Accelerate Your Data Review Processes - Today
Using the industry’s most advanced artificial intelligence (AI) models, Smart Data Quality (SDQ) gives study teams the power to manage the high volume and variety of today’s clinical trial data.
Experience the power of data review automation
Saama is the undisputed leader in AI for life sciences, with over 90+ models trained on over 300 million data points. SDQ automates data review processes, reducing query generation times from 30 minutes to just 3 minutes per query.
Benefits
Automate data
review processes
Use AI modes to automatically identify discrepancies and generate queries. Eliminate manual reviews, reduce errors, and minimize trial delays.
Accelerate time to
database lock
SDQ helps keep data clean in real-time, reducing the time from last patient last visit (LPLV) to database lock (DBL).
Reduce time to
issue a query
With SDQ, data discrepancies are automatically identified as they are captured, reducing time to issue a query from over 25 days to under 2 days.
Scalable across
your portfolio
Built on a cloud-based architecture backed by AWS, SDQ is scalable across your portfolio and is proven on large, global mega trials.
Traditional
Manual Data
Review Process
Days
Resources
27 min
To manually review and write a query.
2,615
Queries
1,177
Hours
Smart Data Quality
Automated Data
Review Process
Days
Resource
3 min
To review and approve AI generated query.
2,615
Queries
130
Hours
How AI is Applied
Saama has 90+ AI models trained for life sciences on over 300 million data points. These models are deployed within SDQ to identify data discrepancies, automatically.
See how Saama reduces query times from 30 minutes to 3 minutes.
“(SDQ) saved us an entire month. It really has had a significant impact on the first-pass quality of our clinical data and the speed through which we can move things along and make decisions.”
Head of Data Monitoring
Top 3 Global Pharmaceutical Company
Features
Accelerate your trials while maintaining clean, high-quality data.
Advanced AI models automatically identify data discrepancies that would typically only be caught by manual data reviews.
Review data listings manually and perform advanced data review in a single location. Users can review pre-built listings or create custom listings using generative AI, and can even assign tasks to team members and vendors.
SDQ’s self-service rule builder allows users to code data quality (DQ) checks directly within SDQ and reuse them across studies. DQ checks can be coded once and used across multiple source systems and work in conjunction with AI-driven checks.
DQ rules can be created and saved as part of a catalog for reuse. Users can apply these rules at the study level and see how they were applied in previous studies.
Complete data review from a single location. See summary of DQ and AI-driven checks, view source data, and pre-generated query text – all on the same screen.
For each data discrepancy, SDQ pre-generates a query response. Easily review and edit query text before sending it back to the source system.
Review each AI-based or rules-based DQ check, along with the source data, to quickly approve or reject queries. Users can edit the pre-generated query text before approving it and sending it back to the source system.
Review query responses and details directly within SDQ when connected to standard EDC systems with an API (e.g., Inform, Veeva, Medidata). View the full query trail and conduct full, end-to-end query workflows.
If SDQ identifies a data discrepancy – but the issue is fixed in the source system before the data manager reviews it – SDQ automatically closes the auto-generated predictions, reducing duplicate queries.
Approve or reject data quality checks in bulk with a few clicks, saving thousands of hours for data managers.
Go directly to the source eCRF with a single click from the prediction page, improving efficiency and streamlining workflows.
SDQ’s AI models improve over time and become more accurate with use, with regular model retraining to incorporate user inputs.
Users can check for missing or incorrect data from third-party vendors, and track responses manually within SDQ. Once the vendor fixes the data, it’s automatically updated within SDQ.
Users can view which data quality checks have been fired and which have failed, as well as the data ingestion status from Data Hub.
