← Back to the catalogue
WF-038 MASKED

Overreliance on a Flawed Prediction Model

Information
Failure pattern
Poor-quality predictive signals entering high-stakes clinical workflows.
Primary WEKID™ layer(s)
Information
Sector
Healthcare
Period
2017–2021
Decision-Matrix outcome
Remediation Required
Primary gate
Information validation; signal-quality review
Severity
High

What happened

A widely deployed sepsis-prediction algorithm was found in a peer-reviewed study to identify only about 63% of sepsis cases, generate many false positives, and often alert too late, while being embedded directly into clinical workflows.

Impact

Reassessment of sepsis-prediction tools and questions about local validation requirements.

WEKID™ insight

Information failure: poor-quality signals entered high-stakes workflows without sufficient local validation.

WEKID™ mitigation

Information-layer controls require local validation, calibrated alerting, and signal-quality metrics before a prediction is allowed to shape care.

MASKED  Named detail withheld

The masked badge stands in for a real, publicly documented organization. The full named organizations, individuals, sources, and timeline for this case are released in the WEKID™ Executive Brief.

Unlock the full record →

Updated: 2026-06-13