Projects

bh-sentinel

Multi-layer NLP pipeline for detecting clinical safety signals in unstructured behavioral health text. Pattern matching with negation and temporal detection, ONNX transformer inference (zero-shot and fine-tuned), NRC emotion lexicon, and configurable rules engine. 40 clinical flags across 6 domains mapped to C-SSRS. Every flag includes evidence spans, basis descriptions, and confidence scores so clinicians can independently review. Designed for zero PHI egress and FDA Non-Device CDS compliance.

Two independently installable packages: bh-sentinel-core (deterministic, no ML dependencies) and bh-sentinel-ml (transformer layer). Text in, flags out, clinician decides.

bh-audit-schema

A canonical, versioned audit event schema for behavioral healthcare systems. JSON Schema with compliance mappings to HIPAA Security Rule (7 sections), SOC 2 Trust Services Criteria (4 controls), and 42 CFR Part 2 (2 sections). Defines the structure for what an audit event should look like in behavioral health.

bh-fastapi-audit

Pure ASGI middleware for emitting PHI-safe audit events from FastAPI applications. Non-blocking async emission, runtime schema validation with three failure modes, configurable DENIED outcome tracking with custom denial callbacks, schema version negotiation for gradual migration, and pluggable sinks. Compliant with bh-audit-schema v1.1.

bh-audit-logger

Framework-agnostic audit event emitter for any Python application. Built for Lambdas, workers, data pipelines, CLI tools, and anything that isn't FastAPI but still needs compliant audit logging. Zero required dependencies in core. Runtime schema validation available via optional extra. Full feature parity with bh-fastapi-audit.