Limbus AI is a health technology startup building AI-powered clinical decision support for psychiatric assessment. Founded by Dr. Marie Claire Bourque, MD, FRCPC, a board-certified psychiatrist, Limbus addresses the critical 2+ year wait for psychiatric assessment across Canada.

Our flagship product is a Diagnostic Avatar — an AI system that conducts comprehensive psychiatric assessments via video, administering validated screening instruments and structured clinical interviews. A deterministic Bayesian diagnostic engine (not LLM inference) processes 75 calibrated likelihood ratios across 22 psychiatric and medical conditions, producing CPSBC-compliant assessment reports.

The system has achieved 87% diagnostic concordance with expert psychiatrist assessments across 46 validated cases. Key safety features include 12 halt conditions for crisis detection, an 11-module validity assessment engine, and complete audit trails for every diagnostic decision.

Our technology stack includes Python/FastAPI, React, PostgreSQL, Anthropic Claude (for interviews only — not for diagnostic reasoning), and Tavus video avatars with multimodal emotion perception. We are pursuing Health Canada Software as a Medical Device (SaMD) Class II classification under IEC 62304 and ISO 14971.

Limbus AI is headquartered in British Columbia, with planned expansion to Ontario and Alberta.

Limbus AI has demonstrated 87% diagnostic concordance with expert psychiatrists across 46 validated cases. For Health Canada SaMD Class II approval and provincial health technology assessment (HTA) reimbursement, rigorous prospective validation evidence and health economic analysis are required. This project produces all clinical and economic evidence needed for regulatory approval and provincial adoption.

The intern will work across three integrated workstreams:

Workstream A — Prospective Diagnostic Accuracy Study: Design and execute a prospective validation study comparing AI-generated psychiatric assessments against gold-standard expert evaluations across 500+ cases. Establish sensitivity, specificity, PPV, NPV, and diagnostic concordance rates for each of the 22 tracked conditions. Compute agreement statistics (weighted kappa) stratified by condition severity, demographic subgroups, and comorbidity patterns. Develop the statistical analysis plan, manage data collection protocols, and produce the clinical evidence report required for Health Canada SaMD submission.

Workstream B — Cost-Effectiveness & Budget Impact Analysis: Build a decision-analytic model comparing AI-assisted psychiatric assessment versus standard-of-care waitlist pathways. Estimate incremental cost-effectiveness ratios (ICERs) from the perspective of provincial payers (BC MSP, OHIP, Alberta Health). Construct budget impact models projecting 5-year fiscal impact of AI adoption at provincial scale. Conduct probabilistic sensitivity analyses and scenario modeling across adoption rates, pricing models, and patient volumes.

Workstream C — Provincial HTA Submission Packages: Synthesize clinical and economic evidence into structured submission packages aligned with requirements of BC HTAC, Ontario Health Technology Advisory Committee (OHTAC), and Alberta HTA. Include systematic literature reviews, clinical evidence summaries, economic evaluations, and equity/access impact analyses.

Deliverables: Validated diagnostic accuracy dataset (500+ cases), clinical evidence report, cost-effectiveness analysis with budget impact models for 3 provinces, 3 HTA submission packages, and 2 manuscript-quality publications.