Unlearn.AI

#ICYMI: 🎉 Unlearn is excited to partner with SOLA Biosciences on an early-phase ALS study of SOL-257, supported by our AI-generated #digitaltwins. We're grateful for the opportunity to help advance clinical research for people living with #ALS. Read the full announcement: na2.hubs.ly/H04kxv_0

Every iteration of a protocol before finalization has a cost: evidence refresh, assumption reconciliation, and cross-functional realignment. For study teams, it's felt as time. For portfolio leaders, it has a dollar equivalent that compounds across every avoidable loop, before a single patient enrolls. We put a number on it. na2.hubs.ly/H04kwYy0

🎯 Predicting trial outcomes is getting harder, and the tools most teams rely on weren’t built for this. As patient populations narrow and standards of care shift faster than trials can read out, the assumptions underlying #trialdesign are increasingly built on shaky ground. Part 1 of our 2-part series breaks down why outcome prediction has become the hardest problem in #oncology #drugdevelopment, and why solving it starts with combining the granularity of patient-level data with the reliability of published trial evidence. Read it here: na2.hubs.ly/H04mg_z0

#UnlearnerSpotlight 🚀 “My favorite part is the mission, and the intentionality behind how we pursue it. We're not racing to layer AI onto everything, we're focused on building trust first. That's what excites me: working somewhere that believes in meeting people where they are, respecting their rigor, and bringing them along.”

🧠 We're in Copenhagen this week for #ADPD2026, and the conversations couldn’t be more timely. The questions driving the field: “How do we reduce trial burden, design smarter studies, and get to more confident answers faster?” are ones we think about every day. We know PD trials are among the most difficult to run and the status quo isn't good enough. Unlearn's #AI solutions are purpose-built for exactly these problems. See how we're doing it: na2.hubs.ly/H04k2wn0

Our Alzheimer’s data asset just got bigger. 🚀 We’ve added several key biomarkers to our AD dataset, enabling new ways to explore how biomarkers can be used as inputs, outcomes, or both when generating #digitaltwins of study patients. Our latest model update, AD DTG 4.2, now incorporates p-tau217 and GFAP, enabling early exploration of biomarker outcomes. Read the blog post to learn more: na2.hubs.ly/H04gZzh0

"Where did this assumption come from?" It's one of the most familiar questions in any protocol review and it’s expensive to answer repeatedly. The real cost isn't the answer. It's the design options that were never stress-tested because rebuilding the analysis would take time no one had. Our new paper puts a number on that: na2.hubs.ly/H04fqtk0

🎉 Unlearn is excited to partner with SOLA Biosciences on an early-phase ALS study of SOL-257, supported by our AI-generated #digitaltwins. We’re grateful for the opportunity to collaborate on advancing clinical research for people living with #ALS — read the full announcement to learn more. na2.hubs.ly/H04bJQ60

Protocol amendments are often treated as a trial conduct problem. The data suggests otherwise. Many originate earlier, during design, when teams reassemble evidence from scratch, triggering repeated rounds of re-analysis that accumulate into costs most organizations never measure. 📄 We wrote a paper on what that upstream rework actually costs, why fragmentation persists, and what changes when trial design gets a proper home. Read it here: na2.hubs.ly/H04588D0

🧠 Heading to #ADPD2026 in Copenhagen on March 17? Join Unlearn as we highlight our latest work in CNS, including: Poster: “Simulating TRAILBLAZER-ALZ 2 with Digital Twins to Boost Power for MCI Subgroups and Secondary Endpoints” — demonstrating how digital twins of study participants delivered up to a 15% increase in power across all endpoints while preserving sample sizes for MCI subgroup analyses. Panel: Forum 2 - Beyond One Size Fits All — Jon Walsh (co-founder and CSO) presenting “Precision Drug Development, AI Methods, and Trial Design in AD/PD” (March 18 at 3:35–4:35 pm in Hall A1). ——— @adpdnet

🧠 Join Unlearn at #ADPD2026 in Copenhagen on March 17, where we’ll be sharing our impact in CNS, including: Poster: “Simulating TRAILBLAZER-ALZ 2 with Digital Twins to Boost Power for MCI Subgroups and Secondary Endpoints” — showing how digital twins of study participants delivered up to a 15% power boost across all endpoints while maintaining sample sizes for MCI subgroup analyses. Panel: Forum 2 - Beyond One Size Fits All — Jonathan Walsh (co-founder and CSO) presenting “Precision Drug Development, AI Methods, and Trial Design in AD/PD” (March 18 at 3:35–4:35 pm) ——— @adpdnet

🚀 We’re proud to partner with CHDI Foundation to advance #AI modeling in Huntington’s disease. Through access to data from CHDI’s Enroll-HD research platform, Unlearn is further refining and updating our Huntington’s disease–specific Digital Twin Generator. This collaboration enables our model to learn from high-quality, longitudinal participant data, strengthening our ability to forecast disease progression and support clinical development. We’re deeply grateful to CHDI and to the thousands of Enroll-HD participants whose contributions make this work possible. Partnerships like this are essential to driving meaningful progress for the Huntington’s disease community. Read the announcement: na2.hubs.ly/H03TPbw0

Grateful to have been at #ISCTM2026 presenting our poster (#22), “Machine learning generated digital twins as an external control in non-randomized trials,” showing how #digitaltwins can reduce bias and variability in #ALS and #HD studies, while highlighting TrialPioneer, our AI-enabled workspace for upstream #CNS trial planning. 🚀 ——— @isctm

In early-stage studies, leading sponsors are increasingly looking beyond traditional designs to AI-enabled approaches that generate stronger evidence from every participant. Case in point: we’ve partnered with VectorY Therapeutics on the PIONEER-ALS Phase 1/2 study of VTx-002, a first-in-class vectorized antibody targeting TDP-43 pathology in ALS. Together, we’re integrating patient-level #digitaltwins into pre-specified exploratory analyses to strengthen evidence generation from a single-arm design and support more confident development decisions. Read more about the partnership here: na2.hubs.ly/H03Rzzm0

#UnlearnerSpotlight 🚀 “I get to work with an incredibly talented and creative, mission-driven team. Every day we get to solve difficult problems and make meaningful impact to delivering faster, smarter clinical trials.”

“In the PIONEER‑ALS study, we are focused on generating high‑quality safety and biomarker signal data for VTx‑002, our first‑in‑class vectorized antibody targeting TDP‑43 pathology. Integrating Unlearn’s patient-level digital twin technology into our prespecified exploratory analyses will help strengthen evidence generation from a single-arm design, with the aim to support more confident development decisions, disease progression modelling, and reduce timelines and patient burden.” — Olga Uspenskaya‑Cadoz, M.D., Ph.D., Chief Medical Officer, VectorY Therapeutics We’re proud to partner with VectorY Therapeutics on this innovative study, applying AI‑generated #digitaltwins to help advance #ALS research. Read more: na2.hubs.ly/H03M16k0

🚀 Headed to #ISCTM2026? Stop by poster #22, “Machine learning generated digital twins as an external control in non-randomized trials,” to see how #digitaltwins can reduce bias and boost power in ALS and HD studies, for stronger evidence when traditional control arms fall short. We’ll also be sharing TrialPioneer, our AI-enabled workspace for upstream #CNS trial planning—bringing benchmarking, precedent review, and scenario simulation into one traceable workflow. ——— @isctm

🎉 We’re thrilled to announce our partnership with VectorY Therapeutics to apply AI-generated digital twins in the PIONEER-ALS Phase 1/2 study evaluating VTx-002, a first-in-class vectorized antibody targeting TDP-43 pathology in #ALS. Unlearn’s ALS Digital Twin Generator will create individualized forecasts of expected disease progression, serving as patient-level external comparators to strengthen evidence generation and support more confident development decisions. Read more: na2.hubs.ly/H03DHqT0

🌴 We had a great few days at #SCOPE2026, connecting with industry leaders to discuss how we help clinical development teams align faster, test assumptions earlier, and move forward with confidence—from trial design through analysis—using #TrialPioneer and AI-generated #digitaltwins. ——— @SCOPE_365

🗒️ Early trial planning is where some of the most important decisions in clinical development get made—and where small changes to endpoints, populations, eligibility criteria, or sample size can have outsized downstream impact. Too often, teams are forced to make these calls with evidence, assumptions, and scenario outputs disconnected—making trade-offs harder to evaluate and the rationale harder to defend as plans evolve. We put together a short one-pager that outlines a different approach to upstream trial planning: connecting evidence, assumptions, historical benchmarks, and design scenarios so teams can make trade-offs explicit and keep decision context review-ready as designs change. Download the TrialPioneer Overview: na2.hubs.ly/H03tcZ_0