Unlearn in Amyotrophic Lateral Sclerosis
The scientific intelligence layer for clinical development
Powered by digital twins, data, and AI
In Amyotrophic Lateral Sclerosis, where patient populations are small and disease progresses rapidly, Unlearn turns data into a compounding advantage — so each trial informs the next, decisions get sharper earlier, and new therapies reach patients faster.
.svg)
Sample-size reduction in a completed Phase 3 ALS trial
Participants needed at Phase 3, with power maintained
Estimated enrollment savings
The Unlearn Platform
Plan, monitor, analyze — one connected platform organized around the key decisions that shape every clinical trial.
Plan
Trial Planning and Simulations
Bring together the critical components for early planning and design — where decisions are iterative and rationale must stay defensible across review cycles. Teams work from a shared source of truth, reducing rework and accelerating alignment.
AI-powered literature and precedent review across PubMed, ClinicalTrials.gov, and drugs@FDA — align on precedent in days, not weeks.
Explore harmonized trial and real-world data to validate assumptions across ADAS-Cog 13, CDR-SB, MMSE, and p-tau217.
Build and compare explainable, reproducible trial-design scenarios before protocol finalization.
.avif)
.avif)
Monitor
Advanced Trial Monitoring
Turn blinded signals into curated insights that support trial decision-making and keep execution on track.
Detect anomalies as they emerge — unexpected values, off-trajectory responders, and multivariate signals benchmarked against historical patient trajectories rather than generic, population-wide cutoffs.
Flag which patient observations warrant medical review, which outliers require investigation, and which sites to escalate.
Analyze
Trial Analyses with Digital Twins
AI-generated digital twins forecast each participant’s control outcomes at every future time point — the powering technology for more rigorous analysis.
Run smaller RCTs that maintain or boost power without additional participants. Validated using completed Phase 2 and Phase 3 ALS trials; qualified by EMA and aligned with FDA guidance.
Digital twins serve as an AI-generated externally controlled arm where randomization is infeasible.
Improve sensitivity in interim looks and subgroup analyses to catch signals traditional methods miss.
Technology
Digital Twin Generators
Digital Twin Generators (DTGs) are machine learning models that produce individualized forecasts, called digital twins, of each trial participant’s expected clinical outcomes under placebo. These forecasts are generated using baseline data and include predicted values for item-level assessments, labs, vitals, and other clinical measures. DTGs are powered by Neural Boltzmann Machines, a proprietary machine learning architecture optimized for probabilistically modeling complex, multivariate, clinical time-series data.
.webp)
Regulatory Acceptance
CHMP qualifies PROCOVA and that the proposed procedures could enable increases in power and/or decreases in sample size in phase 2 and 3 in clinical trials with continuous outcomes.
FDA recommends that sponsors adjust for covariates that are anticipated to be most strongly associated with the outcome of interest… the sample size and power calculations can be based on adjusted or unadjusted methods.
Case studies from retrospective analyses
Proof across ALS development
outcome
SAMPLE SIZE REDUCTION, 24 WEEKS
SAMPLE SIZE REDUCTION, 48 WEEKS
CASE 1 — PHASE 3 · CEFTRIAXONE REANALYSIS · ALS
We reanalyzed a completed Phase 3 trial of 513 participants randomized to ceftriaxone in a 2:1 ratio, with the ALS Functional Rating Scale–Revised (ALSFRS-R) at 48 weeks as the primary outcome. Using our EMA-qualified PROCOVA method, we generated digital twins of study participants and applied linear regression, reducing treatment-effect variance by 18% — equivalent to enrolling 92 fewer participants while maintaining trial power, and roughly $14M in enrollment savings (from ~$77M to ~$63M) for an industry-sponsored trial.These analyses used a pre-specified ALS DTG. Prognostic scores derived from participants’ digital twins reduced treatment-effect variance for the clinical outcomes without compromising Type-1 error control. Assuming the trial’s original power was 60%, PROCOVA raised power to 70% and Bayesian PROCOVA to 78% — a boost suited to Phase 2 interim decisions and end-of-study analyses.
Retrospective reanalysis of the completed Phase 3 ceftriaxone ALS trial (513 participants); analysis performed with ALS DTG 2.4.
Evidence
Driving Impact Across Clinical Development
Explore how our partners are accelerating their clinical development programs with us.
Reduce sample sizes while maintaining power or boost power without adding participants
Strengthen evidence and confidence in early-stage studies
Working with Unlearn to mine their extensive, well-curated database through the use of the ALS DTG will enable us to explore smarter designs and make confident and informed decisions as we plan our Phase 1/2 trial. Ultimately, these insights can help us to move faster for people living with ALS who are waiting for new treatment options.
