Edit check specification

-

 Most important goal of a Clinical Data Manager is to ensure the consistency, quality & accuracy of clinical data. In this journey Edit check specification (ECS)plays a very crucial role to enable data cleaning.

ECS is created by DM’s with the input of study team member in clinical database build stage.

3 crucial things to understand about ECS

1. What are the pre-requisites to create / build ECS?
2. What are the checks to include in ECS?
3. What to avoid while writing ECS?


⭐ 𝗣𝗿𝗲-𝗿𝗲𝗾𝘂𝗶𝘀𝗶𝘁𝗲𝘀 𝘁𝗼 𝗰𝗿𝗲𝗮𝘁𝗲 / 𝗯𝘂𝗶𝗹𝗱 𝗘𝗖𝗦: To build an ECS that severs the CDM needs,

- One should have clear understanding of study protocol & eCRF data points collected.

- Data dictionary of the database (EDC) - this helps to understand the various attributes, definitions of the elements that are being used in database.

- Possible data entry scenarios & test data: This will help to create a correct edit checks to address all the possible data issues that can happen when study go live.

- List of critical data points such as study end points, AE / SAE data etc.

⭐ 𝗖𝗵𝗲𝗰𝗸𝘀 𝗶𝗻𝗰𝗹𝘂𝗱𝗲𝗱 𝗶𝗻 𝗘𝗖𝗦?

Based on the type, checks in ECS can be categorized into

a. Univariate checks (these checks only applicable to a single field or single variable ona eCRF.)

b. Multi-variate Checks (edit checks with more than one fields or variables involved.)

c. Programmed Checks (they will fire as soon wrong data is entered)

d. Manual Checks ( need to run manual programs on the data & output reports are analyzed for data issues)

Based on core function – checks that are included in ECS can be categorized into

1. Missing data & eCRF checks : these checks ensure all the critical data points & eCRF’s are collected as needed (Ex : Missing inform consent date / missing Vital sign forms etc

2. Range Checks & format checks: they raises a query when entered value is out of range or format - specified for data collection point (ex: height, weight dates, time etc

3. Checks for Duplicate data: These checks alerts sites / DM when duplicate data is entered. Ex: Entering same AE event twice

4. Protocol deviation checks : These are must have checks to flag PD’s
   
5. External Data Checks : These check will ensure data quality of external data such as labs data, ECG etc
   
6. Inconsistency across single CRF & other eCRF’s : These will check inconsistencies on the same eCRF form across eCRF forms.

⭐ 𝗪𝗵𝗮𝘁 𝘁𝗼 𝗮𝘃𝗼𝗶𝗱 𝘄𝗵𝗶𝗹𝗲 𝘄𝗿𝗶𝘁𝗶𝗻𝗴 𝗘𝗖𝗦?

1. Avoid complicate queries messages – this will hurt sites

2. Avoid placing too many edit checks in a form or visit

3. Avoid leading /probing/ or guiding participants enter any data point in a particular way.

4. Do not blindly copy checks from other / sister studies.

Comments

Post a Comment

Popular posts from this blog

Difference between central lab and Local Lab

-
 In the context of clinical trials, both central laboratories (central labs) and local laboratories (local labs) play essential roles in processing and analyzing biological samples. However, they differ significantly in their operations, advantages, and applications. Here’s a detailed comparison: ### Central Laboratory **Definition:** A central laboratory is a large, centralized facility that processes and analyzes samples from multiple sites participating in a clinical trial. These labs are usually equipped with advanced technology and staffed by highly trained personnel. **Key Characteristics:** - **Standardization:** Central labs offer standardized procedures and protocols, ensuring consistent and uniform testing across all samples. - **Quality Control:** They maintain stringent quality control measures, often accredited by recognized bodies (e.g., CAP, CLIA). - **Advanced Technology:** Equipped with state-of-the-art equipment and specialized assays, central labs can perform a w...
Read more

Detailed Overview of Patient Identifiers in clinical data overview

-
 Certainly! Here's a more detailed breakdown of the use of patient identifiers in clinical data review within clinical data management: ### Detailed Overview of Patient Identifiers #### Types of Patient Identifiers 1. **Direct Identifiers**    - **Name**: Directly identifies a person and is often replaced with a code in clinical trials.    - **Social Security Number**: Uniquely identifies an individual but is rarely used due to privacy concerns.    - **Contact Information**: Addresses, phone numbers, and emails are crucial for communication but are highly sensitive. 2. **Indirect Identifiers**    - **Date of Birth**: Can help identify a person, especially when combined with other information.    - **Gender**: Less specific but still helps in narrowing down identity.    - **Medical Record Numbers**: Used within healthcare systems to uniquely identify a patient but needs to be kept secure.    - **Health Plan Benefi...
Read more

study start up

-
Image
  STUDY START UP/STUDY SET UP: eCRF(case report form): The case report form is a printed or electronic questionnaire for collecting data from study participants and reporting it to trial sponsors. The document is created specifically for each research project in accordance with the trial protocol, and recommendations of the Clinical Data Acquisitions Standards Harmonization (CDASH). They are developed by Clinical Data Interchange Standards Consortium to streamline industry-wide data exchange. Say, CDASH dictates dd/mm/yy format for collecting dates. (Read our article on CDISC standards to learn more.) Well-designed case report forms collect only data necessary for the particular study avoiding any redundancy. The fields to be filled in may include demographics (age, gender), basic measurements (height, weight), vital signs (blood pressure, temperature, etc.) captured at various time points, lab exams, medical history, adverse events, and more, based on the research requirements....
Read more