KR102531051B1 - System and method for providing, analyzaing medical information in filed of clinical research and methdo for the same - Google Patents

Abstract

A medical information providing system comprising: an electronic medical record storage unit for storing electronic medical records; Searching for an electronic medical record that meets the condition from the electronic medical record stored in the electronic medical record storage unit as a condition of interest for at least one of demographic information, disease information, treatment information, and other information is input to the user terminal a first cohort search unit; a second cohort search unit that excludes electronic medical records that meet the exclusion conditions from the results of the electronic medical records searched by the first cohort search unit as exclusion conditions to be excluded are input to the user terminal; a third cohort search unit for retrieving a final electronic medical record corresponding to the final condition from the electronic medical record result searched by the second cohort search unit when a final condition is input to the user terminal; and a display unit displaying each search result of the electronic medical record that meets the conditions in a multi-layered manner on the display of the user terminal.

Description

System and method for providing, analyzing medical information in filed of clinical research and methdo for the same}

The present invention relates to a system and method for providing and analyzing medical information, and more specifically, to a system for providing and analyzing medical information in a multi-layered manner based on electronic medical records stored and recorded in medical institutions. and its method.

In recent years, the use of an Electronic Medical Record (EMR) system is continuously increasing in order to increase the creation, management, and utilization of medical records in medical institutions.

More specifically, an electronic medical record (EMR) system refers to a computerized system for medical records among hospital care support tasks. The Electronic Medical Record (EMR) system has the effect of speedy work processing, manpower and cost reduction, enabling rapid delivery and utilization of records, and reducing waiting time for patients.

This electronic medical record (EMR) system is a system that integrates and shares electronic medical records into a network, enabling long-term management of patient medical information as well as prescription, clinical research, and treatment decision-making for patients.

However, it is necessary to provide only the desired information to information consumers in a multi-layered manner from electronic medical records that have a very important clinical significance. However, most of the current patents require a complicated and inconvenient process to input boilerplate when preparing medical records. It is focused on providing only methods to quickly and effectively handle medical record preparation tasks.

Korean Patent No. 10-2013-0046009

Therefore, the problem to be solved by the present invention is to provide a system and method for processing data from electronic medical records containing very important data in clinical research or clinical practice, visualizing the results in multiple layers, and statistically analyzing them. .

In order to solve the above problems, the present invention is a medical information providing system, an electronic medical record storage unit for storing electronic medical records; Searching for an electronic medical record that meets the condition from the electronic medical record stored in the electronic medical record storage unit as a condition of interest for at least one of demographic information, disease information, treatment information, and other information is input to the user terminal a first cohort search unit; a second cohort search unit that excludes electronic medical records that meet the exclusion conditions from the results of the electronic medical records searched by the first cohort search unit as exclusion conditions to be excluded are input to the user terminal; a third cohort search unit for retrieving a final electronic medical record corresponding to the final condition from the electronic medical record result searched by the second cohort search unit when a final condition is input to the user terminal; and a display unit displaying each search result of the electronic medical record meeting the conditions in a multi-layered manner on the display of the user terminal.

In one embodiment of the present invention, the display unit simultaneously displays the condition and the electronic medical record search result corresponding thereto according to the order of conditions input to the user terminal.

In one embodiment of the present invention, at least two or more exclusion conditions may be input, and all search results of each exclusion condition are excluded from the electronic medical record results searched by the first cohort search unit.

In one embodiment of the present invention, the display unit displays the conditions and search results corresponding to the conditions in the form of a box, and the relationship between search results is indicated by a line between the boxes.

In one embodiment of the present invention, the final clinical study design conditions include at least one of demographic factors, specific diseases, treatment of interest, control treatment, and treatment period.

In one embodiment of the present invention, the first cohort search unit, when the diagnosis name is the first condition, recognizes only the electronic medical records containing the therapeutic drug corresponding to the diagnosis name as true, and returns the electronic medical records satisfying the first condition. Classify medical records.

In order to solve the above problems, the present invention searches for electronic medical records corresponding to conditions input from a user terminal and displays the result on a display of the user terminal. , and the relationship is displayed in multiple layers. Therefore, the present invention adopts a method of sequentially inputting conditions to be excluded from the initial search result and narrowing the final selection range by excluding them, thereby allowing various information such as disease, patient and prescription information to be recorded in a complicated manner. Due to the nature of the electronic medical record, more effective and precise condition extraction is possible by continuously applying conditions excluded from the “cohort of interest” corresponding to the research subject area. As a result. Data items (e.g., demographic factors, diseases, drugs, surgery/procedure, laboratory test, etc.) can be selected and analyzed.

1 is a box diagram of a medical information providing system according to an embodiment of the present invention.
2 to 8 are schematic diagrams illustrating step-by-step operations by the medical information providing system according to an embodiment of the present invention.
9 to 10 are analysis results obtained by applying the information and analysis method and system according to the present invention.

Hereinafter, the preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

Before describing the present invention in detail, the terms or words used in this specification should not be construed unconditionally in a conventional or dictionary sense, and in order for the inventor of the present invention to explain his/her invention in the best way Concepts of various terms can be appropriately defined and used.

Furthermore, it should be noted that these terms or words should be interpreted as meanings and concepts consistent with the technical idea of the present invention.

That is, the terms used in this specification are only used to describe preferred embodiments of the present invention, and are not intended to specifically limit the contents of the present invention.

It should be noted that these terms are terms defined in consideration of various possibilities of the present invention.

Also, in this specification, a singular expression may include a plurality of expressions unless the context clearly indicates otherwise.

In addition, it should be noted that similarly, even if expressed in a plurality, it may include a singular meaning.

Throughout this specification, when a component is described as "including" another component, it does not exclude any other component, but further includes any other component, unless otherwise stated. It can mean you can do it.

Furthermore, when a component is described as "existing inside or connected to and installed" of another component, this component may be directly connected to or installed in contact with the other component.

In addition, it may be installed at a certain distance, and in the case of being installed at a certain distance, a third component or means for fixing or connecting the corresponding component to another component may exist. .

Meanwhile, it should be noted that the description of the third component or means may be omitted.

On the other hand, when it is described that a certain element is "directly connected" to another element, or is "directly connected", it should be understood that no third element or means exists.

Similarly, other expressions describing the relationship between components, such as "between" and "directly between", or "adjacent to" and "directly adjacent to" have the same meaning. should be interpreted as

In addition, in the present specification, terms such as "one side", "the other side", "one side", "the other side", "first", and "second" refer to one component with respect to another component. It is used to make it clearly distinguishable from the elements.

However, it should be noted that the meaning of a corresponding component is not limitedly used by such a term.

In addition, in this specification, terms related to positions such as “upper”, “lower”, “left”, “right”, etc., if used, are to be understood as indicating relative positions of corresponding components in the drawing.

In addition, unless an absolute location is specified for these locations, these location-related terms should not be understood as referring to an absolute location.

Moreover, in the specification of the present invention, terms such as "... unit", "... unit", "module", and "device", if used, mean a unit capable of processing one or more functions or operations.

It should be noted that this may be implemented in hardware or software, or a combination of hardware and software.

In the drawings accompanying this specification, the size, position, coupling relationship, etc. of each component constituting the present invention is partially exaggerated, reduced, or omitted in order to sufficiently clearly convey the spirit of the present invention or for convenience of explanation. may be described, and therefore the proportions or scale may not be exact.

In addition, in the following description of the present invention, a detailed description of a configuration that is determined to unnecessarily obscure the subject matter of the present invention, for example, a known technology including the prior art, may be omitted.

In order to solve the above-described problem, the present invention searches for electronic medical records corresponding to conditions input from a user terminal, and displays the result on a display of the user terminal. In addition, according to input conditions, the relationship between the search results is displayed in multiple layers. In this specification, the search results may be the number of electronic medical records that meet the conditions.

In the present invention, as one of the most important methods in data research, a method of reducing the number of patients while hierarchically visiting patients is applied to electronic medical record information.

To this end, an operational definition is established to treat conceptual definition as an objective procedure so that it can be measured empirically. For example, in order to determine whether a diagnosis in a medical record is true, a structure in which prescription drugs for treating a disease are searched together with the diagnosis within a certain period corresponds to this structure.

Then, in the process of reducing the corresponding number, as the corresponding search criterion is input and applied to the query node (box) where the condition is entered, the corresponding number of patients obtained according to the operational definition is sequentially reduced for each search step. Then, the results are hierarchically displayed in the form of boxes. In particular, the present invention proceeds with an additional selection process through set processing (union, difference, intersection) between search results, and this type of set processing is a link between boxes ( line), the user can recognize it intuitively.

After that, finally, by setting search criteria for each node (box), data is extracted in detail (eg, time series function required for clinical research, etc.), and it is displayed on the display.

The present invention also configures a node (box) for freely querying search results according to the research design and can list them in a specific order, for example, a specific drug treatment group and a non-treatment group, or specific drug A and specific drug B. .

That is, it is important to perform exploratory data analysis (EDA) on the data of interest in order to find conditions suitable for research, and the present invention can find the following clinical design conditions through such EDA. For example, the distribution of the difference between the first diagnosis date and the first prescription day, the total duration of drug prescription during the study period, the interest evaluation index collection cycle (eg, examination values per visit, etc.), the time of occurrence for clinical outcomes (eg, Examples of such clinical design conditions include long-term treatment effects, or the occurrence of complications following disease progression.

In addition, the present invention noted that it is important to create a dataset by freely adding items with desired variables for high-level visualization and statistical analysis required for clinical research. Therefore, as the user selects the analysis target variable (e.g., therapeutic outcome, complication occurrence, etc.) from patients selected according to the design conditions, whether the corresponding result value of the variable is in a specific evaluation period and in the case of a continuous variable After identifying and removing outliers, the information on remaining patients is defined as the final “cohort for analysis”.

Therefore, in order to realize the effect of the present invention, the search condition input and the result of the system according to the present invention are implemented in the form of a query node (box) on the program screen, and the correlation between the condition and the result is visualized. You can easily understand the flow of research, and you can easily adjust search conditions or the arrangement of nodes (boxes). In particular, the user interface according to the present invention increases user convenience by intuitively displaying condition input and result display when condition input work is repeatedly performed.

In this specification, the condition for setting the initial search range is referred to as a condition of interest, and the result is referred to as a “cohort of interest”, and at least one of drug information, disease information, period information, demographic information, and treatment information may be a condition of interest. can

In particular, the present invention adopts a method of narrowing the final selection range by sequentially receiving conditions to be excluded from the search results of the initial search range and excluding them. Due to the nature of the electronic medical record, which includes various information such as disease names and patient information in a complex way, more effective condition search is possible by continuously applying conditions excluded from the initial scope of interest, and exclusion conditions from the “cohort of interest” are applied. The electronic medical record outcome of interest is referred to as the “selection cohort”. In one embodiment of the present invention, a plurality of exclusion conditions may be entered, and the search results of the exclusion conditions are successively applied from the “interest cohort” so that the final “selection cohort” applies all of the at least two exclusion conditions. It can be a search result.

In the present invention, data items (e.g., electronic medical record information to be finally obtained for clinical research analysis) from the “selection cohort”, which is the result of narrowing the selection range suitable for the research purpose by excluding the above exclusion conditions according to the clinical study design demographic factors, diseases, medications, surgeries/procedures, laboratory tests, etc.) results can be obtained.

1 is a box diagram of a medical information providing system according to an embodiment of the present invention.

Referring to FIG. 1, the system includes an electronic medical record storage unit 100 for storing electronic medical records; As a condition of interest for at least one of patient demographic information, disease information, drug information, and period information is input to the user terminal, an electronic medical record that meets the condition is generated from the electronic medical record stored in the electronic medical record storage unit. A first cohort search unit 200 for searching; a second cohort search unit 300 that excludes electronic medical records meeting the exclusion conditions from the electronic medical record results searched by the first cohort search unit as exclusion conditions to be excluded are input to the user terminal; As the final selection condition is input to the user terminal, a third cohort search unit for searching the final electronic medical record corresponding to the final clinical design condition from the electronic medical record result searched by the second cohort search unit 300 ( 400); and a display unit 500 displaying the number of electronic medical records satisfying each condition in a multi-layered manner on a display of the user terminal.

2 to 8 are schematic diagrams illustrating step-by-step operations by the medical information providing system according to an embodiment of the present invention. The following examples are only for explaining the technical idea of the present invention, and the scope of the present invention is not limited by the following examples.

Referring to FIG. 2, first, the search conditions for the first cohort are input through the user terminal. In FIG. 2, a patient who has taken Atorvastatin is entered as the first condition.

In one embodiment of the present invention, when a disease name is input as the first condition, the electronic medical record with the diagnosis name is recognized as true only when the diagnosis name and prescription conditions for the treatment drug for treating the diagnosed disease are simultaneously input. Then, it is counted and classified as a result that satisfies the search condition. This is in consideration of the fact that, due to the complex nature of electronic medical records, when searching only by disease name, there is a problem that meaningless or practically meaningless patient records are recognized as true.

In FIG. 2, as a disease called hyperlipidemia and the date of Atorvastatin drug for treating it are entered, an electronic medical record that simultaneously satisfies the corresponding conditions is classified as a cohort of interest, and then displayed on a display window.

Referring to FIGS. 3 and 4 , in order to actually classify a target group of men aged 50 or older, an exclusion condition for a group to be excluded from the interest cohort classified in FIG. 2 is input as a second condition.

In FIG. 3, the condition for classifying female patients and in FIG. 4, the condition for classifying patients born after 1972 are input as the second condition. In particular, as shown in FIGS. 3 and 4 , the second condition is displayed as a lower layer box of the search result box of the first condition, enabling the user to more intuitively recognize the search result.

In particular, in consideration of the complex information structure of the electronic medical record, the present invention searches and classifies the cohort of interest as the first condition, sets the condition to exclude it from among them as the second condition, and then excludes the second cohort. (selection cohort) is classified. In particular, the search results of excluded groups are displayed as the lower strata of the cohort of interest.

Referring to FIGS. 5 to 7, the third cohort necessary for the final clinical study is classified from the second cohort classified from the first cohort according to the exclusion conditions. 5 to 7, the patient group based on the first Atorvastatin prescription date after January 1, 2015 is the final cohort. reference), and enter the corresponding prescription date (see FIG. 7). Therefore, the final clinical cohort selected after all three conditions are entered is displayed in a multi-layered structure as shown in FIG. 8, and each search result is intuitively displayed according to the shape of the line between each box.

That is, referring to FIG. 8 , the number of cohorts of interest searched according to the first condition is 72,929, and the search results of female, which is an exclusion condition, and people born before 1972 are displayed as a lower layer of the cohort of interest.

Among them, as the third condition is input again, the search results corresponding to the third condition from the second cohort classified according to the second condition are displayed in the lower box of the search result box of the second condition.

9 to 10 are analysis results obtained by applying the information and analysis method and system according to the present invention. Here, it is known that the risk of developing diabetes increases as a side effect of statin drugs used as a treatment for dyslipidemia. It was confirmed that there were differences in trends.

Referring to FIG. 9 , first, patients with dyslipidemia diagnosis records are queried from the electronic medical records recorded in the electronic medical record storage unit. At the same time, the patient's first diagnosis date of dyslipidemia is extracted, and among patients with dyslipidemia, patients with statin-type drugs (ATC Code: C10AA and lower drugs) prescription records are excluded, and the non-prescription patient group is obtained (Cohort 1). ). In addition, the results are obtained by querying patients whose prescription start date for statins was after the first diagnosis of dyslipidemia, and retrieval of the statin prescription patient group.

The date of the first statin prescription for the prescription patient group and the date of the first diagnosis of dyslipidemia in the case of the non-prescription patient group are taken as the reference date. Patients who have records, prescription records of hypoglycemic drugs, or glycated hemoglobin test levels of 6.5 or higher are classified as diabetes diagnosis and suspected patients, and are excluded from the study. This is because diabetes (diagnosed or suspected) occurring during the treatment period cannot be regarded as an effect of the drug. In addition, it was judged that patients who were prescribed glucocorticoids during the same period could interfere with the study results, so they were excluded by entering exclusion conditions for glucocorticoid prescriptions.

After that, patients in the remaining prescription group are selected based on drug exposure during the treatment period of 1 year. Since the specific reference value can be determined even after confirming the drug exposure distribution of patients, it is indicated as n% in FIG. 9 .

Non-prescription patients who are not prescription patients are selected based on the number of days they visited the hospital with the same diagnosis for one year after the initial diagnosis (second cohort). Likewise, you can determine specific figures by looking at the distribution of the data.

After confirming how long it takes for patients to receive a diabetes diagnosis after receiving a diagnosis or prescription for the first time, a specific follow-up period is set, and patients who have visited the hospital at least once during the follow-up period are selected. to complete patient selection (third cohort).

10 is an actual result obtained according to the analysis flow of FIG. 9 .

Referring to FIG. 10, after confirming the data distribution, specific criteria were set, the criteria for drug exposure, follow-up period, and number of visits were confirmed, and the number of patients satisfying each selection criterion (selection, exclusion conditions) was entered.

The degree of drug exposure used in one embodiment of the present invention is very important in analyzing the clinical results of the drug, and the clinical therapeutic effect is affected by the duration and administration of the drug exposed during the evaluation period.

Therefore, in order to study the causal relationship between drugs and therapeutic effects, the concept of drug exposure is needed. The persistence period is defined as the period from the start date to the end of drug administration. There is an unprescribed section. Therefore, this non-administration interval is called a permissible gap, and although there are differences for each treatment area during data research, there are cases in which drug prescription is considered to have continued by allowing 30 to 90 days. Therefore, the present invention defines such drug exposure as the ratio of consecutive prescription days within a specific period, and uses this as an important condition in data selection.

11 is a study timeline based on prescription group patients using the analysis results according to the present invention.

Referring to Figure 11, after receiving a diagnosis of dyslipidemia, the prescription of statin-based drugs began within 30 days, and then received statin treatment in the environment at least 80% exposure for one year. In this case, it is necessary to confirm that there is no diagnosis of diabetes and no suspicion of diabetes during the entire previous period, including the treatment period. Triglyceride, high-density cholesterol (HDL-Cholesterol), and low-density cholesterol (LDL_Cholesterol) test values are extracted. The test value for 90 days before treatment is used as the reference data, and the change data obtained by subtracting the corresponding value from the test value after the treatment period is also used.

If diabetes occurred within the follow-up period (3 years after the treatment period), it was classified as a NODM (New Onset Diabetes Mellitus) patient, and the date of the first occurrence of diabetes was the endpoint of the study. However, if diabetes did not occur, the last visit to the hospital during the follow-up period would be the end point of the study.

Claims (6)

As a medical information providing system,
an electronic medical record storage unit for storing electronic medical records;
When a condition of interest for at least one of demographic information, disease information, drug information, and period information is input to the user terminal, an electronic medical record that meets the condition of interest is searched from the electronic medical records stored in the electronic medical record storage unit. a first cohort search unit;
a second cohort search unit that excludes electronic medical records that meet the exclusion conditions from the results of the electronic medical record searched by the first cohort search unit when an exclusion condition to be excluded is input to the user terminal;
a third cohort search unit that searches for a final electronic medical record that meets the final condition from the electronic medical record results searched by the second cohort search unit when a final condition is input to the user terminal; and
A display unit displaying each of the search results of the electronic medical record that meets the condition of interest and the exclusion condition in a multi-layered manner on the display of the user terminal;
The first cohort search unit, when the disease information is the condition of interest, recognizes only the electronic medical record containing a therapeutic drug corresponding to the disease information as true, and classifies it as an electronic medical record that meets the condition of interest;
The third cohort search unit searches the final electronic medical record based on the exposure of the therapeutic drug, where the exposure of the therapeutic drug is the ratio of consecutive prescription days within a specific period,
The exclusion condition of the second cohort search unit is input for the search results of the first cohort search unit,
At least two or more of the exclusion conditions may be entered,
The second cohort search unit excludes all search results of each of the exclusion conditions from the electronic medical record results searched by the first cohort search unit,
The medical information providing system, characterized in that the display unit displays search results of each of the exclusion conditions excluded by the second cohort search unit on a display of the user terminal.
The method of claim 1, wherein the display unit,
The medical information providing system characterized in that the condition and the electronic medical record search result corresponding thereto are displayed simultaneously according to the order of conditions input to the user terminal. delete The method of claim 2, wherein the display unit
The medical information providing system characterized in that the condition and the search result corresponding to the condition are displayed in a box form, and the relationship between each search result is displayed with a line between the boxes. delete delete

Images