Iaso
Iaso helps clinicians and patients recognize and navigate interventional options for severe cancer pain that persists despite escalating medication.
Core trick
Claude extracts source-cited facts from a clinician's narrative, while fixed versioned physician rules, not the model, decide which procedures merit specialist discussion.
Tags
Description
Iaso helps clinicians and patients recognize and navigate interventional options for severe cancer pain that persists despite escalating medication. A clinician enters the patient’s pain story; Iaso identifies procedures worth specialist discussion, explains why each may or may not fit, and directs the clinician to an appropriate local specialist. Once selected, Claude drafts an editable referral summary and focused clinical question. Patients receive a cited, plain-language atlas describing realistic benefits, limitations, and risks, helping them use limited consultation time effectively and participate meaningfully in treatment and informed-consent discussions.
Iaso is also an exploration of where AI belongs in high-stakes clinical care. Claude translates ambiguous narratives before a decision and explains results afterward, but does not make the clinical decision itself. Recommendations are governed by fixed, versioned, physician-authored rules. This deterministic safety harness keeps every criterion transparent and testable while reducing the risk that hallucinations or inconsistent model responses alter outcomes.
Both the clinical rules and referral network can be customized to an institution’s procedures, selection criteria, specialists, and workflows. In cancer care, a delayed or misdirected referral can consume precious time. Earlier, better-directed, better-prepared specialist conversations can protect what matters most: quality of life and meaningful time with loved ones.
README excerpt
# Iaso
**A clinician-guided cancer-pain procedure navigator and patient-education platform.**
A clinician describes a patient's dominant pain problem in plain narrative. Claude compiles that
narrative into transparent candidate facts — each tied to the exact source phrase, with uncertainty
and honest unknowns. Fixed rule simulation identifies which registered clarifications are material;
Claude orders that complete set and explains why each question matters. After the
clinician confirms the facts, **fixed physician-authored rules — not the model — surface the exact
procedures that may merit a specialist conversation**, or explain plainly why no implemented pathway
fits.
> **Technical thesis:** Claude handles ambiguity and communication; deterministic code protects the
> clinical decision and referral-routing boundaries.
> ⚠️ **Synthetic prototype.** Built for a hackathon. It accepts no real patient information, makes no
> clinical-outcome claims, and is not diagnosis, candidacy determination, treatment ranking, dosing,
> triage, or EHR software. Everything it surfaces is a *referral consideration for specialist
> discussion — never a candidacy determination.*
---
## The flow
```
narrative → live extraction → material clarifications → clinician confirms → rules speak → considerations → referral draft
(Claude, 4 axes) (code proves material; (nothing moves (pure TypeScript, (unranked, or an (Claude words an
verbatim quotes) Claude