A clinical trial key data automatic checking system

Abstract

The application discloses a kind of clinical trial key data automatic checking system, belong to clinical trial data quality control field.The application includes: logic check module (L23), check the logic relationship between data items (such as death date cannot be later than test end date);Scope check module (L24), check whether value is in preset normal range (such as body temperature 35-42°C);Cross-form consistency check module (L25), check the consistency of the same data item in different CRF forms;Real-time prompt module (L26), feedback error in time when data entry;Quality report generation module (L27), generate data quality report.The application realizes data quality pre-control, discovers and corrects error in real time in data entry stage, reduces later data cleaning workload, improves clinical trial data quality.

Description

Technical Field

[0001] This invention relates to the field of clinical trial data quality control technology, specifically to a system and method for performing real-time logical verification, range verification, and cross-form consistency verification during the data entry stage to achieve pre-control of data quality. Background Technology

[0002] Although some EDC systems support real-time field-level validation (such as data format and required field checks), existing solutions have the following shortcomings:

[0003] (1) Usually only a single dimension is checked (such as range check only or logic check only).

[0004] (2) Lack of cross-form consistency validation capability;

[0005] (3) The verification rules are not closely integrated with the specific needs of clinical trials (such as the order of informed consent date and operation date);

[0006] (4) Lack of a complete corrective loop after verification failure and automatic generation of quality reports.

[0007] Clinical trial data quality is the cornerstone of trial success. Traditional data validation is performed after data entry, meaning that by the time problems are discovered, data quality issues have already been established, resulting in high cleanup costs. Therefore, there is an urgent need for a system that can perform real-time validation during the data entry stage, enabling pre-emptive data quality control. Summary of the Invention

[0008] To address the shortcomings of existing technologies, this invention proposes an automatic verification system and method for key clinical trial data.

[0009] Technical solution

[0010] To achieve the above objectives, the present invention adopts the following technical solution:

[0011] In a first aspect, the present invention provides an automatic verification system for key clinical trial data, comprising:

[0012] The data acquisition interface (L21) is used to access the real-time data stream (L11) of the clinical trial electronic data capture (EDC) system.

[0013] The processing module is configured to perform the following operations:

[0014] • Logical verification (L23): Checks the logical relationships between data items (e.g., the death date cannot be later than the trial end date);

[0015] • Range check (L24): Checks whether the value is within the preset normal range (e.g., body temperature 35-42℃).

[0016] • Cross-Form Consistency Validation (L25): Checks the consistency of the same data item in different CRF forms;

[0017] • Real-time triggering of validation rules to immediately prompt errors during data entry (L26);

[0018] • Generate a data quality report (L27);

[0019] The output module (L28) is used to output the verification results and data quality report.

[0020] Secondly, the present invention provides an automatic verification method for key clinical trial data, including a real-time data access step, a logical verification step, a range verification step, a cross-form consistency verification step, a real-time prompting step, and a quality report generation step.

[0021] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0022] Beneficial effects

[0023] Compared to traditional methods that only use post-hoc verification, this invention:

[0024] 1. Error detection time has been reduced from an average of 24 hours to real-time (<1 second);

[0025] 2. Post-processing data cleaning workload reduced by 72%;

[0026] 3. The data quality pass rate increased from 85% to 98%.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] 1. Implement data quality control upfront to reduce post-processing costs;

[0029] 2. Real-time verification prompts and immediate error correction;

[0030] 3. Multi-dimensional verification coverage improves data integrity. Attached Figure Description

[0031] Figure 1 This is a schematic diagram of the system structure provided in an embodiment of the present invention. The diagram shows the composition and connection relationship of the data input layer (L1), the data processing and analysis platform (L2), and the output terminal (L3).

[0032] Figure 2 This is a schematic diagram of data validation rules provided in an embodiment of the present invention. The diagram shows example rules of the logical validation rule base (R1), the range validation rule base (R2), and the cross-form consistency rule base (R3).

[0033] Figure 3 This is a flowchart of data verification and real-time prompting provided by an embodiment of the present invention. The flowchart shows the complete process from step 1 (S2) to step 8 (S10). Detailed Implementation

[0034] The present invention will now be described in further detail with reference to the accompanying drawings and specific embodiments.

[0035] Example 1: System Structure

[0036] like Figure 1 As shown in the figure, this embodiment provides an automatic verification system for key clinical trial data.

[0037] The data input layer (L1) includes the real-time data stream of the EDC system (L11), which contains CRF input data.

[0038] The data processing and analysis platform (L2) includes:

[0039] • Data acquisition interface (L21) is used to receive real-time data streams from the EDC system;

[0040] • Preprocessing module (L22), used for data format standardization;

[0041] • The logic verification module (L23) is configured to check the logical relationships between data items;

[0042] • The range check module (L24) is configured to check whether the value is within a preset range;

[0043] • The cross-form consistency check module (L25) is configured to check the consistency of the same data item in different CRF forms;

[0044] • The real-time error message module (L26) is configured to provide immediate error messages during data entry;

[0045] • The quality report generation module (L27) is configured to generate data quality reports;

[0046] • Output module (L28) is used to output the verification results.

[0047] The output terminal (L3) includes a data entry operator interface (L31) and a data administrator workstation (L32).

[0048] Example 2: Data Validation Rules

[0049] like Figure 2 As shown, this embodiment details various verification rules.

[0050] The logic validation rule base (R1) includes:

[0051] • Date of death ≤ Trial end date (R11);

[0052] • Enrollment date ≤ Randomization date ≤ Dosing date (R12);

[0053] • Baseline examination date ≤ Post-treatment examination date (R13);

[0054] • The date of signing the informed consent form must be ≤ the date of any research operation (R14).

[0055] The range validation rule base (R2) includes:

[0056] • Body temperature: 35-42°C (R21);

[0057] • Heart rate: 40-180 beats / min (R22);

[0058] • Systolic blood pressure: 70-250 mmHg (R23);

[0059] •Diastolic blood pressure: 40-150 mmHg (R24);

[0060] • Laboratory parameters: upper and lower limits of reference range (R25).

[0061] The cross-form consistency rule base (R3) includes:

[0062] • Adverse event end date vs. concomitant medication end date (R31);

[0063] • Inclusion criteria confirmation vs. exclusion criteria confirmation (R32);

[0064] • Laboratory abnormalities vs. adverse event records (R33).

[0065] Example 3: Data Verification and Real-time Notification Method

[0066] like Figure 3 As shown in the figure, this embodiment details the complete process of data verification and real-time prompts.

[0067] Step 1 (S2): Connect to the real-time data stream of the EDC system.

[0068] Step 2 (S3): Perform logical verification to check the logical relationships between data items.

[0069] Step 3 (S4): Perform range verification to check whether the value is within the preset normal range.

[0070] Step 4 (S5): Perform cross-form consistency verification to check the consistency of the same data item in different CRF forms.

[0071] Step 5 (S6): Verification result judgment:

[0072] • If all validations pass, the data is successfully entered into the database (S7).

[0073] If any verification fails, proceed to step 6.

[0074] Step 6 (S8): Immediately display the error message on the data entry interface, showing the specific reasons for the verification failure and correction suggestions.

[0075] Step 7 (S9): The data entry clerk corrects the data according to the prompts and returns to Step 1 for re-verification.

[0076] Step 8 (S10): Generate a data quality report, including verification statistics, error distribution, correction records, etc.

[0077] Example 4: Clinical Validation

[0078] This embodiment verifies the technical effectiveness of the present invention using actual clinical trial data. A Phase III clinical trial (2000 subjects, 50000 CRF data points) was selected for verification.

[0079] The results show:

[0080] • Real-time verification coverage is 100%;

[0081] • 100% instant detection rate for data entry errors;

[0082] • Post-processing data cleaning workload reduced by 72%;

[0083] • Data quality pass rate increased from 85% to 98%;

[0084] • Data entry staff feedback and error correction time reduced by 65%.

[0085] The clinical value of the system of the present invention in pre-controlling data quality and improving data integrity has been verified.

[0086] Industrial applicability

[0087] The system and method provided by this invention can be integrated into EDC systems, clinical trial data management platforms, or CTMS systems, and are suitable for CRO companies, clinical trial departments of pharmaceutical companies, and clinical research institutions, with broad industrial application prospects.

[0088] The above-described embodiments are merely preferred embodiments to fully illustrate the present invention, and the scope of protection of the present invention is not limited thereto. The scope of protection of the present invention is defined by the claims.

Claims

1. An automatic verification system for key clinical trial data, characterized in that, include: The data acquisition interface (L21) is used to access the real-time data stream (L11) of the clinical trial electronic data acquisition system. The processing module is configured to perform the following operations: • Logical verification (L23): Checks the logical relationships between data items; • Range check (L24): Checks whether the value is within the preset normal range; • Cross-Form Consistency Validation (L25): Checks the consistency of the same data item in different CRF forms; • Real-time triggering of validation rules to immediately prompt errors during data entry (L26); • Generate a data quality report (L27); The output module (L28) is used to output the verification results and data quality report.

2. The system according to claim 1, characterized in that, The logical verification includes: • Date of death ≤ Trial end date; • Enrollment date ≤ Randomization date ≤ Dosing date; • Baseline examination date ≤ Post-treatment examination date; • The date of signing the informed consent form ≤ the date of any research operation.

3. The system according to claim 1, characterized in that, The range verification includes: • Body temperature: 35-42°C; • Heart rate: 40-180 beats / minute; • Systolic blood pressure: 70-250 mmHg; •Diastolic blood pressure: 40-150 mmHg; • Laboratory parameters: upper and lower limits of the reference range.

4. The system according to claim 1, characterized in that, The cross-form consistency check includes: • Consistency between the adverse event end date and the concomitant medication end date; • Consistency between the inclusion criteria and the exclusion criteria; • Consistency between laboratory abnormalities and adverse event records.

5. A method for automatic verification of key data in clinical trials, characterized in that, Includes the following steps: Step S2: Connect to the real-time data stream of the EDC system; Step S3: Perform logical verification to check the logical relationships between data items; Step S4: Perform range verification to check whether the value is within the preset range; Step S5: Perform cross-form consistency verification to check the consistency of data across different forms; Step S6: Determine the verification result. If the verification passes, the data is normally entered into the database. If the verification fails, proceed to step 7. Step S7: Immediately display error messages on the data entry interface; Step S8: The data entry clerk corrects the data according to the prompts and returns to step 2; Step S9: Generate a data quality report.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method as described in claim 5.

Images