OncoSignal · Vertical AI for Oncology · Pre-Seed

Every patient deserves a top oncologist's care.

A clinical decision companion for practicing oncologists — bringing the right answer within reach of every patient.

The problem

The same patient, different prescriptions — depending on the oncologist they meet.

The gap is not in competence. It is the structural limit of time, knowledge, and memory.

Why prior attempts died

Trust is decided not by the average —
but by the worst case.

95 / 100
correct recommendations
5 dangerous
answers end clinician trust
in the system — completely.

One widely publicized oncology AI achieved 87.9% concordance with experts¹ — and still failed. Failure didn't come from the technology. It came from the asymmetry of trust.

What we guarantee

Four guarantees,
built into the system from day one.

01

Every recommendation comes with verifiable sources.

Every clinical claim links to a primary paper or authoritative guideline. The clinician verifies in one click — never accepts on faith.

02

When evidence is insufficient, the system stays silent.

Plausible-sounding answers never appear. The system explicitly states “insufficient evidence” — freeing the clinician from hallucination risk.

03

Nothing appears that isn’t in the patient’s record.

If a mutation isn’t in the clinician’s input, the system never assumes it. Only the clinician’s own facts ground every output.

04

No definitive diagnosis or prescription.

Output is always presented as options and considerations. The final judgment remains the clinician’s — authority is never displaced.

Input · How clinicians use it

One line.
Or fifty fields. Both work.

Mode A · Natural

Paste the whole case.

History, symptoms, labs, imaging, molecular results — in plain prose. The system extracts the structure automatically.

Example input

“62 y/o male, right hemicolectomy 3 yrs ago. Recent CT shows multiple liver lesions (S6, S8), suspicious for mets. CEA 73.9 ng/mL (rising). KRAS G12C positive, MSS, HER2 negative. ECOG 1, eGFR 75. Progression after 1L — need 2L options.”

Mode B · Structured

Enter precise fields.

35+ clinical parameters — every variable the case warrants:

  • Cancer type · Stage · Age · Sex · Ethnicity
  • Mutations · MSI · HER2 · TMB · PD-L1
  • ECOG · Treatment line · Renal & hepatic function
  • Drug history · Comorbidities · Metastasis sites
  • Symptoms · Biomarkers · Routine lab panels
Patient companion

Not a one-off answer —
a companion through the patient’s entire course.

Most medical AI answers once and forgets. OncoSignal accumulates, remembers, and adapts.

01

Private clinician accounts

Each clinician’s patient records are accessible only to them. Identifiers are scoped to the account.

02

One patient ID, one timeline

Every analysis for one patient stacks chronologically: diagnosis, 1L decision, follow-up scans, RECIST response, progression, 2L decision.

03

Recommendations evolve with the patient

Each new lab, scan, or RECIST result updates the recommendation. Next-line candidates, dose adjustments, matching trials all refresh on history.

04

Patient-level search and recall

“What did I see for this patient last year?” One patient ID unfolds the full history. The system supplements clinical memory.

Why now

Three forces have created the moment
for vertical clinical AI.

01

Safe AI is finally possible.

Reliably refusing to answer when evidence is insufficient — without losing utility — has only become technically tractable in the last 12-18 months. The architectural primitives didn’t exist before.

02

The market is actively searching.

82% of healthcare professionals trust clinical AI’s potential — but only 26% actually use it². That 56-point trust-usage gap is the demand pool waiting for a system worth adopting.

03

A generational shift in reference tools.

Manually edited reference databases can no longer keep pace with the literature. The shift from manual curation to AI-synthesized clinical reference has already begun.

Market

A fast-growing market
— with an empty seat at the top.

$5.4B → $49.5B³
AI in oncology, global · 2026 → 2036 · CAGR 24.8%
$2.8B → $15.3B
AI clinical decision support · 2025 → 2033 · CAGR 20.89%
Comparable general medical AI
$6B
OpenEvidence
$12.8B
Tempus AI

Neither is purpose-built for the oncology decision workflow. The vertical seat is open.

Short term to long term

Companion now.
Beyond knowledge, time, and memory — later.

Year 1-2

Companion validation

Real-world use by practicing oncologists. Embedded in the visit. Information-only — clear of medical-device regulation.

Year 3-5

Clinical data accumulation

With user growth — under anonymization and consent — a feedback loop forms: which recommendations were taken, which outcomes followed.

Year 5-7

Specialty-tuned clinical AI

Models tuned on accumulated data deliver patient-specific support — beyond simple search and synthesis.

Year 7+

Regulated diagnostic AI

Once trust is sufficiently earned, formal medical-device approval (FDA / MFDS / CE) — from information to diagnostic AI.

Approval is not the starting point — it is the result of trust sufficiently earned.

What we stand for

Every prescription —

delivered safely.

accurately.

at its best.

Request access

For practicing oncologists
building the future of evidence-disciplined clinical AI.

Closed beta opening soon. Priority access for medical oncologists across solid-tumor specialties. Additional tumor types added on a rolling basis.

Email
Role
Primary tumor focus (optional)
We will only contact you about beta access. No marketing.
✓ Thank you. We will be in touch as the beta opens.

¹ Independent concordance evaluation, Manipal Comprehensive Cancer Centre (peer-reviewed, 2018).   ² Wolters Kluwer Health Clinician AI Survey, 2024 — 1,000+ U.S. clinicians.   ³ ResearchAndMarkets, AI in Oncology — Global Forecast to 2036 (May 2026).    DataM Intelligence, AI-CDSS Market (Feb 2026).    OpenEvidence valuation, 2025.    Tempus AI public valuation, 2024.