TrialTriage
Find eligible cancer trials in minutes, with a nurse's sign-off.
AI clinical trial matching for oncology nurses and insurers.
- Client
- TrialTriage
- Industry
- Healthcare / Oncology
- Region
- United States
- Engagement
- SaaS · multi-role (admins, nurses, patients, insurers) · Full-stack AI web application
TrialTriage helps oncology nurses match patients to clinical trials. Nurses enter de-identified patient data; the platform uses large language models, NCCN guidelines, and drug efficacy data to generate ranked trial recommendations. A nurse reviews and finalizes every result. Insurers can upload batch files for bulk processing. Built HIPAA-aligned, with full audit trails.
The problem we set out to solve.
Oncology nurses spent hours reviewing records, cross-referencing NCCN guidelines, and searching trials by hand.
No central system matched patients to eligible trials by cancer type, stage, biomarkers, and prior treatments.
Slow manual work delayed trial identification and risked missed enrollment windows.
Patient records, NCCN guidelines, drug databases, and trial data lived in separate systems.
Insurers had no automated batch eligibility processing.
Audit trails and de-identification for protected health information were insufficient.
What success needed to look like
- Nurses get ranked trial matches in minutes instead of hours of manual cross-referencing.
- Every recommendation stays under nurse review — AI ranks, humans finalize.
- Patient data stays de-identified and every action is auditable, aligned with HIPAA.
- Insurers can process trial-eligibility checks in batches, not one at a time.
How we delivered it.
01
Diagnose
Mapped how nurses manually cross-referenced patient records against NCCN guidelines and trial databases, and found where the search — not the eligibility decision — was consuming the hours.
02
Design
Designed the AI ranking pipeline so LLM-generated trial recommendations stay in a nurse review-and-adjust loop, plus the de-identification model (age ranges, ZIP prefixes, pseudo-patient IDs) and the insurer batch workflow.
03
Build
Built the platform on NestJS and PostgreSQL with Fireworks AI powering trial matching against NCCN guidelines and drug efficacy data, Redis-backed background jobs for insurer batch processing, and Socket.IO for real-time progress updates.
04
Launch
Shipped with session-based auth, TOTP multi-factor authentication, and a 23-action audit trail in place from day one, so the platform launched HIPAA-aligned rather than retrofitted for compliance.
05
Run
Kept extending the drug efficacy database and cancer-type hierarchy, and tracked AI usage analytics to keep matching accuracy under nurse oversight as volume grew.
What we built.
We built a cloud AI platform that brings patient records, NCCN guidelines, drug efficacy data, and clinical trial information into one place. Large language models generate ranked trial recommendations, and a nurse reviews, adjusts, and finalizes every one — so clinical judgment stays in the loop. The platform supports both individual assessments and insurer batch processing, with real-time progress over WebSocket and HIPAA-aligned compliance throughout. It tracks 23 audit action types and enforces role-based access for four user types.
Tech stack
Integrations
- Fireworks AI (LLM API)
- AWS S3 (file store)
- BullMQ (background processing)
- Socket.IO (real-time)
- Paubox (HIPAA email)
- Stripe
- SendGrid
Roles & access
- Admin
- Nurse
- Patient
- Insurer
Security
- Session-based auth with HttpOnly cookies
- TOTP multi-factor authentication with backup codes
- bcrypt password hashing
- Field-level PHI encryption and automated PHI masking
- Audit trail across 23 tracked actions
- HIPAA alignment
- Helmet.js, strict CORS, and rate limiting
In clinical matching, speed only matters if a human still signs off — we built the AI to rank fast and kept the nurse as the final decision-maker.
