Page Comparison

Interested in joining one of the Data Transparency Emerging Trends & Innovation Working Group Projects? The projects below are currently calling for welcome new volunteers.

Project Scope:

Project Scope:

This project aims to develop a new template or enhance an existing one such as the Study Data Standardisation Plan (SDSP) or Analysis Data Reviewer’s Guide (ADRG), to ensure that metadata pertaining to the versions of statistical packages and procedures is consistently documented in alignment with health authority expectations. This standardised template will streamline the submission of clinical study metadata to health authorities as part of the regulatory review process.

Current Status:

• Continue FDA Engagement

• Finalise Metadata Approach

• Onboard New Team Members

• Develop Project Plan

The use cases of artificial intelligence and machine learning (AI/ML) in digital health technologies to improve healthcare through software.

Understand the challenges, and identify the gaps. Connect different stakeholders, share knowledge, and advance in developing AI/ML in DHTs.  

Current Status:

• Q1 2025 Forum with proposed date and speaker

Regular Project Meeting Day/Time:

• Bi-weekly: Wednesdays 7-8pm Meetings every two months on Mondays 18:00-19:00 GMT

Key Skills:

• Experience in statistical programming language

• Experience in processing metadata

(currently being reviewed by WG Leads)

• Experience with the use of DHTs

• Experience with AI/ML

Project Scope:

Comparing Analysis Method Implementations in Software (CAMIS) has evolved from the Clinical Statistical Reporting in a Multilingual World project.

Several discrepancies have been discovered in statistical analysis results between different programming languages, even in fully qualified statistical computing environments. Subtle differences exist between the fundamental approaches implemented by each language, yielding differences in results which are each correct in their own right. The fact that these differences exist causes unease on the behalf of sponsor companies when submitting to a regulatory agency, as it is uncertain if the agency will view these differences as problematic. Understanding the agency’s expectations will contribute significantly to enabling the broader adoption of multiple programming languages in the production of data submission packages for regulatory review

The CAMIS project seeks to clearly define this problem and provide a framework for assessing the fundamental differences for a particular statistical analysis across languages. In this context, the risk of interpreting numerical differences in analysis results due solely to differences in programming language can be mitigated, instilling confidence in both the sponsor company and the agency during the review period. This will be accomplished by:

1. Identifying common statistical analyses performed during submissions to narrow the scope of where discrepancies must be identified (e.g., continuous summaries, frequency counts, hazard models, bioequivalence testing, steady-state assessments, bioavailability testing, ANOVA)

2. Providing necessary documentation to produce equivalence in results between separate statistical analysis software packages/languages (where possible)

3. Evaluating and documenting differences in results between popular statistical analysis implementations as use cases

4. Provision of sample code for use cases through a publicly accessible code repository for both review and consumption

5. Promoting the notion that the ‘right’ implementation of a particular statistical analysis should be based sound statistical reasoning and not limited by the capabilities of a specific programming language or statistical analysis software package, nor its default settings

The CAMIS repository to document known differences is now live and open for community contributions. 

Current Status:

• Review repo environment and assess costs to improve.

Regular Project Meeting Day/Time:

• Bi-weekly: Mondays 4:30-5:30pm GMT

Key Skills:

• Experience in statistical programming languages (SAS, R, Python)

• Experience with statistical methodology in different software and languages

• Familiar with using Github

Increasing interest in eSource keeps the issue of data integration between Research Systems (EDC, CTMS, CDMS, etc) and healthcare systems (EHR, etc) as a consistent want for Sponsors of Clinical Investigators and Regulators. Previous efforts to make this a repeatable, scalable solution have not met with wide-scale adoption, for a variety of reasons.

Some common historical points of view have included:

• That the quality of the data that can be retrieved from the Healthcare sites is insufficient to meet research needs.

• That uptake of electronic systems at investigative sites has been slow, expensive, and not delivering real value to healthcare practises.

• Types of data captured in healthcare have been more operational rather than clinical.

• Enabling the Necessary interfaces is an expensive and process-heavy undertaking.

• There is not a suitable, generally supported electronic exchange format, with a number of standard representations being supported in recent memory.

Many of these issues are on the path to being resolved; government programs have pushed the adoption and accessibility of electronic health records. In addition, there are a number of stakeholders in the Research Industry that are making the use of healthcare resources a priority for the future; examples include Transcelerate eSource initiative and HL7 Vulcan Accelerator.

Current Status:

• Jan 25 Connectathon PoC with SDC.

Regular Project Meeting Day/Time:

• Calls have moved over to Vulcan, which the Lead will add you too.

Key Skills: (currently being reviewed by WG Leads)

• Experience with HL7 Vulcan

• Experience with

• FHIR

• Experience in

• writing Use Cases