OncoSphere AI reads a patient’s outside records and produces one structured workup that brings each specialty’s perspective together: radiology, pathology, medical, radiation and surgical oncology, clinical trials, palliative care, and pharmacy. Each section shows its sources, and the physician reviews and edits it before it is used.
The workflow
- 1. Ingest. Paste a case summary or upload records (pathology, imaging, genomics). OncoSphere AI structures the heterogeneous, longitudinal data into a clean case.
- 2. Analyze each specialty. Each specialty perspective is analyzed against current guidelines and the latest literature.
- 3. Synthesize. The platform assembles the findings into one integrated workup, with alternatives and areas of uncertainty made explicit.
- 4. Verify. Every section surfaces its citations and notes on uncertainty, so the physician can trace each point to its source and decide.
The specialty perspectives
Medical Oncology
Systemic therapy options, guideline-anchored regimen selection, and rationale tied to the patient’s stage, biomarkers, and prior lines.
Radiation Oncology
Indications, target/technique considerations, and follow-up, aligned to guideline criteria.
Surgical Oncology
Resectability assessment and procedure considerations against guideline and AJCC criteria.
Pathology
Histology, IHC, and molecular findings — reported exactly as documented, including negatives that rule out targeted therapy.
Radiology
Imaging interpretation, measurements, and AJCC/RECIST-aligned staging.
Pharmacy
Dosing, preparation/administration, interactions, and supportive-care guidance.
Clinical Research
Trial concepts and eligibility considerations matched to the case.
Palliative Care
Symptom-management considerations, goals-of-care discussion triggers, and early-referral options — framed as considerations for the treating clinician, never directives.
Alongside the specialty perspectives, every case also includes two always-on care layers: Nurse Navigation — a care-coordination checklist and intake worksheet to keep the plan moving — and Patient Education, a plain-language summary written for the patient.
Adaptive by design
System telemetry from the ASCO 2026 validation showed adaptive compute behavior: the platform autonomously allocated 1.73× more reasoning to complex, refractory cases than to standard scenarios — spending effort where the case warrants it.