Loading...
We believe every cancer patient deserves care that's as precise as it is compassionate. Burna AI exists to make that possible, by giving clinical teams the intelligence they need, exactly when they need it.
Burna grades adverse events with the evidence attached and ships both the CTCAE grade and the MedDRA LLT code on every encounter, from clinical trials through postmarket surveillance. Site queries resolve on first read. Trials close on time. The downstream is better cancer care, for every patient.
“The prospective real-time design eliminates the de-identification burden that killed every retrospective AI study I have seen in this space. That is the right way to prove workflow value.”
“The validation endpoints I co-designed for Burna are the endpoints I would have wanted to see as a sponsor’s CMO before pilot kickoff. Pre-registered, peer-reviewed, paired-grader timing. The science is the procurement asset.”
“Citation-bound output is what makes oncology adverse event attribution defensible at the regulator’s desk. With the source sentence and the CTCAE criterion inside the audit envelope, the reviewer reads the evidence, not the inference.”
A coordinator opens a patient encounter. Burna has read the clinical note, the labs, the medication list, the prior cycles, and the regimen protocol. Adverse events surface with the source sentence highlighted, the CTCAE criterion quoted, and the WHO-UMC or Kramer attribution path surfaced. The clinician reviews, modifies if needed, signs. The signed record flows into the EDC or the postmarket ICSR workflow. Every step is audit-ready.
Clinical note, labs, medications, prior cycles, and the regimen protocol, all in the working context.
Every suggested grade arrives with a source sentence, a CTCAE criterion, and a named attribution path.
The coordinator modifies or approves. 21 CFR Part 11 e-signature trail captured automatically.
Signed grades land in Medidata, Veeva Vault, Oracle Clinical One, or the postmarket ICSR workflow.
AI suggests. Clinicians decide. Human-in-the-loop, always.
TODAY 09:14
Grade 2MedDRA · 10052015NEW
Fever with hypotension responsive to fluids
Low-flow oxygen support
VISIT TRAJECTORY
CITATION PATH
ATTRIBUTION PATH
Monday morning in a cancer trial unit. The senior coordinator opens her queue. Six adverse events landed over the weekend. Each one arrives with the source sentence highlighted, a suggested CTCAE grade, and the attribution path already worked out. She reads. She agrees on five. She modifies one: the patient’s nausea is Grade 2, not Grade 1, and her reasoning is logged with the edit. She signs. The audit trail is built before the monitoring visit. She leaves at five.
By the third week of pilot, the work feels different. The fifteen-to-twenty minutes she used to spend reconstructing attribution for a single adverse event compresses to under three. The new coordinators on the floor are grading consistently from their first cycle, because the reasoning they need is on screen, not in someone else’s notebook. The senior coordinator is reviewing their work, not redoing it.
The medical executive who reviews the unit’s grading consistency dashboard sees cross-site agreement up since pilot start. The CFO sees query closure compressed and database lock arriving earlier. The PI sees every attribution carry its named-algorithm reasoning. The regulator who reviews the IND annual report sees cleaner safety data than last year. The downstream is better cancer care, for every patient.
The downstream is better cancer care, for every patient.
“She agrees on five. She modifies one. She signs.”
WHO-UMC and Kramer attribution. Multi-drug oncology, not single-drug lookup.
CTCAE v5.0 and v6.0, each carrying its MedDRA v28.0 LLT code (see /meddra-coding). The trial database and pharmacovigilance get what they need in one pass.
Cross-site grading inconsistency surfaces while the trial is running, not at the next monitoring visit.
Four numbers shape the safety and data quality work in oncology drug development today. Burna closes each with architecture, not workflow patch.
Of adverse event queries are confirmation requests, not data corrections. The answer was already in the file (Pronker et al., 2011).
Of investigator-assigned attributions get changed by central review, because the reasoning was not visible (Hillman et al., 2010; Le-Rademacher et al., 2017).
Per oncology trial in query labor, of which roughly 85% is structurally avoidable (Oracle ClearTrial, 2021).
The FDA-NCI 2019 workshop characterization of the current state of oncology adverse event attribution.
Burna closes all four gaps. With one platform.
Oncology safety is the work of many roles. Burna is built for all of them.
Three minutes per adverse event, not seventeen. Source sentence, CTCAE criterion, and attribution arrive with every suggestion. You sign.
For Clinicians and CoordinatorsYour voice is part of your care. Burna makes it easier to share, in your own words, in your own language.
For Patients and FamiliesRun the next two hundred trials without breaking the audit trail. Citation-bound grading, real-time across every site, with the 90-day pilot risk-reversed.
For Cancer Trial DirectorsAttribution decisions defensible at the point of clinical encounter. Protocol Safe deploys inside your cloud. The signal flows out; the protocol stays in. Also for pharmacovigilance teams: see /pharmacovigilance for the PV-team architecture conversation.
For Pharma and BiotechSMART on FHIR. Fits inside Epic and Oracle Health. No new infrastructure to stand up.
For IT and SecurityFaster grading. Cleaner data. Your sponsors notice. Burna runs across every site in the trial.
For CROsThe four we hear most often. The full FAQ has the rest.
Read the full FAQ →The previous generation of clinical AI in oncology failed on three architectural choices: broad scope, opaque reasoning, and autonomous decision-making. Burna is the opposite shape on every axis: narrow (CTCAE grading and multi-drug attribution only), transparent (citation on every grade), human-in-the-loop by design, and unified across clinical trials and postmarket on the same platform. The architectural shape is the lesson learned from what came before.
Those systems manage the case after attribution. Burna helps investigators and safety teams make the attribution decision upstream, while the source note, CTCAE criterion, regimen profile, and named algorithm are still visible together.
Patient identifiers stay inside your network in on-premises deployments and inside your jurisdiction in regional cloud deployments. The grading model only sees de-identified clinical text. Architecture diagram and data flow documentation available for your CISO inside a 5-page brief.
No. Burna is a clinical decision support tool. Clinicians approve every output. The platform does not prescribe, modify dose, or alter care pathways. 21 CFR Part 11, SOC 2, HIPAA, and GDPR aligned.
The 90-day pilot ships on the pilot outcome terms. In success, your unit gets citation-bound CTCAE grading inside the EHR, the labor recovery the platform was scoped to produce, and a peer-reviewed manuscript with your unit as primary authors. If the pre-registered endpoints are not met, the contract terminates with no further fee, and your unit retains the deployment, the training materials, and the co-authored manuscript. Either way, your team publishes.
The 2026 design partner cohort accepts pilot scoping conversations through the end of Q3 2026. Pilots that begin in Q4 2026 ship co-authored manuscripts in late 2027.
Scoping conversation runs fifteen minutes. The Overview Brief reads in five.
Subscribe to the quarterly safety and data quality briefing. Validation readouts, platform updates, and conference timing only. No tracking beacons, no marketing email cadence.