analyzing data of inspection order information that has occurred in the past and inferring the occurrence frequency of the combination of items, it is possible to predict inspection order information that is likely to occur even if it has not yet occurred. Further, since not all past data is required as in the case of using a histogram, the database storage capacity and processing load can be reduced.

In addition, the description content in the said embodiment is a suitable example of this invention, and is not limited to this.
For example, in the above-described embodiment, a case has been described as an example in which inspection order information that is likely to be mistaken in a radiology imaging system is warned. However, the present invention is not limited to this and occurs in the electronic medical chart system shown in FIG. It can also be applied to treatment orders, medication information, examination order information, or a combination thereof. Here, the treatment order has a plurality of test items in blood test, urine test, etc., and information indicating the test item in which the order has occurred is “1” and the test item in which the order has not been generated is “0”. is there. The medication information is information that includes a plurality of drug items, the drug item for which the order has been generated is indicated by “1”, and the drug item for which the order has not been generated is indicated by “0”. For example, in the case of asthma, medication such as petrolatum is often performed together with zaditen syrup. However, it is not necessarily limited to this combination, and in some cases, different skin drugs, gastrointestinal drugs, and the like may be issued depending on the patient's request. Even in such a case, it is possible to prevent mistakes due to the assumption of the person in charge of the examination or pharmacist by executing the above-described order extraction processing and order display processing that are likely to be mistaken for treatment orders and medication information, and giving a warning. Become.

  The technical idea of the present invention can also be applied to various kinds of order information generated outside a medical facility. Here, the order information in a restaurant is information having a plurality of menu items, where the menu item with the order is “1” and the menu item with no order is “0”. For example, gyoza and beer are often ordered together. However, the present invention is not necessarily limited to this combination. For example, gyoza and juice may be ordered. Even in such a case, for example, if the order extraction process or the order display process described above, which is likely to be mistaken, is executed for a menu order on a PC such as a kitchen, and a warning is issued, it is possible to prevent mistakes due to the store clerk's assumptions. It becomes.

  The extracted order information that is easy to be mistaken is not only used for a warning to prevent the user from assuming that the order information is a combination of frequently occurring orders, but also used for confirmation at the time of order entry. You can also. For example, in an order generation device that generates order information, if the input order information is easily confusing order information, it is similar to the order information composed of a combination having a high coincidence frequency. A high combination may be displayed to prompt confirmation of the entered order information.

  The parameters, threshold values, reference numbers, and reference values (CNT_NG / CNT_OK) used in the first and second embodiments are determined experimentally and empirically, but are only examples and are not limited thereto. Is not to be done. For example, the configuration may be such that the user can change the setting of these parameters, threshold values, reference numbers, and reference values. This makes it possible to perform extraction according to the status of each facility that uses the order information.

  For example, in the above description, an example in which an HDD or a semiconductor nonvolatile memory is used as a computer-readable medium of the program according to the present invention is disclosed, but the present invention is not limited to this example. As another computer-readable medium, a portable recording medium such as a CD-ROM can be applied. Further, a carrier wave is also applied as a medium for providing program data according to the present invention via a communication line.

  In addition, the detailed configuration and detailed operation of each device constituting the order system 100 can be changed as appropriate without departing from the spirit of the invention.

100 Order system 1 Order generation device 2 Console 3 X-ray imaging device 21 Control unit 22 RAM
23 storage unit 231 order DB
232 Extraction result file 24 Operation unit 25 Display unit 26 Communication unit 27 I / F
28 Bus N Communication network

Claims (10)

An order system that receives order information including a combination of a plurality of items generated by an order generation device via a network, and outputs order information including the received combination of the plurality of items ,
Storage means for storing order information generated in the past;
Order information obtained by extracting a combination of items having a high coincidence frequency according to a predetermined criterion based on past order information stored in the storage means and changing a part of the extracted combination of items. Extraction means for extracting, as order information that is likely to be mistaken, order information having a frequency of occurrence lower than a predetermined reference with respect to the order information composed of the extracted combinations;
Output means for determining whether or not the order information received from the order generation device corresponds to the order information that is likely to be mistaken, and outputs a warning if applicable;
An order system comprising   The order system according to claim 1, wherein the output unit outputs the combination of items having a high frequency of simultaneous occurrence together with the order information that is more likely to be mistaken.   The extraction unit reads the order information generated in the past from the storage unit, generates a histogram indicating the frequency of combination of items in the order information generated in the past, and based on the generated histogram, The order system according to claim 1 or 2, wherein a combination of items having a high occurrence frequency is extracted.   The extraction means analyzes the order information generated in the past stored in the storage means and infers the occurrence frequency of the combination of items of each order information, so that the combination of items having a high simultaneous occurrence frequency is obtained. The order system according to claim 1 or 2, wherein the order system is extracted.   The order system according to claim 4, wherein the extraction unit performs the data analysis by a statistical method.   The order system according to claim 5, wherein the extraction unit performs the data analysis using a learning algorithm.   The order system according to claim 6, wherein the extraction unit extracts the occurrence frequency by a mixed Bernoulli distribution model using a variational Bayes method.   The order system according to any one of claims 1 to 7, wherein the order information including the plurality of items is any one or a combination of examination order information, medication information, and treatment order information.   The said order system has a console which receives and displays the order information transmitted from the order production | generation apparatus, The said console is provided with the said memory | storage means, the said extraction means, and the said output means. Order system described in the section. A computer used for an order system that receives order information including a combination of a plurality of items generated by an order generation device via a network and outputs the received order information including the combination of the plurality of items .
Order information obtained by extracting a combination of items having a high coincidence frequency according to a predetermined criterion based on past order information stored in the storage means, and changing a part of the extracted combination of items, Extraction means for extracting, as order information that is likely to be mistaken, order information that is less frequently generated than the predetermined reference for the order information that is composed of the extracted combinations;
An output means for determining whether or not the order information received from the order generation device corresponds to the order information that is likely to be mistaken, and to output a warning if applicable;
Program to function as.

Images