Missing User Warnings
Medium
- Confidence
- 94% confidence
- Finding
- The skill instructs users to drop every row containing any missing lab value before harmonization, which can silently discard a large fraction of real-world clinical data and introduce severe selection bias. In healthcare analytics, this can distort cohorts, skew model training and evaluation, and remove clinically important partial records without user awareness, creating downstream patient-safety and research-integrity risks.
