Full-Time
Posted on 9/19/2025
AI-powered patient digital twins for simulations
$150k - $180k/yr
H1B Sponsorship Available
Remote in USA + 1 more
More locations: San Francisco, CA, USA
In Person
| , |
Unlearn.AI builds AI-powered digital twins of patients to simulate health outcomes and predict how conditions may evolve. It generates patient-specific virtual replicas from data and runs treatment scenarios to forecast results. Unlike traditional trials, its twins model control groups for clinical studies, potentially reducing the number of real patients needed and speeding drug development. The goal is to speed healthcare decisions, improve trial efficiency, and lower costs by using digital twin simulations to forecast outcomes.
Company Size
51-200
Company Stage
Series C
Total Funding
$130.7M
Headquarters
San Francisco, California
Founded
2017
Help us improve and share your feedback! Did you find this helpful?
Health Insurance
Dental Insurance
Vision Insurance
401(k) Retirement Plan
401(k) Company Match
Unlimited Paid Time Off
Paid Holidays
Commuter Benefits
Paid Parental Leave
Company Equity
AD model update: AD DTG 4.2 - exploring biomarker outcomes in Alzheimer's disease. March 13, 2026. Unlearn is excited to announce the release of AD DTG 4.2, the latest update to its Alzheimer's disease Digital Twin Generator. This release expands the biomarker data available to its model and enables early exploration of biomarkers as potential clinical outcomes. Why biomarkers matter in AD trials. Biomarkers are measurable biological molecules whose concentration shifts in response to disease processes or treatments. Unlike traditional lab values that monitor general physiology, such as electrolytes or liver enzymes, disease-specific biomarkers target molecular pathways tied to a specific condition. In Alzheimer's, novel biomarkers like phosphorylated tau-217 (p-tau217), amyloid beta 40 (Aβ40), and amyloid beta 42 (Aβ42) can signal neurodegenerative changes years before symptoms appear, making them valuable for detecting disease, tracking progression, and evaluating therapeutic response in clinical trials. Expanded data, expanded possibilities. The updated data asset now includes or enriches several AD-relevant biomarkers, including: Aβ40, Aβ42, total tau (t-tau), phosphorylated tau-181 (p-tau181), p-tau217, glial fibrillary acidic protein (GFAP), and neurofilament light chain (NfL). Incorporating these biomarkers into the data asset creates new opportunities to explore their role in inputs, outputs, or both when generating digital twins of study patients in future DTG releases. An early exploration of ptau-217 as a clinical outcome. AD DTG 4.2 incorporates two biomarkers from the updated data asset, p-tau217 and GFAP. P-tau217 is a sensitive and specific marker of Alzheimer's pathology, correlating with amyloid accumulation, tau burden, brain atrophy, and physical degradation - and notably does not predict such changes in patients with other neurodegenerative disorders, making it highly specific to Alzheimer's disease. This specificity makes it a compelling feature for modeling disease progression. With this release, the model can now predict longitudinal changes in ptau-217 concentration as a clinical outcome, a capability Unlearn is optimistic about as Unlearn continue to grow and validate the underlying dataset. This capability may help support broader biomarker modeling within the AD DTG framework for future model updates. In addition, treating ptau-217 as the sole input to the model can provide prognostic information for other outcomes commonly measured in Alzheimer's trials. What's next. This biomarker work builds on the validated foundation of the AD DTG, which has already demonstrated meaningful impact in Alzheimer's studies. In retrospective analyses, digital twins of study participants have supported sample size reductions of up to 15% and up to 33% in control arms using Unlearn's EMA-qualified and FDA-supported method. As Unlearn continue to grow and enrich its AD dataset, now trained on over 25,000 patient records spanning cognitively normal individuals through moderate Alzheimer's disease, the model will be positioned to support increasingly robust biomarker modeling and stronger digital wins in future DTG releases. Blog.
Unlearn, a San Francisco-based AI company, will support SOLA Biosciences' Phase 1/2 clinical study of SOL-257, an investigational gene therapy for amyotrophic lateral sclerosis. The partnership will use AI-generated digital twins to strengthen the early-phase study. The single-arm trial will use digital twins as external comparators to help interpret clinical outcomes, addressing challenges posed by disease heterogeneity and small sample sizes in early-stage ALS studies. Unlearn's digital twins are created by a machine-learning model trained on extensive patient-level historical ALS data. The collaboration will support trial planning, regulatory engagement and participant-level analyses during the Phase 1/2 study and long-term follow-up. Unlearn has secured EMA qualification and FDA support for its digital twin technology in clinical trials.
Unlearn, an AI company specialising in clinical development, will use data from CHDI Foundation's Enroll-HD research platform to refine its Huntington's disease-specific Digital Twin Generator. The machine learning model generates individualised forecasts of disease progression using longitudinal, patient-level data. Enroll-HD is a global clinical research platform with over 22,000 active participants across 157 sites in 23 countries. CHDI Foundation is a privately funded nonprofit exclusively dedicated to developing Huntington's disease therapeutics. Unlearn's AI-generated digital twins are used in clinical trials to reduce variability and strengthen treatment effect estimation. The company has received EMA qualification and FDA support for applying AI in clinical trials. The collaboration aims to improve how Huntington's disease trials are designed and analysed.
Unlearn, a leader in AI solutions for clinical development, has launched TrialPioneer, an AI-powered workspace designed to accelerate decision-making in upstream trial planning. The platform helps clinical development teams optimise study designs by consolidating evidence, assumptions and scenario evaluations in one workflow. TrialPioneer integrates three capabilities: Scout for AI-powered precedent review from sources like PubMed and ClinicalTrials.gov; Hindsight for exploring historical benchmarks using patient-level data; and SimLab for on-demand trial simulations comparing design scenarios. The workspace addresses fragmentation in planning workflows by making assumptions explicit and traceable, enabling teams to evaluate trade-offs earlier and align on study designs. Unlearn has received EMA qualification and FDA support for its science-first approach to applying AI in clinical trials.
Dr. Robert Lenz joins Unlearn as strategic advisor.