Unlearn.AI

💊 #Clinicaltrial design sits between evidence discovery and protocol execution, a middle space that has never had a dedicated home. Most organizations fill that gap with tools that weren’t built for it. They work well enough for one iteration. As designs evolve, version control becomes manual, provenance gets lost between documents, and scenario exploration stays serialized. The result: fewer design options are rigorously stress-tested than the team would’ve liked, because running one more scenario wasn't worth the delay. 📄 Our new paper puts a number on the cost. Download it here: na2.hubs.ly/H04w_Lc0

🎗️ Standard of care in #oncology evolves rapidly, and treatments are increasingly tested on narrower, biomarker-defined populations. As this happens, the ability of patient-level data alone to provide the insight needed to understand outcomes diminishes. RWD sources are also costly and time-consuming to collect, especially for narrowly defined populations. Published trial results offer population-level authority, but cannot be queried at the patient level or transferred across eligibility criteria. The ability to combine these two sources, harnessing the strength of each, would be of tremendous practical value. Today we are publishing a whitepaper describing how we approach this problem. Our approach, FRESH modeling (Fusion of Recent Evidence and Subject Histories), pairs a pan-cancer foundation model trained on biopsy assays from approximately 300,000 cancer patients with a calibration procedure that anchors patient-level predictions to published trial results. The result is a system that integrates patient-level granularity with population-level rigor, without requiring a bespoke data acquisition for each new cohort or #trialdesign question. Practical applications include precision trial simulation, calibrated synthetic comparator generation, and head-to-head comparative effectiveness analyses. Leading sponsors are already working with us to apply this across their oncology programs. 📄 The whitepaper includes validation case studies across NSCLC and mCRC. Download below, or reach out directly if you'd like to discuss how this applies to your pipeline. na2.hubs.ly/H04w5qq0

The CNS community came together in Copenhagen for #ADPD2026 and it was a week of real conversations about where #clinicaldevelopment needs to go next. We shared new work on how #digitaltwins of trial participants can improve trial design in Alzheimer’s and Parkinson’s, including a simulation of TRAILBLAZER-ALZ 2 showing up to a 15% increase in power across key endpoints, without increasing sample size. Unlearn’s Co-founder and Chief Scientific Officer, Jon Walsh, also joined Forum 2 to discuss how our AI clinical trial solutions are being applied in practice in AD/PD and where the field is heading. More than anything, this week was about being in the room: discussing challenges and connecting with the people driving this work forward. Appreciative of the conversations and excited about what comes next. 🚀 ——— @adpdnet

#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