CN115136129A

CN115136129A - Digital inspection method and device applied to clinical test and related equipment

Info

Publication number: CN115136129A
Application number: CN202080096775.7A
Authority: CN
Inventors: 朱彤; 艾杰; 梅昀; 胥世承; 王军涛
Original assignee: Yidu Cloud Beijing Technology Co Ltd
Current assignee: Yidu Cloud Beijing Technology Co Ltd
Priority date: 2020-05-13
Filing date: 2020-05-13
Publication date: 2022-09-30
Also published as: WO2021226895A1

Abstract

A digital inspection method, device, electronic equipment and computer readable storage medium applied in clinical trials. The digital inspection method applied to clinical trials comprises the following steps: acquiring a target data record of a target subject from a clinical trial electronic data acquisition system (S110); obtaining a source data record of the target object from the full EHR data (S120); automatically identifying the source data records to obtain a target time table of the source data records of the target object (S130); and comparing the target data record with the target time table to obtain a comparison result of the target object (S140). The method compares the target data records with the target timetable obtained by identification to obtain a comparison result, and can realize a high-quality and high-efficiency digital inspection process in clinical tests so as to adapt to a massive data environment and reduce the cost of the clinical tests.

Description

Digital inspection method and device applied to clinical test and related equipment

Technical Field

The present disclosure relates to the field of computer technology, and more particularly, to a digital auditing method, apparatus, electronic device and computer-readable storage medium applied in clinical trials.

Background

In a conventional clinical trial, in order to ensure the data quality of the clinical trial, 1-2 manual inspections are usually performed during the execution process. The main contents of the inspection are operation compliance inspection and data accuracy inspection. The Data accuracy inspection mainly aims at the aspect of Data inspection in an Electronic Data Capture System (EDC) of a clinical trial. Because the source data need to be sorted and searched manually, and whether the source data are matched with the data input in the EDC needs to be compared manually, the time efficiency is low, and the manual error phenomenon cannot be avoided. Based on this, the traditional manual inspection adopts a sampling inspection mode aiming at the patient. The sampling inspection mode has the following problems:

1. the source data volume related to a Case Report Form (CRF), an adverse event record Form (AE), and a combined medication record Form (CM) is large, a lot of time is needed for manually checking the total volume of each patient, and meanwhile, manual errors are inevitable.

2. The sampling inspection mode for the patients can lead to the problem that the data of the patients which are not inspected can not be corrected in time. Meanwhile, because the manual inspection mode is difficult to accumulate and precipitate, the efficiency cannot be qualitatively improved.

3. The difference between the storage format and the organization format of the source data records and the record storage format in the EDC is large, the inspection difficulty is increased for a manual inspection mode, and the inspection method depends on the inspection experience of an inspector to a large extent.

Therefore, how to achieve high-efficiency and high-quality digital inspection in clinical trials is a problem to be solved urgently.

Disclosure of Invention

The embodiment of the disclosure provides a digital inspection method applied to clinical tests, which comprises the following steps: obtaining a target data record of a target object from a clinical trial electronic data acquisition system; obtaining a source data record for the target object from the full EHR data; automatically identifying the source data records to obtain a target time table of the source data records of the target object; and comparing the target data record with the target time table to obtain a comparison result of the target object.

In an exemplary embodiment, the method further comprises: acquiring a target standard dictionary; and normalizing the source data records according to the target standard dictionary to obtain normalized source data records.

In an exemplary embodiment, the target schedule of the source data records includes a target case report visit table of the source data records; wherein automatically identifying the source data record to obtain a target schedule of the source data record for the target object comprises: acquiring a case report visit standard table aiming at a target case report visit table in the clinical test electronic data acquisition system; and automatically identifying the normalized source data records according to the case report visiting standard table to obtain a target case report visiting table of the source data records of the target object.

In an exemplary embodiment, the target schedule of the source data records comprises a target consolidated medication record table of the source data records; wherein automatically identifying the source data record to obtain the target schedule of the target object comprises: obtaining a consolidated medication standard table for a target consolidated medication visit table in the clinical trial electronic data collection system, the consolidated medication standard table comprising a consolidated medication plan collection start time and a consolidated medication plan collection end time for the target subject; and automatically identifying the normalized source data records according to the combined medication standard table to obtain a target combined medication record table of the source data records of the target object.

In an exemplary embodiment, the target schedule of the source data records comprises a target adverse event record table of the source data records; wherein automatically identifying the source data record to obtain the target schedule of the target object comprises: obtaining an adverse event criteria table for a target adverse event visit table in the clinical trial electronic data collection system, the adverse event criteria table including an adverse event scheduled collection start time and an adverse event scheduled collection end time for the target subject; and automatically identifying the normalized source data record according to the adverse event standard table to obtain a target adverse event record table of the source data record of the target object.

In an exemplary embodiment, the method further comprises: and normalizing the target data record according to the target standard dictionary to obtain a normalized target data record.

In an exemplary embodiment, comparing the target data record with the target schedule to obtain a comparison result of the target object includes: acquiring configuration information; comparing the target data record with the target time table according to the configuration information to obtain a comparison result of the target object; the configuration information comprises fields of events corresponding to the event primary key field, the event state field and the event time field in the target time table.

In an exemplary embodiment, comparing the target data record with the target schedule according to the configuration information to obtain a comparison result of the target object includes: acquiring a target time table of the target data record from the target data record; according to the configuration information, acquiring an event main key field, an event state field and an event time field of a first event from a target time table of the target data record; searching a second event from a target time table of the source data record according to an event primary key field of a first event of the target data record; sequencing the second events according to the occurrence time of the second events; searching a target event of which the occurrence time accords with the event time field of the first event of the target data record from the sequenced second events; and comparing the event state field of the target event with the event state field of the first event to obtain the comparison result of the target object.

In an exemplary embodiment, comparing the target data record with the target schedule according to the configuration information to obtain a comparison result of the target object, further includes at least one of: if the event main key field, the event state field and the occurrence time of the target event are completely matched with the event main key field, the event state field and the event time field of the first event, the comparison result is completely matched; if the event primary key field of the second event is matched with the event primary key field of the first event, and the occurrence time of the second event is partially matched with the event time field of the first event, the comparison result is partial matching; if the second event is found to be failed, or the occurrence time of the second event is not matched with the event time field of the first event completely, the comparison result is that evidence is not found; if the source data record further includes a third event that the event primary key field is not matched with the first event of the target data record completely, or the source data record further includes a fourth event that the event primary key field is matched with the first event of the target data record and the occurrence time is not matched with the event time field of the first event completely, the comparison result is not reported.

In an exemplary embodiment, the method further comprises: generating correction information according to the comparison result; and correcting the configuration information and the target standard dictionary according to the correction information.

In an exemplary embodiment, the method further comprises: generating reason analysis information of the target record according to the comparison result; and displaying the comparison result and the reason analysis information of the target object on display equipment.

The disclosed embodiment provides a digital inspection device applied in clinical trials, which comprises: a first data acquisition module configured to acquire a target data record of a target subject from a clinical trial electronic data acquisition system; a second data acquisition module configured to acquire a source data record of the target object from the full amount of EHR data; a source data identification module configured to automatically identify the source data record and obtain a target schedule of the source data record of the target object; and the data record comparison module is configured to compare the target data record with the target time table to obtain a comparison result of the target object.

An embodiment of the present disclosure provides an electronic device, including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the digital auditing method applied in a clinical trial as described in embodiments of the present disclosure via execution of the executable instructions.

The disclosed embodiments provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a digital auditing method applied in clinical trials as described in the disclosed embodiments.

According to the technical scheme provided by some embodiments of the disclosure, the target data records in the clinical test electronic data acquisition system are compared with the target schedule identified from the full EHR data to obtain the comparison result, so that a high-quality and high-efficiency digital inspection process in the clinical test can be realized, the digital inspection process is suitable for massive data environments, and the clinical test cost is reduced.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings used in the embodiments or the description of the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without inventive efforts.

FIG. 1 is a flow chart of a digital auditing method applied in a clinical trial according to an example embodiment of the present disclosure;

FIG. 2 is a flow chart of a digital auditing method applied in a clinical trial according to an exemplary embodiment of the present disclosure;

FIG. 3 is a flow chart of a digital auditing method applied in a clinical trial according to an exemplary embodiment of the present disclosure;

FIG. 4 is a flow chart of a digital auditing method applied in a clinical trial according to an exemplary embodiment of the present disclosure;

FIG. 5 is a flow chart of a digital auditing method applied in a clinical trial according to an exemplary embodiment of the present disclosure;

FIG. 6 is a flow chart of a digital audit method applied in a clinical trial according to an example embodiment of the present disclosure;

FIG. 7 is a flow chart of a digital auditing method applied in a clinical trial according to an exemplary embodiment of the present disclosure;

FIG. 8 is a flow chart of a digital auditing method applied in a clinical trial according to an exemplary embodiment of the present disclosure;

FIG. 9 is a flow chart of a digital auditing method applied in a clinical trial according to an exemplary embodiment of the present disclosure;

FIG. 10 is a schematic illustration of a distribution of cause analysis information for an adverse event record table according to an exemplary embodiment of the present disclosure;

FIG. 11 is a flow chart of a digital auditing method applied in a clinical trial according to an exemplary embodiment of the present disclosure;

FIG. 12 is a schematic diagram of a digital auditing apparatus for use in clinical trials according to an exemplary embodiment of the present disclosure;

FIG. 13 illustrates a schematic structural diagram of a computer system suitable for use with the electronic device implementing an embodiment of the present disclosure.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and the like. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.

Further, the drawings are merely schematic illustrations of the present disclosure, in which the same reference numerals denote the same or similar parts, and thus, a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

In the related art, the inspection work of EDC mainly includes the inspection work of Case Report Form (CRF), adverse event record Form (AE), and combination medication record Form (CM). An adverse event is an adverse medical event that occurs after a patient or clinical subject receives a drug, but is not necessarily causal to treatment. The combined administration means that two or more medicines are applied simultaneously or sequentially for achieving the purpose of treatment, and the result is mainly to increase the curative effect of the medicines or to reduce the toxic and side effects of the medicines.

The following detailed description of exemplary embodiments of the disclosure refers to the accompanying drawings.

Fig. 1 is a flowchart of a digital auditing method applied in a clinical trial according to an exemplary embodiment of the present disclosure.

As shown in fig. 1, a digital inspection method applied in a clinical trial provided by an embodiment of the present disclosure may include the following steps.

Step S110, a target data record of a target object is acquired from a clinical trial electronic data acquisition system.

In the embodiment of the disclosure, the clinical test electronic data acquisition system is a data acquisition system for directly and remotely acquiring the clinical test data of the mobile phone from a test center (Sites) through the internet. The target object may be a target patient currently in need of digital auditing. The target data records may include, but are not limited to, a case report form, an adverse event record form, a combined medication record form, and the like.

In step S120, a source data Record of the target object is obtained from the full volume EHR data (Electronic Health Record).

In the embodiment of the disclosure, the full EHR data is a digital health file with an electronic medical record of a hospital as a main body and information sharing as a core. The source data record is electronic medical record information of the target object in the full volume EHR data. In an exemplary embodiment, at least one electronic medical record information of at least one hospital for the target object can be obtained and integrated to obtain the source data record of the target object.

Step S130, automatically identifying the source data record, and obtaining a target time schedule of the source data record of the target object.

In the disclosed embodiments, the target schedule may include, but is not limited to, a case report form, an adverse event record form, a combined medication record form, and the like. The source data records can be automatically identified according to a standard dictionary, a preset rule or based on semantics, and a target time table of the source data records of the target object is obtained. Taking the dictionary-based recognition of the combined medication record form as an example, the medication records are usually stored as structured information in the medical orders, and the writing of the drugs is a limited data set, so that a standard dictionary of the writing of the drugs can be obtained, and the source data records are recognized according to the standard dictionary of the writing of the drugs to obtain the combined medication record form. As shown in table 1 below, the different writings of levofloxacin are covered in the standard dictionary of the writing of drugs.

TABLE 1

Standard words	Synonyms
Levofloxacin	Levofloxacin hydrochloride
Levofloxacin	Zoxamic acid fimbristylis

Step S140, comparing the target data record with the target schedule to obtain a comparison result of the target object.

In the embodiment of the disclosure, the case report visit table, the adverse event record table, the combined medication record table and the like in the target data record can be compared with the case report visit table, the adverse event record table, the combined medication record table and the like in the target time table respectively to obtain the comparison result of the target object.

According to the digital inspection method applied to the clinical test, the target data records in the clinical test electronic data acquisition system are compared with the target timetable identified from the full EHR data to obtain the comparison result, so that the high-quality and high-efficiency digital inspection process in the clinical test can be realized, the digital inspection method is suitable for massive data environments, and the clinical test cost is reduced.

Fig. 2 is a flowchart of a digital auditing method applied in a clinical trial according to an exemplary embodiment of the present disclosure.

As shown in FIG. 2, in one embodiment, a digital auditing method applied in a clinical trial may include:

in step S210, a target data record of a target subject is acquired from a clinical trial electronic data acquisition system.

In step S220, the source data record of the target object is acquired from the full EHR data.

In step S230, a target standard dictionary is acquired.

In the embodiment of the present disclosure, the target standard dictionary may be a preset medical dictionary, and may also be a medical dictionary for the target object.

And step S240, normalizing the source data records according to the target standard dictionary to obtain normalized source data records.

In the disclosed embodiment, the specific object of the normalization operation may include, but is not limited to, a pair key field (e.g., a test name, a test value, a drug name), and the like.

In step S250, the normalized source data records are automatically identified to obtain a target schedule of source data records of the target object.

In step S260, the target data record is compared with the target schedule to obtain a comparison result of the target object.

In an exemplary embodiment, the target data records may also be normalized according to a target standard dictionary to obtain normalized target data records.

According to the digital inspection method applied to the clinical test, before the source data records are automatically identified, the source data records are normalized, so that all fields or field values in the source data records can be unified into a consistent expression mode, and the accuracy of digital inspection is improved.

FIG. 3 is a flow chart of a digital auditing method applied in a clinical trial according to an exemplary embodiment of the present disclosure.

As shown in fig. 3, in one embodiment, the target schedule of the source data records includes a target case report visit table of the source data records. Step S250 may include:

step S310, a case report visit standard table for a target case report visit table in the clinical trial electronic data collection system is obtained.

In the embodiment of the disclosure, the medical record report visit standard table may include specific rules of visit time.

And step S320, automatically identifying the normalized source data records according to the case report visit standard table to obtain a target case report visit table of the source data records of the target object. According to the digital auditing method applied to the clinical test, the source data records are automatically identified according to the case report visit standard table aiming at the case report visit table in the clinical test electronic data acquisition system, the target case record visit table with the format consistent with that of the target data records can be obtained, convenience is provided for data comparison, and the accuracy of digital auditing is improved.

Fig. 4 is a flowchart of a digital auditing method applied in a clinical trial according to an example embodiment of the present disclosure.

As shown in FIG. 4, in one embodiment, the target schedule of source data records includes a target consolidated medication record table of source data records. Step S250 may include:

step S410, acquiring a merged medication standard table aiming at a target merged medication visit table in the clinical trial electronic data acquisition system, wherein the merged medication standard table comprises a merged medication plan collection starting time and a merged medication plan collection finishing time of a target object.

In an exemplary embodiment, the combined medication standard table may further include a medication classification table describing detailed classification information of the medicine, such as specific medicines under the contraband category, specific medicines under the non-care medication category that are not included in the combined medication, and the like.

And step S420, automatically identifying the normalized source data records according to the combined medication standard table to obtain a target combined medication record table of the source data records of the target object.

According to the digital inspection method applied to the clinical test, the source data records are automatically identified according to the combined medicine standard table (and the medicine classification table) aiming at the combined medicine visit table in the clinical test electronic data acquisition system, the target combined medicine record table consistent with the target data record format can be obtained, convenience is brought to data comparison, and the accuracy of digital inspection is improved.

FIG. 5 is a flow chart of a digital auditing method applied in a clinical trial according to an exemplary embodiment of the present disclosure.

As shown in FIG. 5, in one embodiment, the target schedule of source data records includes a target consolidated medication record table of source data records. Step S250 may include:

step S510 acquires an adverse event criteria table for a target adverse event visit table in the clinical trial electronic data collection system, the adverse event criteria table including an adverse event scheduled collection start time and an adverse event scheduled collection end time for the target subject.

In the disclosed embodiment, the Adverse event Criteria table may be Common Adverse event evaluation Criteria (CTCAE). Common adverse event evaluation criteria is a descriptive term that can be used for adverse event reporting. A grade (severity) ranking was performed for each adverse event.

And step S520, automatically identifying the normalized source data records according to the adverse event standard table to obtain a target adverse event record table of the source data records of the target object. According to the digital inspection method applied to the clinical test, the source data records are automatically identified according to the adverse event standard table of the adverse event visit table in the clinical test electronic data acquisition system, the target adverse event record table consistent with the target data record format can be obtained, convenience is provided for data comparison, and the accuracy of digital inspection is improved.

FIG. 6 is a flow chart of a digital auditing method applied in a clinical trial according to an exemplary embodiment of the present disclosure.

As shown in fig. 6, in one embodiment, step S140 may include the following steps.

Step S610, configuration information is acquired.

Step S620, comparing the target data record with the target time schedule according to the configuration information to obtain a comparison result of the target object; the configuration information comprises fields of events corresponding to the event primary key field, the event state field and the event time field in the target time table.

In an exemplary embodiment, the target data record may be, for example, a normalized target data record generated by normalizing the target data record according to a target standard dictionary.

FIG. 7 is a flow chart of a digital auditing method applied in a clinical trial according to an exemplary embodiment of the present disclosure.

As shown in fig. 7, in one embodiment, step S620 may include the following steps.

Step S710, obtain the target schedule of the target data record from the target data record.

In embodiments of the present disclosure, the target schedule of the target data records may include a case report visit table, an adverse event record table, and a combined medication record table. In an exemplary embodiment, the target data records may be normalized in advance according to the target standard dictionary to obtain normalized target data records, so as to perform step S710 on the normalized target data records.

Step S720, according to the configuration information, the event main key field, the event state field and the event time field of the first event are obtained from the target time table of the target data record.

Step S730, according to the event primary key field of the first event of the target data record, searching for the second event from the target time table of the source data record.

In an exemplary embodiment, the source data records may be normalized in advance according to the target standard dictionary to obtain normalized source data records, so as to perform step S730 on the source target data records.

Step S740, sorting the second events according to the occurrence time of the second events.

Step S750, searching for a target event whose occurrence time matches the event time field of the first event in the target data record from the sorted second events.

Step S760, comparing the event status field of the target event with the event status field of the first event, so as to obtain a comparison result of the target object.

In an exemplary embodiment, the comparison of the adverse event record table is taken as an example. Table 2 is a truncated portion of the table of adverse event records in the target data record (or normalized target data record).

TABLE 2

Table 3 shows a truncated portion of the target adverse event record table in the source data record (or normalized source data record).

TABLE 3

As shown in tables 2 and 3, in the target data record in the clinical trial electronic data acquisition system, events of the same state that have continued for a while are generally recorded as one event, and in the source data record in the full EHR data, the same state time that has occurred at different time points is generally recorded a plurality of times. For example, in step S720, the event primary key field in the target data record may be determined as the AE name, the event status field as the rank, and the event time field as the start time and the end time according to the configuration information. For another example, in step S720, the event primary key field may be determined as an AE name and a rank according to the configuration information. The configuration information describes fields of the corresponding events in the target time table of the event primary key field, the event state field and the event time field. When the event primary key field is AE name, in step S730, the field value of the event status field of the first event in the target data record in table 2 is: nausea. A second event with an event primary key field of "nausea" may be looked up in the target schedule of the source data record in table 3. And searching a target event of which the occurrence time accords with the event time field of the first event in the sequenced second events. The event time field that corresponds to the first event may be: the occurrence time T satisfies the rule: the start time T is the end time.

According to the digital inspection method applied to the clinical test, the configuration information is utilized to obtain the event main key field, the event state field and the event time field from the first event in the target data record, the second event is obtained by searching the target time table in the source data record according to the event main key field, and the matching based on the event main key field can be realized. And sequencing the second events according to the occurrence time, searching in the second events according to the event time field to obtain the target events, and realizing the analysis and matching based on the time sequence. In summary, according to the technical scheme of the embodiment of the present disclosure, based on the comparison process of the three dimensions of the event main key field, the event time field, and the event status field, the target data record and the source data record can be compared quickly and efficiently in the digital inspection process in the clinical test, so as to obtain a high-quality comparison result.

In one embodiment, step S620 may further include at least one of the following steps.

Step S761, if the event primary key field, the event status field, and the occurrence time of the target event are completely matched with the event primary key field, the event status field, and the event time field of the first event, the comparison result is a complete match.

In step S762, if the event primary key field of the second event matches the event primary key field of the first event, and the occurrence time of the second event partially matches the event time field of the first event, the comparison result is a partial match.

In step S763, if the second event is found to be failed, or the occurrence time of the second event is not matched with the event time field of the first event, the comparison result is that no evidence is found.

In the embodiment of the present disclosure, when the search for the second event fails, or the occurrence time of the second event does not match the event time field of the first event completely, it may be determined that the target data record includes an event that is not recorded in the source data record.

In step S764, if the source data record further includes a third event that the event primary key field is not matched with the first event of the target data record completely, or the source data record further includes a fourth event that the event primary key field is matched with the first event of the target data record and the occurrence time is not matched with the event time field of the first event completely, the comparison result is not reported.

In the embodiment of the present disclosure, when a third event whose event primary key field does not match the first event of the target data record completely is further included in the source data record, or a fourth event whose event primary key field matches the first event of the target data record and whose occurrence time does not match the event time field of the first event completely is further included in the source data record, it may be determined that an event recorded in the source data record is absent in the target data record.

In an exemplary embodiment, configuration information may be set, the configuration information including fields of the event corresponding to the event primary key field, the event status field, and the event time field in the target schedule.

According to the digital inspection method applied to the clinical test, the target data records and the target time tables of the target source data records are matched according to the event main key fields, the event state fields and the event time fields, the comparison result is determined according to the matching result, the comparison result is divided into complete matching, partial matching, evidence not found and reported not, the comparison result can be accurately divided on the basis of three-dimensional data comparison, an operator can find the reason of data error timely according to the comparison result, and user experience is improved.

FIG. 8 is a flow chart of a digital auditing method applied in a clinical trial according to an exemplary embodiment of the present disclosure.

As shown in FIG. 8, in one embodiment, the digital auditing method applied in a clinical trial may further include the following steps.

Step S810, generating correction information according to the comparison result.

Step S820, the configuration information and the target standard dictionary are corrected according to the correction information.

In the embodiment of the disclosure, the configuration information and the target standard dictionary are corrected according to the correction information, so that the configuration information and the target standard dictionary can be continuously optimized, and the accuracy of digital inspection is improved.

FIG. 9 is a flow chart of a digital auditing method applied in a clinical trial according to an exemplary embodiment of the present disclosure.

As shown in FIG. 9, in one embodiment, the digital auditing method applied in a clinical trial may further include the following steps.

Step S910, generating reason analysis information of the target record according to the comparison result.

Step S920, displaying the comparison result and the reason analysis information of the target object on the display device.

In the embodiment of the present disclosure, the reason analysis information may be as follows:

1. and (3) complete matching: no care is required.

2. Partial matching: the source data record does not necessarily exist entirely within the target data record, such as paper evidence (e.g., an out-of-hospital paper medical record).

1) The paper quality is correct: and finding real evidence in the paper evidence, and finally confirming a complete match.

2) Confirming the error recording: no true evidence is found in the paper evidence and the final confirmation is a CRC entry error.

3. No evidence was found: the target data record does not necessarily reside entirely within the source data record, such as paper evidence (e.g., an out-of-hospital paper medical record).

1) Paper covering: and finding real evidence in the paper evidence, and finally completely matching.

2) Confirming error recording: true evidence has not been found in paper evidence, and the final confirmation is that the Clinical Research Coordinator (CRC) misincorporated the data.

3) Unknown: the paper evidence still does not find true evidence, and is finally reported to a Clinical investigator (CRA) for further confirmation.

4) The algorithm problem is as follows: the algorithmic problem that still exists due to machine recognition in natural language needs to be corrected.

4. Not reported: it is likely that there is a source data record, but the CRC is not found at the time of logging.

1) Confirming input missing: the researcher has confirmed the record to be entered, the CRC is not entered, and there is a manual error.

2) And (4) determining whether the leakage is detected: the researchers have not judged the abnormal data, and the CRC does not find the researchers to judge and has manual errors.

3) Confirming that reporting is not required: the researchers confirm that the report is not needed.

Fig. 10 is a schematic diagram of a distribution of cause analysis information for an adverse event log table according to one example of the present disclosure. As shown in fig. 10, the reason analysis information may be as follows:

1. complete matching

1) Complete match 901: the inspector does not need to pay any attention any more, and the whole time is saved.

2. Partial matching

2) Confirmation of error in entry 902: the AE level is actually 2 level error entry to 1 level, requiring modification.

3) Paper quality is correct 903: the AE grade is 1 grade in a source data record, is 2 grades in a paper record, and is correctly recorded.

3. No evidence was found

4) Paper cover 904: the actual evidence is in paper case history.

5) The algorithm problem 905: the auditor judges partial problems of the machine algorithm, and the algorithm needs to be further strengthened.

6) Unknown 906: the auditor also finds no evidence and needs to have the CRA further verified.

7) Error entry 907: AE record records were repeated two times.

4. Has not reported yet

8) AE missing entry 908: the investigator has confirmed an AE, but the CRC was not entered EDC, entered error.

9) AE missing determination 909: the investigator does not judge the suspected AE and needs to process the suspected AE after judgment.

10) NAE 910: and the judgment shows that the algorithm is not AE, and the algorithm needs to be further strengthened without inputting.

In an exemplary embodiment, the correction information can be determined according to the reason analysis information, and the configuration information and the target standard dictionary are corrected according to the correction information, so that the accuracy of digital inspection is improved, and the degree of manual participation is reduced. Taking a dictionary in the combined medication as an example:

there was one combined medication record in EDC: levofloxacin; year 2018, month 2 and day 2. According to the technical scheme of the embodiment of the disclosure, the comparison result is determined to be that evidence is not found, the record is checked by an inspector to exist in the medical advice of the outpatient medicine mouth, and then the fact that the doctor writes the medicine as that the levofloxacin has wrongly written characters is found out, and the new words do not appear in the target standard dictionary to cause that the levofloxacin is not correctly normalized. The problem is solved after the levofloxacin is updated into a word stock. The accuracy of the whole combined medication identification is improved in the iterative process.

FIG. 11 is a flow chart of a digital auditing method applied in a clinical trial according to an exemplary embodiment of the present disclosure. As shown in FIG. 11, in one embodiment, a digital auditing method applied in a clinical trial may include the following steps. Step S1110, disassembling the scheme.

In the embodiment of the disclosure, the case report visit standard table, the combined medication standard table, the adverse event standard table, the medication classification table and the target standard dictionary of the target object can be determined according to the clinical test scheme of the target object.

The acquisition process of the case report visit standard table may take steps similar to step S310, which are not described in detail here.

The acquiring process of the medication combination standard table may take steps similar to step S410, and will not be described herein.

The obtaining process of the adverse event criteria table may take steps similar to step S510, which are not described herein.

The target standard dictionary can be obtained by performing extraction and integration in the standard dictionary according to the clinical test scheme of the target subject.

In step S1120, the data is normalized.

In embodiments of the present disclosure, the target data records may be normalized. And carrying out normalization and automatic identification on the source data records to obtain a target time table of the source data records. The normalization and automatic identification process for the source data records may take steps similar to steps S240, S250, which are not described in detail herein.

Step S1130, data comparison.

In the embodiment of the present disclosure, the normalized target data record may be compared with the target schedule of the normalized source data record to obtain the comparison result of the target object. The data alignment process may adopt steps similar to step S140 or steps S710 to S760, S761 to S764, and will not be described herein again.

Step S1140, data analysis.

In the embodiment of the disclosure, reason analysis information of the target record can be generated according to the comparison result; and displaying the comparison result and the reason analysis information of the target object on display equipment.

Step S1150, iterate feedback.

In the embodiment of the disclosure, the correction information can be generated according to the comparison result; and correcting the configuration information and the target standard dictionary according to the correction information.

In an exemplary embodiment, if the automatic identification of the source data record is based on a rule, the rule may be further modified according to the modification information.

In an exemplary embodiment, an audit report may also be generated. Wherein, an inspection report can be generated according to the comparison result and the reason analysis information; and sending the audit report to the sponsor of the target object.

Based on the same concept as the method embodiment of the present invention, fig. 12 shows a schematic structural diagram of a digital inspection device applied in clinical trials according to an exemplary embodiment of the present disclosure. Referring to fig. 12, a digital auditing apparatus for clinical trials is also provided in the embodiments of the present invention. As shown in fig. 12, the digital auditing apparatus 1200 applied in a clinical trial may include a first data acquisition module 1210, a second data acquisition module 1220, a source data identification module 1230, and a data record comparison module 1240.

In a digital auditing apparatus 1200 employed in a clinical trial, a first data acquisition module 1210 may be configured to acquire target data records of a target subject from a clinical trial electronic data acquisition system.

The second data acquisition module 1220 may be configured to acquire source data records for a target object from the full amount of EHR data.

The source data identification module 1230 may be configured to automatically identify the source data records to obtain a target schedule of source data records for the target object.

In an exemplary embodiment, the target schedule of the source data records may include a target case report interview table of the source data records. The source data identification module can comprise a case report visit standard table acquisition unit and a case report visit table identification unit. Wherein the case report visit standard table acquisition unit may be configured to acquire a case report visit standard table for a target case report visit table in the clinical trial electronic data collection system. The medical record report visiting table identification unit can be configured to automatically identify the normalized source data records according to a medical record visiting standard table to obtain a target medical record report visiting table of the source data records of the target object.

In an exemplary embodiment, the target schedule of source data records may include a target consolidated medication record table of source data records. The source data identification module may include a combined medication standard table acquisition unit and a combined medication record table identification unit. Wherein the medication combination standard table acquiring unit may be configured to acquire a medication combination standard table for a target medication combination visit table in the clinical trial electronic data collection system, the medication combination standard table including a medication combination plan collection start time and a medication combination plan collection end time of the target subject. The merged medication record table identifying unit may be configured to automatically identify the normalized source data records according to the merged medication standard table, and obtain a target merged medication record table of the source data records of the target object.

In an exemplary embodiment, the target schedule of source data records may include a target adverse event record table of source data records. The source data identification module may include an adverse event criteria table acquisition unit and an adverse event record table identification unit. Wherein the adverse event criteria table acquisition unit may be configured to acquire an adverse event criteria table for a target adverse event visit table in the clinical trial electronic data collection system, the adverse event criteria table including an adverse event scheduled collection start time and an adverse event scheduled collection end time for the target subject. The adverse event record table identifying unit may be configured to automatically identify the normalized source data records according to an adverse event criteria table, to obtain a target adverse event record table of source data records of the target object.

The data record comparison module 1240 may be configured to compare the target data record with the target schedule to obtain a comparison result of the target object.

In an exemplary embodiment, the data record alignment module 1240 may include a configuration information acquisition unit and a data alignment unit. Wherein the configuration information obtaining unit may be configured to obtain the configuration information. The data comparison unit can be configured to compare the target data record with the target time table according to the configuration information to obtain a comparison result of the target object; the configuration information comprises event main key fields, event state fields and corresponding event fields of the event time fields in the target time table.

In an exemplary embodiment, the data alignment unit may include a target schedule acquisition unit, a field acquisition unit, a primary key field alignment unit, a time sorting unit, a time field alignment unit, and a status field alignment unit. Wherein the target schedule acquiring unit may be configured to acquire the target schedule of the target data record from the target data records. The field acquisition unit may be configured to acquire an event primary key field, an event status field, and an event time field of the first event from a target schedule of the target data record according to the configuration information. The primary key field comparison unit may be configured to look up a second event from the target schedule of the source data record according to the event primary key field of the first event of the target data record. The time ordering unit may be configured to order the second events according to their occurrence times. The time field comparison unit may be configured to search for a target event whose occurrence time matches the event time field of the first event of the target data record from the sorted second events. The state field comparison unit may be configured to compare the event state field of the target event with the event state field of the first event, and obtain a comparison result of the target object.

In an exemplary embodiment, the data alignment unit may further include at least one of: a first result unit, a second result unit, a third result unit, and a fourth result unit. The first result unit may be configured to determine that the comparison result is a complete match if the event primary key field, the event status field, and the occurrence time of the target event are completely matched with the event primary key field, the event status field, and the event time field of the first event. The second result unit may be configured to determine that the comparison result is a partial match if the event primary key field of the second event matches the event primary key field of the first event, and the occurrence time of the second event partially matches the event time field of the first event. The third result unit may be configured to determine that no evidence is found if the search fails for the second event or the occurrence time of the second event completely does not match the event time field of the first event. The fourth result unit may be configured to determine that the comparison result is not reported if the source data record further includes a third event whose event primary key field does not match the first event of the target data record completely, or the source data record further includes a fourth event whose event primary key field matches the first event of the target data record and whose occurrence time does not match the event time field of the first event completely.

In an exemplary embodiment, the digital auditing apparatus 1200 applied in a clinical trial may also include a dictionary acquisition module and a source data normalization module. Wherein the dictionary acquisition module may be configured to acquire the target standard dictionary. The source data normalization module may be configured to normalize the source data records according to the target standard dictionary to obtain normalized source data records.

In an exemplary embodiment, the digital auditing apparatus 1200 applied in a clinical trial may further include a target data normalization module, where the target data normalization module may be configured to normalize the target data records according to a target standard dictionary, obtaining normalized target data records.

In an exemplary embodiment, the digital auditing apparatus 1200 applied in a clinical trial may also include a configuration information setting module. The configuration information setting module may be configured to set configuration information including fields of events corresponding to the event primary key field, the event status field, and the event time field in the target schedule.

In an exemplary embodiment, the digital auditing apparatus 1200 applied in clinical trials may further include a correction information generation module and a data correction module. The correction information generation module can be configured to generate correction information according to the comparison result. The data correction module may be configured to correct the configuration information and the target standard dictionary based on the correction information.

In an exemplary embodiment, the digital auditing apparatus 1200 applied in a clinical trial may further include a cause analysis information generation module and a cause analysis information presentation module. The reason analysis information generation module may be configured to generate reason analysis information of the target record according to the comparison result. The reason analysis information presentation module may be configured to present the comparison result of the target object and the reason analysis information on the display device.

According to the digital inspection device applied to the clinical test, the target data records in the clinical test electronic data acquisition system are compared with the target timetable identified from the full EHR data to obtain the comparison result, so that the high-quality and high-efficiency digital inspection process in the clinical test can be realized, the digital inspection device is suitable for massive data environments, and the cost of the clinical test is reduced.

For convenience of description, the above device embodiments are described with functions divided into various units or modules, and the functions of the units or modules may be implemented in one or more software and/or hardware when implementing the present invention.

FIG. 13 illustrates a schematic structural diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present disclosure. It should be noted that the computer system 1500 of the electronic device shown in fig. 13 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 13, the computer system 1300 includes a Central Processing Unit (CPU)1301 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)1302 or a program loaded from a storage section 1308 into a Random Access Memory (RAM) 1303. In the RAM 1303, various programs and data necessary for system operation are also stored. The CPU 1301, the ROM 1302, and the RAM 1303 are connected to each other via a bus 1304. An input/output (I/O) interface 1305 is also connected to bus 1304.

The following components are connected to the I/O interface 1305: an input portion 1306 including a keyboard, a mouse, and the like; an output portion 1307 including a signal such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 1308 including a hard disk and the like; and a communication section 1309 including a network interface card such as a LAN card, a modem, or the like. The communication section 1309 performs communication processing via a network such as the internet. The drive 1310 is also connected to the I/O interface 1305 as needed. A removable medium 1311 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 1310 as needed, so that the computer program read out therefrom is mounted in the storage section 1308 as needed.

In particular, the processes described below with reference to the flowcharts may be implemented as computer software programs, according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such embodiments, the computer program may be downloaded and installed from a network through communications component 1309 and/or installed from removable media 1311. When the computer program is executed by a Central Processing Unit (CPU)1301, various functions defined in the system of the present application are executed.

It should be noted that the computer readable medium shown in the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer-readable signal medium may include a propagated data signal with computer-readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The modules and/or units and/or sub-units described in the embodiments of the present disclosure may be implemented by software, or may be implemented by hardware, and the described modules and/or units and/or sub-units may also be disposed in a processor. Wherein the names of such modules and/or units and/or sub-units do not in some way constitute a limitation on the modules and/or units and/or sub-units themselves.

As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or program product. Accordingly, various aspects of the present invention may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.

It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, and may also be implemented by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium having stored thereon a program product capable of implementing the above-described method of the present specification. In some possible embodiments, aspects of the invention may also be implemented in the form of a program product comprising program code means for causing a terminal device to carry out the steps according to various exemplary embodiments of the invention described in the above-mentioned "exemplary methods" section of the present description, when the program product is run on the terminal device.

Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

In the several embodiments provided in the present disclosure, it should be understood that the disclosed electronic device, computer-readable storage medium, and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit is only a logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electrical, mechanical or other form of connection.

Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the elements may be selected according to actual needs to achieve the objectives of the embodiments of the present disclosure.

In addition, functional units in the embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present disclosure may be substantially or partially contributed by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method of the embodiments of the present disclosure. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

While the present disclosure has been described with reference to specific embodiments, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

Claims

A digital auditing method for use in a clinical trial, comprising:

obtaining a target data record of a target object from a clinical trial electronic data acquisition system;

obtaining a source data record for the target object from the full EHR data;

automatically identifying the source data records to obtain a target time table of the source data records of the target object;

and comparing the target data record with the target time table to obtain a comparison result of the target object.
The method of claim 1, wherein the method further comprises:

acquiring a target standard dictionary;

and normalizing the source data records according to the target standard dictionary to obtain normalized source data records.
The method of claim 2, wherein the target schedule of the source data records comprises a target case report interview table of the source data records; wherein automatically identifying the source data record to obtain a target schedule of the source data record for the target object comprises:

acquiring a case report visit standard table aiming at a target case report visit table in the clinical test electronic data acquisition system;

and automatically identifying the normalized source data records according to the case report visiting standard table to obtain a target case report visiting table of the source data records of the target object.
The method of claim 2, wherein the target schedule of the source data records comprises a target consolidated medication record table of the source data records; wherein automatically identifying the source data record to obtain the target schedule of the target object comprises:

obtaining a consolidated medication standard table for a target consolidated medication visit table in the clinical trial electronic data collection system, the consolidated medication standard table comprising a consolidated medication plan collection start time and a consolidated medication plan collection end time for the target subject;

and automatically identifying the normalized source data records according to the combined medication standard table to obtain a target combined medication record table of the source data records of the target object.
The method of claim 2, wherein the target schedule of the source data records comprises a target adverse event record table of the source data records; wherein automatically identifying the source data record to obtain a target schedule of the target object comprises:

obtaining an adverse event criteria table for a target adverse event visit table in the clinical trial electronic data collection system, the adverse event criteria table including an adverse event scheduled collection start time and an adverse event scheduled collection end time for the target subject;

and automatically identifying the normalized source data record according to the adverse event standard table to obtain a target adverse event record table of the source data record of the target object.
The method of claim 2, wherein the method further comprises:

and normalizing the target data record according to the target standard dictionary to obtain a normalized target data record.
The method of claim 1, wherein comparing the target data record to the target schedule to obtain a comparison of the target object comprises:

acquiring configuration information;

comparing the target data record with the target time table according to the configuration information to obtain a comparison result of the target object; the configuration information comprises fields of events corresponding to the event primary key field, the event state field and the event time field in the target time table.
The method of claim 7, wherein comparing the target data record to the target schedule according to the configuration information to obtain a comparison result of the target object comprises:

obtaining a target schedule of the target data records from the target data records;

according to the configuration information, acquiring an event main key field, an event state field and an event time field of a first event from a target time table of the target data record;

searching a second event from a target time table of the source data record according to an event primary key field of a first event of the target data record;

sequencing the second events according to the occurrence time of the second events;

searching a target event of which the occurrence time accords with the event time field of the first event of the target data record from the sequenced second events;

and comparing the event state field of the target event with the event state field of the first event to obtain the comparison result of the target object.
The method of claim 8, wherein comparing the target data record to the target schedule according to the configuration information to obtain a comparison result of the target object further comprises at least one of:

if the event main key field, the event state field and the occurrence time of the target event are completely matched with the event main key field, the event state field and the event time field of the first event, the comparison result is completely matched;

if the event primary key field of the second event is matched with the event primary key field of the first event, and the occurrence time of the second event is partially matched with the event time field of the first event, the comparison result is partial matching;

if the second event is found to be failed, or the occurrence time of the second event is not matched with the event time field of the first event completely, the comparison result is that evidence is not found;

if the source data record further includes a third event that the event primary key field is not matched with the first event of the target data record completely, or the source data record further includes a fourth event that the event primary key field is matched with the first event of the target data record and the occurrence time is not matched with the event time field of the first event completely, the comparison result is not reported.
The method of claim 7, wherein the method further comprises:

generating correction information according to the comparison result;

and correcting the configuration information and the target standard dictionary according to the correction information.
The method of claim 1, wherein the method further comprises:

generating reason analysis information of the target record according to the comparison result;

and displaying the comparison result and the reason analysis information of the target object on display equipment.
A digital auditing apparatus for use in a clinical trial, comprising:

a first data acquisition module configured to acquire a target data record of a target subject from a clinical trial electronic data acquisition system;

a second data acquisition module configured to acquire source data records of the target object from the full amount of EHR data;

a source data identification module configured to automatically identify the source data record and obtain a target schedule of the source data record of the target object;

and the data record comparison module is configured to compare the target data record with the target time table to obtain a comparison result of the target object.
An electronic device, comprising:

a processor; and

a memory for storing executable instructions of the processor;

wherein the processor is configured to perform the digital auditing method applied in a clinical trial of any of claims 1-11 via execution of the executable instructions.
A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the digital auditing method for use in a clinical trial according to any one of claims 1-11.