Smart Data Quality (SDQ)

Smart Data Quality (SDQ) by Saama is an AI-powered clinical data review platform designed to help study teams manage the high volume and variety of data generated in modern clinical trials. Leveraging more than 100 AI models trained exclusively for life sciences, SDQ automates data review processes and dramatically reduces query generation times — from 27 minutes per query with traditional manual methods down to just 3 minutes using AI-generated queries.

SDQ is purpose-built for data managers, medical monitors, clinical programmers, and study managers who need to maintain clean, high-quality trial data while accelerating timelines. The platform has demonstrated measurable impact in large, global trials, with one Head of Data Monitoring at a top-three global pharmaceutical company noting that SDQ saved an entire month and significantly improved first-pass data quality and decision-making speed.

Key Benefits

• Automate data review processes: AI-powered models eliminate manual reviews, reduce errors, and minimize trial delays.
• Accelerate time to database lock: SDQ keeps data clean as it is collected, speeding the path to database lock.
• Reduce time to issue a query: Automatically identify data discrepancies and generate queries, cutting review time from 47 days and 3 resources to 16 days and 1 resource for the same volume of queries.
• Scalable across your portfolio: Built on a cloud-based architecture backed by AWS, SDQ is proven on large, global trials and scales across an entire study portfolio.

Core Features

• AI-assisted data reviews: Advanced AI models automatically identify data discrepancies that would typically only be caught through manual review, and generate predefined query text to accelerate resolution.
• Interactive review listings: Users can review pre-built data listings or create custom listings using generative AI, perform advanced data review in a single location, and assign tasks to team members and vendors.
• Integrated rule builder: A self-service rule builder allows users to code data quality (DQ) checks directly within SDQ, reuse them across studies and multiple source systems, and combine them with AI-driven checks.
• Data quality Co-Pilot: Users describe a desired DQ check in plain language, and SDQ automatically writes and tests the code using generative AI trained on proprietary historical DQ check data.
• Discrepancy management: Track, review, and take action on all queries in one centralised location, regardless of their source.
• Blinded/Unblinded integration: Automatically captures data masking configurations from Data Hub to SDQ, ensuring secure and precise data management throughout the trial.
• Clean patient tracker: Track data-cleaning status and missing data at the patient level, with fully configurable and reusable milestone readiness views.
• Query anomaly detection: Leverages generative AI to uncover unknown data patterns and anomalies that might otherwise be missed during standard review.
• Integrated Data Review Assist (IDRA): Provides a unified process to create, collaborate on, and approve the data review plan, connecting DQ checks, interactive review listings, subcategories, and listings into a structured workflow.
• Protocol Deviations: Enables collaborative review and management of both query-based and non-query-based protocol deviations within SDQ to prevent duplicate protocol deviations.

Deployment and Integration

SDQ is part of Saama's Clinical Data Foundation and integrates with Data Hub for seamless blinded and unblinded data management. The platform is hosted on a cloud-based AWS infrastructure, making it scalable for organisations running large, complex, global clinical trials. SDQ works in conjunction with Saama's broader AI Clinical Analytics platform, supporting end-to-end clinical data quality and operational efficiency.