Saama vs Unlearn.AI (2026)
Both sell AI to trial sponsors, for different parts of the work. Saama runs the data side of a trial: models find discrepancies and draft queries for a reviewer to approve, Source to Submission maps raw trial data to the CDISC SDTM standard with a confidence score on each mapping, and modular Clinical AI Agents, introduced in September 2025, run from study start to submission. Unlearn changes the statistics of the trial itself. Its digital twins forecast how each participant would progress on control, and the forecast enters the analysis as a prognostic covariate, a method the European Medicines Agency qualified in 2022 for primary analysis of phase 2 and 3 trials. They rarely compete for the same budget. Saama makes a study's data cleaner and faster to submit; Unlearn can make a study smaller or better powered.
- Data review that drafts queries for a reviewer to approve, with a generative assistant that writes and tests data quality checks.
- Mapping of raw trial data to CDISC SDTM with a confidence score on every mapping.
- Use the company reports in more than 1,500 studies at over 50 sponsors, with Pfizer on its data review automation since 2020.
- Digital Twin Generators for 26 conditions, forecasting each participant's course on control.
- PROCOVA, qualified by the European Medicines Agency in 2022 for primary analysis of phase 2 and 3 trials.
- Company scientists working across trial design, interim analysis and re analysis after readout.
This comparison is published by AI Health Index, an independent research platform that compares healthcare AI vendors objectively. Saama 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 | Saama | Unlearn.AI |
|---|---|---|
| Primary category | Clinical Trials AI | Clinical Trials AI |
| Founded | Not recorded | 2017 |
| Headquarters | Campbell, California | San Francisco, California, United States |
| Website | saama.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.
Saama, based in Campbell, California, sells a clinical data platform and AI modules to pharmaceutical and biotechnology sponsors and contract research organizations. Smart Data Quality uses models to find data discrepancies and draft queries for reviewer approval, with a generative copilot that writes and tests data quality checks.
Source: AI Health Index, September 2026
Unlearn, based in San Francisco, builds Digital Twin Generators: disease specific machine learning models trained on historical patient level data that forecast how each clinical trial participant would progress under control or standard of care, from their baseline data. In a randomized trial the forecast is used as a prognostic covariate (PROCOVA, with Bayesian and repeated measures variants), which can raise power or shrink the control arm without introducing bias.
Source: AI Health Index, September 2026
Questions buyers ask
How are Saama and Unlearn.AI priced and sold?
For Saama, enterprise agreements with pharmaceutical and biotechnology sponsors and contract research organizations, sold as platform software and as customized solutions and services, with agents offered as modular additions to a sponsor's existing platforms.
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 September 29, 2026. No vendor pays for placement.
How do Saama and Unlearn.AI handle patient data?
In Saama's case, the privacy notice (effective 25 Apr 2024) says the company processes pseudonymized trial participant data as a processor for sponsors and contract research organizations, keeps personal information as long as reasonably necessary or as agreed by contract, and may use anonymized data indefinitely.
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 September 29, 2026. No vendor pays for placement.
Which settings and specialties do Saama and Unlearn.AI cover?
With Saama, the clinical platform covers sponsor-side development from study design and startup through conduct, biometrics and submission, and the company also sells commercial, medtech and provider-side products (revenue cycle management, care coordination, hospital orchestration) that sit outside the trial scope this listing describes.
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 September 29, 2026. No vendor pays for placement.
What evidence is published for Saama and Unlearn.AI?
For Saama, the home page credits Smart Data Quality with more than 20,000 hours of manual work saved, Patient Insights with 40 percent time savings in patient data review, and the document generator with 30 percent less drafting time. The BRAIN SDTM page says its automation is expected to cut effort by 50 percent and output generation timelines by 69 percent per study.
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 September 29, 2026. No vendor pays for placement.
Related comparisons
Other published head to head assessments involving these vendors or their closest peers.
Both records were reviewed on this site in September 2026. Neither company publishes a price.
Ask Saama how a mapping or query with low confidence reaches a person, and ask Unlearn how a twin generator is validated for a new indication before a sponsor relies on it.