Smart Data Quality (SDQ)
Clean Patient Tracker (CPT)
The Clean Patient Tracker gives study teams a real-time, subject-level view of data-cleaning status — so you can resolve issues early and shorten time to database lock.
One subject-level view of clean status
AI-Assisted Data Reviews is the foundation of Smart Data Quality. Advanced AI models, deployed directly inside SDQ, continuously scan incoming EDC and non-EDC data to identify discrepancies that would typically surface only through slow, sample-based manual review — then generate predefined query text ready for a data manager to approve.
As a clinical AI pioneer — SDQ was one of the first AI solutions in the pharmaceutical industry — Saama builds advanced AI and machine-learning models trained for clinical data. Applied to data review, they cut query generation from roughly 30 minutes to about 3 minutes per term, so your team spends its time on judgment, not detection.
Why teams choose the Clean Patient Tracker
A single source of truth
Consolidates SDV, coding, and missing-data checks in one dashboard instead of three systems.
Milestone-based
Turn on only the checks relevant to a given milestone and hide the rest.
Action-oriented views
Dedicated Missing Visit and Missing Form tabs show exactly where data is overdue.
Audit-ready
Every configuration and status change is written to the platform audit trail.
One dashboard
How the Clean Patient Tracker works
CPT tracks cleaning from configuration all the way to a green, clean status.
Define the criteria — SDV, coding, missing-data logic — that determine when a subject is clean.
EDC and non-EDC data flow in, and CPT tracks cleaning status across sites and milestones, detecting missing visits and forms using anchor-date windows.
Data managers work each line — Missing Data, On Hold, Queried, Escalated, or Closed — until all pending items are resolved.
Features
A bird’s-eye view of clean status per subject, pending issues, a six-month cleaning-trend graph, and data-quality metrics like time-to-entry and query turnaround.
User-defined milestones feed a confidence-score algorithm and a Likelihood of Meeting Milestone indicator.
A single location for missing visits and forms with multi-factor filters, CSV export, and threaded comments.
Per-criterion pending counts plus deep links into SDQ (Discrepancy Management, IRL, To-Do) and EDC.
Cleaning-criteria selection, custom subject status, coding and vendor dataset selection, and milestone setup — with the ability to inherit configurations from other studies.
Every configuration, status event, export, and comment is logged.
