Loading...
Validation readouts. CTCAE v6.0 explainers. Architectural deep-dives. The conversations we have with research directors, safety medical officers, and the regulators who review our work, published.
FeaturedProduct Updates · 6 min read
Most of the variance in adverse event grading does not come from disagreement about what Grade 2 nausea looks like. It comes from disagreement about whether a given event is treatment-emergent, a comorbidity flare, or both. This week we put more of that context into the grading flow.
Long-form essays on the engine architecture, validation readouts, industry analysis, and the archive of Clinical Intelligence Weekly. Most readers subscribe to the newsletter; everything also lives here.
Most clinical trial software treats the protocol as a PDF to attach somewhere and forget. We think that is a missed opportunity. The protocol is the trial; everything that gets graded, queried, or audited downstream traces back to what the protocol says.
Most product weeks are about adding things users can see. This one was about replacing the plumbing underneath what they already use, so the things they care about feel faster, more consistent, and easier to extend.
Most clinical AI treats patient-reported outcomes as a separate track: the patient answers a questionnaire, the score sits in a table, and someone downstream translates it. This week we closed that gap by running PRO-CTCAE submissions through the full grading pipeline.
Generic CTCAE criteria are a starting point. The protocol, the investigator brochure, and the institution's own guidelines are the real source. This week we made the platform read all of them, and weigh them during grading.
Every cancer center has its own grading conventions. This week we built the mechanism for institutions to encode their own preferences into the AI's grading reasoning, expanded EHR data coverage, and made severity the default ordering for adverse event review.
Three repeated administrative burdens consume coordinator time: regulatory paperwork, manually titling and summarizing visits, and tracking multi-site trial operations. This week we automated all three.
Coordinators told us the most time-consuming part of adverse event documentation is not the initial grading. It is the follow-up: attribution analysis, interaction review, and the report compile. This week we eliminated the multi-step burden by connecting the analysis into one pass.
Coordinators spend a surprising amount of time moving data between systems and resolving grading disagreements one at a time. This week we collapsed both of those flows, and we doubled the vocabulary the synonym mapper recognizes.
CTCAE grading accuracy depends on context. A peripheral neuropathy finding means something different in a patient with Type 2 Diabetes than in a patient without prior neurological history. This week we shipped four capabilities that bring the right clinical context into the grading workflow.