PhaseV vs Unlearn.AI (2026)
PhaseV and Unlearn.AI help sponsors examine trial power and sample size before finalizing development plans. PhaseV compares designs and treatment response patterns; Unlearn uses digital twin forecasts as statistical inputs within a defined trial analysis. PhaseV's Trial Optimizer simulates fixed, adaptive and Bayesian designs across recruitment, power, duration and cost. Response Optimizer investigates responder groups, and supported projects can connect retrospective analyses to revised protocols. Annual Exploration Access starts at $50,000, with advanced optimization plans and additional services priced separately. The available responder case evidence concerns retrospective analytical use, rather than prospective proof that a future trial will succeed. Unlearn's disease specific Digital Twin Generators forecast participant progression under control or standard care from baseline information. In randomized trials, PROCOVA uses that forecast as a prognostic covariate while preserving randomization and a prespecified analysis. The EMA qualification concerns a defined continuous outcome use, not every newer digital twin application. Single arm and external comparator uses have different unresolved bias boundaries. PhaseV fits teams comparing trial designs and selecting populations through a modular analytical workspace. Unlearn fits sponsors considering a digital twin informed statistical method with scientific partnership support. Both inform study planning, but they change different parts of the design and analysis process.
- Teams need comparisons across fixed, adaptive and Bayesian designs.
- Responder subgroup investigation is part of protocol planning.
- Recruitment, duration and cost tradeoffs should be explored together.
- A modular annual software purchase is preferred.
- A digital twin forecast should inform trial analysis.
- The randomized design will use a prognostic covariate.
- Scientists should support method selection across a program.
- Generator access is needed through an app or sponsor cloud.
This comparison is published by AI Health Index, an independent research platform that compares healthcare AI vendors objectively. PhaseV and Unlearn.AI are each graded against the same capability taxonomy, from each vendor's own public materials and the regulatory record, under the AI Health Index verification standard. No vendor pays for placement, and no vendor has reviewed this page. How this evidence is graded
Plain facts
| Fact | PhaseV | Unlearn.AI |
|---|---|---|
| Primary category | Clinical Trials AI | Clinical Trials AI |
| Founded | Not recorded | 2017 |
| Headquarters | Cambridge, Massachusetts, United States | San Francisco, California, United States |
| Website | phasevtrials.com | unlearn.ai |
Side by Side
Select any grade to read the note behind it.
Each vendor in one paragraph
Written to be quoted whole. Each paragraph opens the AI Health Index profile of the vendor: what the product is, who buys it and what it does.
PhaseV provides clinical development software for pharmaceutical sponsors, biotechnology companies, and contract research organizations. Its analytical modules help teams identify treatment responders, compare trial designs, select sites, and assess development opportunities. Response Optimizer estimates how treatment effects differ across patient groups, while Trial Optimizer simulates fixed, adaptive, and Bayesian designs.
Source: AI Health Index, October 2026
San Francisco company whose Digital Twin Generators, disease specific machine learning models trained on historical patient level data, forecast how each clinical trial participant would progress under control or standard of care from their baseline data. The forecast is used as a prognostic covariate in the trial analysis (PROCOVA, with Bayesian and repeated measures variants), which can raise power or reduce sample size in a randomized trial without introducing bias.
Source: AI Health Index, October 2026
Questions buyers ask
How are PhaseV and Unlearn.AI priced and sold?
For PhaseV, a purchase route is available before a sales conversation, although customized offers are also offered. Transactions are nonrefundable and additional infrastructure charges may apply.
With Unlearn.AI, the company states value rather than price: about 20 percent sample size reduction locked into design, about $2 million saved on a phase 1/2 study, and about $14 million less for the next ALS trial in one re-analysis. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified October 15, 2026. No vendor pays for placement.
How do PhaseV and Unlearn.AI handle patient data?
In PhaseV's case, the privacy policy's breach notification commitment concerns data incidents rather than a complete clinical AI safety process.
For Unlearn.AI, the technology page says sponsors can build custom generators from their proprietary data entirely within their own environments and under their control. The privacy notice (effective 1 April 2026) keeps information for as long as reasonably necessary and says its AI supports trial design and analysis rather than decisions about individuals. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified October 15, 2026. No vendor pays for placement.
Which settings and specialties do PhaseV and Unlearn.AI cover?
With PhaseV, the broader portfolio also targets oncology, immunology, neurological disease, metabolic disease, and rare disease research.
In Unlearn.AI's case, the technology page lists generators for 26 conditions across neurology, oncology, immunology, respiratory, metabolic and psychiatric disease, and the company sells into trial design, in-progress analysis and post-readout work for phase 1 to 3 studies. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified October 15, 2026. No vendor pays for placement.
What evidence is published for PhaseV and Unlearn.AI?
For PhaseV, the analysis combined Phase III and earlier Phase II data, checked findings against external Phase III studies, and included sensitivity and false discovery tests. Responding subgroups differed by age, body mass index, and baseline HbA1c; the case connects the analysis to an amended trial protocol.
With Unlearn.AI, the research list includes a Nature (2019) paper on forecasting Alzheimer's progression, Alzheimer's Association presentations evaluating digital twins on completed phase 2 trial data (2022, 2024), and arXiv papers on the generators and PROCOVA variants. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified October 15, 2026. No vendor pays for placement.
Related comparisons
Other published head to head assessments involving these vendors or their closest peers. The full set for this category is on the Clinical Trials AI page.
PhaseV is based in Cambridge, Massachusetts, and Unlearn.AI in San Francisco. Unlearn has no public fee schedule. Its PROCOVA qualification covers a defined use rather than every single arm or external comparator design, and reported efficiencies largely come from retrospective analyses.