SMARtCARE: Privacy-Preserving Agentic AI Systems for Bounded-Autonomy Clinical Decision Support

2026-09-24

AI Summary

This study addresses the tendency of long-context clinical AI systems to overlook historical medical records and misinterpret early vital sign drifts in intensive care units. To mitigate these issues, we propose a four-state constrained autonomous decision support architecture. The method employs six-channel lossy fingerprinting to match historical trajectories, retrieving complete records exclusively under physician-in-the-loop collaboration. By integrating metacognitive upgrading with a patient identity guard mechanism, the system explicitly surfaces intermediate contextual risks while preserving privacy. Validation using the MIMIC database and Monte Carlo simulations demonstrates that the proposed framework accurately identifies recurrence patterns and supports comprehensive audit trails. Ultimately, this work effectively reconciles privacy preservation with interpretability in clinical decision-making.

Abstract

Long-context clinical AI systems can miss relevant patient history when prior admissions fall outside the active reasoning context. In ICU monitoring, this can cause early vital-sign drift to appear nonspecific even when it resembles a prior deterioration pattern. SMARtCARE addresses this gap through a four-state clinical decision-support architecture: Stable, Meta-cognitive, Assisted, and Regulated (Revoked). Rather than automatically retrieving prior records, SMARtCARE uses a lossy six-channel fingerprint of the patient's prior trajectory. When current drift matches that fingerprint and the prior record is absent from context, the system raises a Meta-cognitive escalation for clinician review; full retrieval occurs only through clinician action in the Assisted state. A patient-identity guard is designed to enforce correct attribution across data loading, logging, and audit layers. Evaluation combines a synthetic Monte Carlo study that validates the state-transition logic and estimator stability, not clinical performance, with real-data runs on both the MIMIC-III and MIMIC-IV Clinical Database Demos. On MIMIC-III, one prior-pattern recurrence was identified among 14 two-admission patients; on MIMIC-IV, the same pipeline produced no fingerprint matches among 9 two-admission patients, which illustrates a key limitation of a fixed canonical pattern library. Across both runs all logged decisions were fully traceable and correctly attributed. The results support SMARtCARE as a traceable, privacy-aware mechanism for surfacing middle-context risk; they are not a clinical efficacy claim.

Problem

• clinical decision support
• long-context AI
• patient history retrieval
• privacy preservation
• ICU monitoring

Innovation

• Privacy-Preserving
• Agentic AI
• Bounded-Autonomy
• Clinical Decision Support
• Meta-cognitive Escalation