Veritas-RPM: Provenance-Guided Multi-Agent False Positive Suppression for Remote Patient Monitoring
For healthcare providers using remote patient monitoring, this system reduces alert fatigue by accurately filtering false alarms.
Veritas-RPM uses a provenance-guided multi-agent architecture to suppress false positives in remote patient monitoring, achieving a True Suppression Rate of 92.5% and a False Escalation Rate of 3.1% on 530 synthetic patient epochs.
We present Veritas-RPM, a provenance-guided multi-agent architecture comprising five processing layers: VeritasAgent (ground-truth assembly), SentinelLayer (anomaly detection), DirectorAgent (specialist routing), six domain Specialist Agents, and MetaSentinelAgent (conflict resolution and final decision). We construct a 98-case synthetic taxonomy of false-positive scenarios derived from documented RPM patterns. Synthetic patient epochs (n = 530) were generated directly from taxonomy parameters and processed through the pipeline. Ground-truth labels are known for all cases. Performance is reported as True Suppression Rate (TSR), False Escalation Rate (FER), and Indeterminate Rate (INDR).