JP5582872B2 - Information processing apparatus, information processing system, information processing method, and program - Google Patents

Description

The present invention relates to an information processing apparatus, an information processing system, an information processing method, and a program, and more particularly to a result display technique in an information search system.

  In recent years, a large amount of information has been handled in the medical field, and there is an increasing situation in which such information is managed on a database and searched and used as necessary. In order to effectively use the database, it is important how to appropriately present the target information to the operator (user) who performs the search.

  One of the purposes of searching the database as described above is to find a case to be browsed. However, it is difficult to present only corresponding case information in a single search of the database. Therefore, in reality, the search condition is corrected and the search is performed to narrow down the results, and information on the target case is searched. Therefore, in the list display of search results, it is necessary to clearly indicate individual differences within the resulting case group and to enable the operator to select target case information from the list displayed. It is done.

  In the medical field, there are people with various roles such as doctors, engineers, and accountants. Therefore, even if the information in the same database is accessed, the situation differs between when the doctor accesses for diagnosis and when the engineer accesses during examination. In order to cope with such a situation, for example, Patent Document 1 below proposes a database system or the like that has a function of allowing a user to select and process display items when a list of search results is displayed. For example, Patent Document 2 below proposes an information display system having a function of storing attributes selected by a user for each user and selecting different display items depending on a person who performs a search. Further, for example, in Patent Document 3 below, display items corresponding to several situations are set in advance, such as when a doctor uses or when a non-doctor uses, and a corresponding display format is selected from the display items. Information processing technology has been proposed.

JP-A-2005-242742 JP 2006-39673 A JP 2006-350998 A

However, in the methods described in Patent Literature 1 and Patent Literature 2, only the display items selected by the user are used, and the display items when the search results are displayed in a list cannot be changed according to the search results. In the technique described in Patent Document 3, display items corresponding to the situation are set in advance, and a corresponding display format is only selected from the display items. Therefore, in these methods, the individual differences within the case group of the search results are clearly indicated, and the operator can select the target case information from those displayed in a list. Display items cannot be changed.
The present invention has been made in view of such circumstances, and an object of the present invention is to display a list of search results using appropriate items according to the search results of a database.

An information processing apparatus according to the present invention is an information processing apparatus that is capable of accessing a database in which a plurality of medical information records are registered, a setting unit that sets display item candidates, and a plurality of medical information a condition acquiring means you get the conditions for identifying at least some of the records, a plurality of records obtained as the search result by the search in accordance with the condition acquired by the condition acquiring means is executed, If the determination means determines whether or not the information corresponding to the display item candidate set by the setting means can be identified, and if the determination means determines that the information cannot be identified, the search result is obtained. Selecting means for selecting display items for enabling identification of a plurality of records, and for each of the plurality of records obtained as the search results, And having a display control means for displaying on the display unit information corresponding to the display item selected by the-option means.

  According to the present invention, it is possible to display search results appropriately, display a plurality of pieces of medical information obtained as search results so that they can be identified to the maximum, It becomes possible to acquire efficiently.

It is a figure showing an example of composition of an information processing system concerning this embodiment. It is a flowchart which shows the process sequence of the information processing apparatus which concerns on this embodiment. It is a flowchart which shows the process in step S270 shown in FIG. It is a figure which shows an example of the search result which concerns on this embodiment, and its display example. It is a figure which shows the example of a display of the search result which concerns on this embodiment. It is a figure which shows the example of a display of the search result which concerns on this embodiment.

Embodiments of the present invention will be described with reference to the drawings.
In the following, the three-dimensional tomographic image of the retina acquired by the optical coherence tomography (OCT) and the result of performing image processing on the tomographic image are stored together with the patient information of the patient having the eye to be examined and the image of the fundus camera. The display of database search results will be described as an example. In addition, as a situation in which the search to the database is performed, a case where an engineer who takes a tomographic image performs a search and a case where a doctor who performs diagnosis performs a search will be described as an example.

(First embodiment)
A first embodiment of the present invention will be described.
In the present embodiment, when a list of search results executed in accordance with an input by an operator (user) is displayed, an effective search result can be displayed by selecting and displaying valid items according to the search result. It is what I do. More specifically, the search result variation for each item value varies depending on how the search condition is set. Therefore, by selecting from items with large value variations in the search results, individual differences among the case groups included in the search results are effectively specified. In particular, when the space for displaying the results is limited, it is effective to select items by taking into account the magnitude of the variation of the values in the search results and the medical importance depending on the situation. List display can be performed.

FIG. 1 is a block diagram illustrating a configuration example of an information processing system according to the first embodiment. The information processing system 10 according to the present embodiment includes an information processing apparatus 100 and a database 200 that can be accessed by the information processing apparatus 100.
The information processing apparatus 100 includes an access information acquisition unit 110, a search condition acquisition unit 120, a control unit 130, a storage unit 140, a query creation unit 150, an output unit 160, a search result acquisition unit 170, an item selection unit 180, and a display unit 190. Have

  The access information acquisition unit 110 and the search condition acquisition unit 120 acquire an input by an operator (user). For example, the access information acquisition unit 110 acquires operator ID information and the like input by the operator. For example, the search condition acquisition unit 120 acquires a search condition input by the operator. The operator ID information and search conditions acquired by the access information acquisition unit 110 and the search condition acquisition unit 120 are stored in the storage unit 140 through the control unit 130.

  The control unit 130 comprehensively controls each functional unit in the information processing apparatus 100. For example, the control unit 130 acquires items (display items, display candidate items) according to the operator from the storage unit 140 based on the operation input acquired by the access information acquisition unit 110. The storage unit 140 stores operator information and search conditions acquired based on operation inputs, and stores display items and display candidate items that are set according to the operator. Here, the display item is an item (item group) that is considered essential for displaying the search result list, and the display candidate item is an item that is not essential for displaying the search result but is considered effective for display ( Item group). Note that display items need not be set, but display candidate items need to be set.

  The query creation unit 150 acquires search conditions, display items and display candidate items corresponding to the operator through the control unit 130, and creates a query (query, search processing request) related thereto. The output unit 160 performs output to the database 200, and the search result acquisition unit 170 acquires the result of the search performed on the database 200. That is, the query (search processing request) created by the query creation unit 150 is output to the database 200 by the output unit 160 through the control unit 130. Information as a search result of the database 200 corresponding to the query is acquired by the search result acquisition unit 170.

  The item selection unit 180 selects an item suitable for display of the search result according to the search result acquired by the search result acquisition unit 170. The display unit 190 causes the display unit such as a monitor to output a record list of search results. Here, a record refers to each result obtained as a search result. The database 200 is a database in which medical information is registered in this embodiment. In the database 200, a three-dimensional tomographic image of the retina acquired by OCT, a result of image processing performed on the tomographic image, patient information of a patient having an eye to be examined, and an image of a fundus camera are registered and stored.

  Next, a processing procedure of the information processing apparatus 100 in the present embodiment will be described with reference to the flowchart shown in FIG. FIG. 2 is a flowchart illustrating an example of a processing procedure of the information processing apparatus 100. As described above, in the database according to the present embodiment, examination information, patient information, electronic medical record information, and the like are registered and stored together with an OCT image obtained by capturing a tomographic image of the retina. The examination information includes information such as whether the eye to be examined is right and left, the imaging region, the imaging date and time, and the presence or absence of use of a contrast agent. The patient information includes information such as the age and sex of the corresponding patient and the doctor in charge. The electronic medical record information includes information such as disease diagnosis information and medication history. There is a difference in the selection method of items when displaying a list of search results between a case where an engineer who captures an OCT tomographic image searches for such a database and a case where a diagnosis doctor performs a search. By providing it, more accurate search results can be presented.

  In step S210, the access information acquisition unit 110 acquires operator information (such as the operator's name and whether it is a doctor or an engineer) from the login ID of the operator who uses the system. The acquired operator information is transmitted to the storage unit 140 through the control unit 130. As an example, the following description will be made assuming that the operator is a doctor.

  In step S220, the search condition acquisition unit 120 acquires search conditions that the operator inputs from an input device or the like. The acquired search condition is transmitted to the storage unit 140 through the control unit 130. Here, the search condition is input by, for example, opening a search condition input dialog and inputting the patient name, examination date, diagnosis name, and the like there. Here, it is not necessary to input all the items, and items that are not input are also important elements for the search purpose.

In step S230, the control unit 130 acquires the display item, the display candidate item, and the importance for each item from the storage unit 140 based on the operator information acquired in step S210. Here, it is assumed that each item group of display items and display candidate items is selected and stored in advance depending on whether the operator is a doctor or an engineer. For example, if the operator is physician, nothing is set as the display item groups N _D, if the operator is the technician, the display item groups N _O as {patient ID, age, gender , Doctor in charge, imaging resolution} is set.

As a display candidate item group, items that are not suitable for display and items already selected as display items are excluded from all items in the database. Items that are not suitable for display include, for example, automatically assigned unique IDs, device serial numbers and manufacturers that are known to be always the same in the database at a medical institution where a single device is installed, and discretization Some items have continuous attribute values that are difficult to understand. Here, when the operator is a doctor, {patient ID, patient name, age, sex, drug used, examination date, left and right eyes, imaging site, number of imaging} is set as the display candidate item group E _D. And If the operator is an engineer, it is assumed that {imaging region, number of images} is set as the display candidate item group E _O.

  In the above description, the operator is a doctor and an engineer. However, it is also possible to set items for each operator. The display items and the display candidate items are selected in advance as defaults, but may be changed by the operator as necessary.

  Further, the importance level for each item designates an order in which priority is given to display for items in the display candidate item group. As the importance level, different values may be set depending on whether the operator is a doctor or an engineer, or the same value may be set. If not specified, all items are determined to have the same importance. The importance of the display items is also used for the display order.

  In step S240, the query creation unit 150 creates a search query (search processing request) using the search conditions acquired in step S220 and the display items and display candidate items acquired in step S230. The search query is generated using the SQL syntax so that the record of the search result returns the values of all display items and display candidate items, and is transmitted to the database 200 having the SQL server function through the output unit 160. A result (search result) for the transmitted search query is acquired again by the information processing apparatus 100 through the search result acquisition unit 170 and is stored in the storage unit 140 through the control unit 130.

  In step S <b> 250, control unit 130 determines whether or not each record can be identified from only the display items with respect to the search result stored in storage unit 140. Here, one record represents one OCT tomographic image. In addition, it is possible to identify each record obtained as a search result when there are not a plurality of records in which the values of items to be displayed are all equal. That is, when each record of the search result can be identified, if the value of the item to be displayed is determined, one corresponding record is confirmed, or there is no corresponding record. If no display item is set, it is determined that each record cannot be identified, and the process proceeds to the next step.

An example of specific processing for evaluating the identifiability of search results is shown below.
It is assumed that the search result is n records, and each record is k (= 0 to (n−1)). First, the control unit 130 compares the values of items to be displayed with the records of k = 1 to (n−1) against the record of k = 0, and there is a record in which all the values of the items are the same. Investigate whether or not to do so. As a result, if there is a record having the same item value as that of the record with k = 0, it is determined that identification could not be performed, and the process is terminated. On the other hand, when the same record as the record with k = 0 does not exist, the control unit 130 displays the records with k = 2 to (n−1) for the record with k = 1 next. Compare the values of the items to be checked, and check whether there is a record in which the values of the items are all the same. If there is a record having the same item value as that of the record with k = 1, it is determined that identification has not been possible, and the process ends. On the other hand, if the same record as the record with k = 1 does not exist, the control unit 130 determines whether there is a record with the same value of all items to be displayed next with respect to the record with k = 2. Check for no. Thereafter, this process is repeated. Specifically, the control unit 130 sequentially increments the value of l by 1 if there are no items with the same value to be displayed, and k = (l + 1) to ( Comparison is made with each of the records of (n-1). It is assumed that all records can be identified when the item values of both are not the same by comparing the record of k = (n−2) and the record of k = (n−1).

  Note that the method for examining the identifiability of the search result is not limited to the above-described method, and there are a plurality of methods other than the above-described method. For example, paying attention to one item, all records are classified into a plurality of groups by the item value, and only a group having a plurality of records in one group is selected. A group having a plurality of records in the group is further classified into subgroups by the value of the second item, and only a subgroup having a plurality of records is selected. In the same way, the above-described operation is repeated, and there is a method in which each record of the search result is not identifiable when there is a group having a plurality of records even after classification by all required items is completed. .

  In step S260, control unit 130 branches the process according to the identifiability evaluation result in step S250. When all the records of the search result are identified only by the display item (when each record of the search result can be identified), only the display item is selected, and the process proceeds to step S290. On the other hand, when the record of the search result cannot be identified only by the display item, the process proceeds to step S270, and processing for adding an item and displaying it is performed.

  In step S270, the item selection unit 180 selects an item necessary for display from the display candidate items acquired in step S230. In order to display the list of search results most effectively within the limited display space, the display candidate items are evaluated according to the search results, and the number of items that can be displayed in order from the item with the highest effectiveness is selected. .

  Here, two viewpoints are considered as indicators of effectiveness. The first point of view is setting in advance by an operator or manufacturer, which corresponds to selecting / saving display items and giving importance to display candidate items. As a result, it is possible to ensure display items that are essential in the medical field, and to reflect differences due to differences in the situation of the search and the role of the operator. This is dealt with by acquiring the corresponding item in step S230.

  The second point of view is how each item can clearly show individual differences in the case group that is the search result, and the operator can contribute to selecting target case information from the list. . In other words, it is how to display the information contained in the display part in an effective order, and the purpose can be achieved by calculating the information amount of the display items and displaying the information amount in order of the amount of information. it can.

  Hereinafter, regarding the second viewpoint, a method for calculating the amount of information that each item has for the search result will be described in detail with reference to the flowchart shown in FIG. FIG. 3 is a flowchart illustrating an example of a processing procedure in step S270 illustrated in FIG.

  In step S271, the item selection unit 180 divides search results by display items. The search results are divided by classifying the search result records into subsets having the same value of each item according to the values of all items set as display items. If no display item is set, the process proceeds to the next step without dividing the search result.

In step S272, the item selecting section 180, for all items included in the display candidate items E _D, to evaluate its effectiveness. Here, as the display candidate item E _D shall {patient ID, name, age, gender, using the drug, examination date, the right and left eyes, the imaging site, the number of imaging} is set. FIG. 4 shows an example of a result of searching for these items by setting only the patient's last name as a search condition (patient name = “search”). FIG. 4A shows 16 cases of “Search Taro” having a last name of “Search” and 7 cases of “Search Hanako”. Also, for each of the cases, the values of all items that have been set as a display candidate items E _D are shown, respectively.

  FIG. 4B shows an example in which the result shown in FIG. 4A is displayed as five fixed items {patient ID, patient name, age, sex, left and right eyes}. In the display shown in FIG. 4B, the result of each record is almost the same in the five items {patient ID, patient name, age, sex, left and right eyes}. Therefore, even if a list of search results is presented as shown in FIG. 4B, it is difficult for the operator to select case information to be obtained from the list. However, if the search is performed by specifying an examination date, a list of a plurality of patients examined on the corresponding examination date is obtained, so the fixed five items described above are effective item sets for list display. It is expected that

Therefore, we evaluated as follows validity of each item included in the example display candidate items E _D.
Assume that the set of all records of the search result is S, and the number of elements of all records is n. The amount of information necessary to individually identify all the records of the search result is expressed by the following (Formula 1).

Set S, a subset S _1, S ₂ by the value of an item a, · · ·, and is divided into S _V. At this time, the amount of information necessary to classify the objects belonging to all the subsets S _i is expressed as in the following (Formula 2).

Note that s _i is the number of records belonging to the subset S _i . As a result, the gain G of the amount of information obtained by dividing the item a is obtained by the following (Equation 3). The item with the largest gain G is the item with the highest effectiveness.

For example, in the case shown in FIG. 4A, the gain G is calculated as follows.
G (patient ID) = G (patient name) = G (age) = G (gender) = 0.614
G (used drug) = 1.354
G (inspection date) = 2.186
G (left and right eyes) = 0.387
G (imaging region) = 0.646
G (number of captured images) = 0.85

In step S273, the item selection unit 180 selects one item having the largest gain based on the processing result in step S272 and adds it to the list of items having high effectiveness (hereinafter referred to as the effectiveness list). Then, computing the sum G _S of the acquired gain to date. In the example of the processing result in step S272 described above, since “inspection date” has the largest gain, the item “inspection date” is added to the validity list. Since nothing has been added to the list so far, the “examination date” is at the top of the validity list, and the sum of gains G _S = G (examination date) = 2.186.

  Note that the gains G by “patient ID”, “patient name”, “age”, and “sex” are all equal. As is clear from FIG. 4, the values of these four items are always present as a set in the search result. Such item groups have the same amount of information gain regardless of which of them, and therefore, there is no difference in effectiveness from the processing in step S272. Therefore, the difference in effectiveness is evaluated based on the difference in importance acquired in step S230. Specifically, when there are a plurality of items having the maximum gain G, the item having the highest importance is selected. If the importance is equal, any item among them may be selected. For example, if the gain G of “patient ID”, “patient name”, “age”, and “gender” is the largest and the importance is patient name> age = gender> patient ID, Select “Patient Name” from

In step S274, it is determined whether the record of the search result has already been identified by the item selected so far. This determination is performed by determining whether or not the sum of gains G _S calculated in step S273 is equal to the information amount I (n) obtained by (Expression 1). When only “inspection date” is added to the validity list, it is determined that the sum of gains G _S = 2.186 and does not match I (23) = 3.135, so that identification is not possible. .

  In step S275, item selection unit 180 determines whether there is an item that has not been added to the validity list among the display candidate items. Here, since only “examination date” is added to the validity list, and {patient ID, patient name, age, sex, drug used, left and right eyes, imaging region, number of imaging} remain, the process returns to step S272. . However, here, if the calculation result of the gain in step S273 becomes 0 for all the remaining items, it is determined that there are no remaining display candidate items. This is because further division cannot be performed using the remaining items.

In step S272, the item selection unit 180 considers dividing the case information that cannot be identified only by the “examination date” by adding another item. Assume that the subset S _{i that} has already been divided by the item a is divided into the subset S _ij by the new item b. At this time, the amount of information necessary to classify the objects belonging to all the subsets S _ij is expressed as (Equation 4) below.

Note that s _ij is the number of records belonging to the subset S _ij . Thereby, the gain G of the information amount by further dividing by the item b is obtained by the following (Formula 5).

The calculation result in the case shown in FIG. 4A is as follows.
G (examination date, patient ID) = G (examination date, patient name) = G (examination date, age) = G (examination date, gender) = 0.287
G (examination date, drug used) = 0.287
G (examination date, left and right eyes) = 0.218
G (examination date, imaging region) = 0.565
G (inspection date, number of images) = 0.203

In step S273, the item selection unit 180 adds “imaging part” to the validity list based on the above-described processing result. The gain sum G _S is calculated as G _S = 2.186 + 0.565 = 2.751.

The above-described processing is repeated until the record of the search result can be identified or until there are no remaining display candidate items. In this example, in the next processing loop, G (examination date, imaging region, left and right eyes) = G (examination date, imaging region, drug used) = 0.203 is obtained. Here, it is assumed that the importance levels acquired in step S230 are the same for the “left and right eyes” and the “medicine used”. If the importance levels are equal, either one may be selected, so here, the item “left and right eyes” is selected and added to the validity list. At this time, the sum G _S of gains is G _S = 2.751 + 0.203 = 2.954.

In the next processing loop, the gain G becomes equal for all the remaining items (item c = {patient ID, patient name, age, sex, drug used}), and G (examination date, imaging region, left and right eyes). C) = 0.181. Here, if the importance acquired in step S230 is “patient name”> “age” = “sex”> “patient ID” and “medicine used” = “age”, the importance is highest. “Patient name” is added to the list of effectiveness. At this time, the sum of gains G _S becomes G _S = 2.954 + 0.181 = 3.135. Since the sum of gains G _S coincides with the information amount I (23) = 3.135 obtained by (Equation 1), it is shown that the information of all 23 cases as search results can be identified, In step S274, it is determined that the record of the search result has been identified.

  In step S276, item selection unit 180 selects an item based on the validity list created by the above processing. The contents of the effectiveness list obtained in the above-described example are “examination date, imaging region, left and right eyes, patient name”. The number of selection items is affected by the size of the display space. For example, if four items can be displayed, the item selection unit 180 selects all four items in the validity list. For example, when only three items can be displayed due to the display space, the item selection unit 180 selects three items from the upper side of the effectiveness list, in this example, “examination date, imaging region, left and right eyes”. To do.

In the above description, a method for selecting an item necessary for display when a display item is not set has been described. However, in the medical field, there are some items that are always required to be displayed regardless of the large amount of information. For example, in the above-mentioned example, when displaying with three items, items (patient ID and patient name) for identifying a patient are not included, but it is very important to specify a patient uniquely in a medical field. It is. Therefore, it is necessary to previously set items to be displayed as display items regardless of search results. As already described in the description of the processing in step S230, the display item can be set according to the situation of the medical site according to the access information. For example, as the display items N _D {patient ID, name, examination date} is set as a display candidate items {age, gender, using the drug, the right and left eyes, the imaging site, the number of imaging} and is set. In this case, since all the items included in the display items are to be displayed, in step S271, the information amount gain G (G (patient ID, patient name, examination date)) for all the items included in the display items is calculated. I do. Subsequent steps S272 and subsequent steps are effective for the item group included in the display candidate item by selecting the item having the large gain G by repeating the same processing using the above-described (Expression 4) and (Expression 5). Create a sex list.

Returning to FIG. 2, in step S <b> 270, the control unit 130 stores the display items and the display candidate items selected as described above in the storage unit 140.
In step S280, display unit 190 causes the display unit such as a monitor to display the display item, the value of the selected display candidate item, and the record of the search result. FIG. 5 shows an example of a list display of search results obtained by this embodiment. FIG. 5A shows a display example in the case where four items are selected only from the calculation of the information amount gain without setting the display items, and the items are sorted by the value of “inspection date”. In FIG. 5A, it can be seen that all search result records are uniquely identified. On the other hand, FIG. 5B shows a display example when {patient ID, patient name, examination date} is designated as a display item. The results are sorted by the values of “patient ID” (“patient name”) and “examination date”. In FIG. 5B, the record of the search result is uniquely identified, and at the same time, the patient ID and the patient name which are important items for the doctor are shown, and it can be seen that the display is more appropriate.

  According to the present embodiment, when displaying a list of database search results requested by the operator, it is possible to select and display appropriate items according to the search results, and to identify search result records. It can be displayed as possible. In this way, effective search results can be displayed by combining medical importance according to the situation and an item selection method that reflects differences in search result variations.

(Second Embodiment)
Next, a second embodiment of the present invention will be described.
In the first embodiment, an example is shown in which different display items and display candidate items and their importance levels are set depending on whether the operator is a doctor or an engineer. However, even if the operator is the same doctor, the items considered to be appropriate may differ depending on the time and place of the search. In the second embodiment, a case will be described in which different displays are performed depending on the time and place of accessing the database.
The configuration of the information processing system according to the second embodiment is the same as that of the first embodiment described above. Hereinafter, only the differences from the first embodiment described above will be described in the processing of the information processing apparatus in the second embodiment.

In the second embodiment, in the access information acquisition process (step S210 shown in FIG. 2), the access information acquisition unit 110 accesses the database together with the operator information (login ID and the like). Get time and location information. In the first embodiment, different display item groups N _D and N _O are set and stored depending on whether the operator is a doctor or an engineer. In the second embodiment, it is assumed that different display item groups can be set depending on access time and access location.

For example, when search results are displayed as a list, consider not only medical personnel such as doctors and engineers but also patients who may see them, and cases where they do not. As an example, it is assumed that the consultation time is from 9:00 am to 6:00 pm and the conference is held from 8:00 pm. In this case, for example, as a display item group N _D of the doctor, as from 9 am until 7:00 pm and only "patient ID" without including the "patient name", 7 pm include a "patient's name" Set. By setting in this way, it is possible to avoid presenting the names of other patients who have undergone the same examination to a general patient when displaying a list of search results.

  Even when the same doctor searches at the same time, it may be convenient to display differently between the terminal in the outpatient office and the terminal in the laboratory where the examination is performed. Only the “patient ID” is presented in the outpatient office, and “patient name” is also displayed in the laboratory, so that the name of another patient obtained as a search result for a patient can be displayed. Can be avoided. In addition, when an interpretation doctor makes a diagnosis at an interpretation center or the like, additional information (such as age, sex, drugs used, surgery history, etc.) may be required in addition to the patient name. In such a case, even if the operator is the same doctor, it is possible to set so that “patient name” is not displayed when a search result is displayed as a list when searching at the interpretation center. It is also possible to set so that items to be displayed are distinguished from the diagnostic doctor and the interpretation doctor by the login ID.

(Third embodiment)
Next, a third embodiment of the present invention will be described.
In the first embodiment, the method of selecting an item for the purpose of identifying a record after a set of records as a search result is given has been described. However, the knowledge given when the search condition is input by the operator has not been used to select items to be displayed when displaying the search results as a list. In the third embodiment, a case will be described in which the method for selecting an item necessary for display is changed according to the input content of a search condition. In this way, by considering the input contents of the search condition, it becomes possible to display the search result more in line with the operator's intention.

  The configuration of the information processing system according to the third embodiment is the same as that of the first embodiment described above. In the following, an example will be described in which the contents of the search conditions related to age (step S220 shown in FIG. 2) are applied to selection of items necessary for display (step S270 shown in FIG. 2).

  In the selection process of items necessary for display (step S270 shown in FIG. 2), the item selection unit 180 selects items necessary for display from the items set as display candidate items. At this time, records are classified according to item values. However, when the method shown in the first embodiment is used, an attribute having a large division number of item values tends to be prioritized. That is, “sex” has only two types of values, male or female, but “age” has a value of 80 or more if it is from about 0 to 80 years old. As a matter of course, in many cases, “age” obtains a larger information gain than “sex”. Similarly, items that handle date and time such as “examination date” and items that handle continuous values such as “height” and “weight” generally give a large information gain. In such a case, it is necessary to pay attention to discretization of item values. Discretization is an indispensable process when values that can be taken as item values are continuous values, but discretization is performed as necessary for items that can be handled as they are, such as age and date.

  For example, with respect to patient age, those suffering from ophthalmic diseases increase with age. Regarding glaucoma, patients in their 20s are rare, but it is known that the number of patients increases from their 40s and the prevalence exceeds 10% in their 70s. Reflecting this bias in the number of patients, discretization of the age is not every 1 year, but every 10 years under 40 years, every 5 years under 40 to 60 years, and under 60 to 80 years Then, it is divided by changing the division width every two years. In this way, by appropriately changing the division width, the age that was divided into 80 for every one year is reduced to 18 divisions.

  The distribution of patients by such age varies depending on the disease. Therefore, when a disease is specified by the search condition acquired in the search condition acquisition process (step S220), the age according to the corresponding disease is discretized by appropriately changing the division width. A display that matches the search purpose can be performed. Conversely, when no disease is specified by the search condition, discretization is performed with a fixed division width that divides all ages every 5 years, and display that does not consider the bias of the age distribution is performed. However, if the database itself targets a specific disease group and the age distribution is biased, it is also effective to use a discretization that equalizes the entire age distribution for a search in which no disease is specified. is there. Specifically, for example, if it is desired to discretize the age value to 20, a method of using the age range when the ages at the time of examination of all cases are arranged in descending order and divided into 20 may be considered.

  Similarly, with regard to the examination date, the examination period has a characteristic depending on the disease. For example, in glaucoma, since the disease itself lasts for a long time, tests are often performed every three months or every six months. On the other hand, when bleeding occurs due to retinal vein branch occlusion or the like, treatments and examinations for observing the effects are frequently performed. Therefore, when the disease is determined by the search condition acquired in the search condition acquisition process (step S220), it is also effective to change the discretization of the examination date for each disease.

  Furthermore, at the stage where the search condition is acquired in the search condition acquisition process, the search result acquisition and identification process (step S250) and the selection process of items necessary for display (step S270) may be simplified. For example, when a patient ID is input as a search condition, all search result records have the same patient ID. Therefore, in this case, by removing the item “patient ID” from the processing target, it is possible to omit the calculation based on “patient ID” when selecting an item necessary for display. In other words, if there is an item whose value is uniquely determined as the search condition acquired in the search condition acquisition process, the item must be deleted from the evaluation items to be processed in the selection process of the item required for display. Thus, the processing can be simplified.

(Fourth embodiment)
Next, a fourth embodiment of the present invention will be described.
In displaying the search result, a function on a GUI (Graphical User Interface) may be used to cause the operator or the viewer to pay attention to an important part. For example, in the search result shown in FIG. 4, as described above, “examination date” is the item having the largest gain for identifying the record of the search result. In such a case, as shown in an example in FIG. 6A, attention can be paid by highlighting a column of “inspection date” with a color. Further, as shown in FIG. 6B, it is possible to prevent misunderstanding by coloring and highlighting with different colors in the imaging region and the left and right eyes that are not sorted. Such highlighting has a greater effect when a large number of items can be selected as items to be displayed.

(Other embodiments of the present invention)
The present invention can also be realized by executing the following processing. That is, software (program) that realizes the functions of the above-described embodiments is supplied to a system or apparatus via a network or various storage media, and a computer (or CPU, MPU, or the like) of the system or apparatus reads the program. It is a process to be executed.

  The above-described embodiments are merely examples of implementation in carrying out the present invention, and the technical scope of the present invention should not be construed as being limited thereto. That is, the present invention can be implemented in various forms without departing from the technical idea or the main features thereof.

  DESCRIPTION OF SYMBOLS 100 ... Information processing apparatus 110 ... Access information acquisition part 120 ... Search condition acquisition part 130 ... Control part 140 ... Storage part 150 ... Query creation part 180 ... Item selection part 190 ... Display part 200 ... Database

Claims (18)

An information processing apparatus capable of accessing a database in which a plurality of medical information records are registered,
A setting means for setting display item candidates;
A condition acquiring means you get the conditions for identifying at least some of the records of the plurality of medical information,
Whether a plurality of records obtained as search results by performing a search according to the condition acquired by the condition acquisition means can be identified by information corresponding to display item candidates set by the setting means Determining means for determining whether or not;
When it is determined by the determination means that it is not identifiable, a selection means for selecting a display item for enabling identification of a plurality of records obtained as the search results;
The search for each of the results as a plurality of records obtained, the information processing apparatus characterized by having a display control means for displaying information corresponding to a display item selected by the selection unit on the display unit. The search result based on differences between a plurality of records obtained, the information processing apparatus according to claim 1, characterized in that it comprises a processing means for applying a priority to items to be displayed. At least one of the plurality of medical information records stored in the database includes information corresponding to each of the display item candidates ,
When it has the same information about the candidates of the at least two records have different information about the candidates of the first display item, and other display items among the plurality of records obtained as the search result, the 1 the information processing apparatus according to claim 1, characterized in that it comprises a processing means for imparting a higher priority than a candidate of the other displayed items in the candidate display items. Wherein the display control unit, the search for each of the results as a plurality of records obtained, according to claim 2 or 3, the information corresponding to the display item of the candidate to which the higher priority is granted, characterized in that to display side by side in this order The information processing apparatus described. Wherein the display control unit, the search of the resulting that a plurality of records, claim 1, characterized in that to display the information of the selected item in order gain is large amount of information from the candidates of the display item The information processing apparatus according to any one of to 4 . 2. When item information is uniquely specified by a condition acquired by the condition acquisition unit , the item is excluded from processing targets related to selection of an item for displaying information. The information processing apparatus according to any one of 5 . The information processing apparatus according to claim 5 , wherein the display control unit highlights a column of an item having a large gain in the information amount. The determination unit compares information corresponding to display item candidates set by the setting unit for each of the plurality of records obtained as the search result, and can be identified when there is no completely matching information. The information processing apparatus according to claim 1, wherein the information processing apparatus is determined. The selection unit selects a display item based on an information amount gain of information corresponding to the selected display item, and further selects a display item selected based on the information amount gain based on importance information. The information processing apparatus according to claim 1, wherein the information processing apparatus is an information processing apparatus. 10. The determination unit according to claim 1, wherein the determination unit determines whether or not a plurality of records obtained as the search result can be identified by information corresponding to a display item selected by the selection unit. The information processing apparatus according to any one of claims. The selection means selects a display item for enabling identification of a plurality of records obtained as the search result in addition to a predetermined display item. The information processing apparatus described. Information of an operator of the information processing apparatus, a time at which a search is executed according to a condition acquired by the condition acquisition unit, and at least a terminal at which a search is executed according to a condition acquired by the condition acquisition unit It further has information acquisition means for acquiring any information,
The information processing apparatus according to claim 1, wherein the setting unit sets the display item based on information acquired by the information acquisition unit. Information of an operator of the information processing apparatus, a time at which a search is executed according to a condition acquired by the condition acquisition unit, and at least a terminal at which a search is executed according to a condition acquired by the condition acquisition unit It further has information acquisition means for acquiring any information,
The information processing apparatus according to claim 1, wherein the selection unit selects the display item based on information acquired by the information acquisition unit. When the display control means includes information specifying a specific value for the first item in the condition acquired by the condition acquisition means, the display control means depends on the distribution of the value of the second item for the specific value. The information processing apparatus according to claim 1, wherein a plurality of records obtained as the search results are displayed. The display control means, when a part of the information corresponding to the display item selected by the selection means for at least two records among the plurality of records obtained as the search result matches, and the part does not match, The information corresponding to the selected display item of the two records is displayed on the display unit so that at least one of the partial information that does not match can be identified. The information processing apparatus according to any one of the above. An information processing system capable of accessing a database in which a plurality of medical information records are registered,
A setting means for setting display item candidates;
Condition acquisition means for acquiring a condition for identifying at least a part of the records of the plurality of medical information;
Whether a plurality of records obtained as search results by performing a search according to the condition acquired by the condition acquisition means can be identified by information corresponding to display item candidates set by the setting means Determining means for determining whether or not;
When it is determined by the determination means that it is not identifiable, a selection means for selecting a display item for enabling identification of a plurality of records obtained as the search results;
An information processing system comprising: display control means for displaying information corresponding to a display item selected by the selection means on a display unit for each of the plurality of records obtained as the search result. An information processing method for accessing a database in which a plurality of medical information records are registered,
A setting step in which the computer sets display item candidates;
A condition acquisition step in which a computer acquires a condition for identifying at least a part of the plurality of records of medical information ;
A plurality of records obtained as a search result by performing a search according to the condition acquired in the condition acquisition step is information corresponding to display item candidates set in the setting step. A determination step of determining whether or not identification is possible;
When it is determined that the computer is not identifiable in the determination step, a selection step for selecting a display item for enabling identification of a plurality of records obtained as the search result;
An information processing method comprising: a display control step for causing a display unit to display information corresponding to a display item selected in the selection step for each of the plurality of records obtained as the search result. . A program for causing a computer to execute each step of the information processing method according to claim 17.

Images