Inter-rater agreement on adverse event grading today, kappa 0.59 to 0.68 (Hong et al., 2020). Independent investigator-assigned attributions are changed by central review 31 to 36 percent of the time (Hillman et al., Journal of Clinical Oncology, 2010). The 2019 FDA-NCI workshop characterized the current state of oncology adverse event attribution as sub-optimal, unreliable, inefficient.
The standard the field deserves is real-time, citation-bound, and defensible. Burna is building that standard. A platform that does the grading and citation work a person would do with unlimited time, and hands the finished, cited, attributed, audit-ready result to a clinician for review and signature. The work is compressed. The clinician is preserved. Human-in-the-loop, always.
Burna AI is the safety and data quality platform for oncology drug development, from clinical trials through postmarket surveillance. Two product lines on one engine. CTCAE AI for cancer centers, academic medical centers, and CROs running oncology trials. Protocol Safe for pharma sponsors who need an isolated AI environment for protocol-aware adverse event attribution inside their own cloud. Same engine, two deployment shapes, one evidence spine.