Generating publication-grade real-world evidence in minutes to days for precision medicine and clinical decision support.
Palo Alto, CA
Joined April 2022
- Tweets403
- Following165
- Followers237
- Likes50
Thank you to @ZSAssociates, @McKesson, and @SilversmithCap for hosting this year's AI Innovation Day! It was a privilege to showcase our rapid evidence generation tools and discuss how cross-industry collaboration is driving the future of #HealthcareAI.
We are proud to announce that @_Becaris is leading a 12-month independent peer review to evaluate the clinical quality and methodological rigor of Alexandria, the Atropos Evidence Library: businesswire.com/news/home/2… #RealWorldEvidence #HealthcareAI
We've been named a 2026 Fierce Life Sciences Innovation Awards in AI Innovation by @FierceHealth for the Atropos Evidence™ Agent's contribution toward advancing the future of healthcare and life sciences! fiercelifesciencesinnovation…
#RealWorldEvidence #PrecisionMed #HealthcareAI
Our team is headed to Boston for the 14th Annual IMPACCT Real-World Evidence Summit! We’ll be there to talk about all things novel RWE generation, data fitness, and delivery at the point of care.
📅 Oct 27 - 29, 2026
📍 Boston, MA
5️⃣ Booth #5
#RWE #HEOR #IMPACCTRWE
For three of the four models, 63–76% of answers using web search alone cited their sources accurately, yet those sources described a different patient group, comparison, or outcome. Others found no matching evidence.
The questions and grading rubric are open under CC BY-SA 4.0. We invite other groups to run the benchmark on their own systems and share what they find. Dataset on @huggingface: huggingface.co/datasets/atro…
We posed 209 patient-specific questions like this to four frontier LLMs. Each model answered every question twice: once with web search alone, and once with added access to Alexandria®, our library of real-world evidence.
We graded each answer on two points. Does one cited source match the patient, treatment, comparison, and outcome in the question? Does the answer report that source accurately? Answers that did both earned a "precision match."
Why it matters: clinicians often need evidence for one specific patient. For example, for someone with type 2 diabetes and reduced kidney function, which of two common drugs carries more risk of acute kidney injury? Trials often leave comparisons like this unreported.
New preprint: Precision Evidence Bench, an open benchmark that tests whether AI can find evidence matching the specific patient in a clinical question, and report that evidence faithfully.
Read the preprint: medrxiv.org/content/10.64898…
#ClinicalAI #RWE
Across healthcare, the AI conversation keeps coming back to trust: can you stand behind the evidence? We're looking forward to doing a deep dive on this topic with industry leaders at AI Innovation Day, hosted by @ZSAssociates, @McKesson, and @SilversmithCap. #HealthcareAI #RWE
On a recent episode of Digital Health Talks (@HITHealthIMPACT), our CEO @BrighamHyde discusses how #RWE reaches clinicians at the point of care, how Atropos Health generates studies for patients research leaves out, and what builds trust in that evidence: digitalhealthtalks.com/episo…
Join us next week at @ArcadiaHealthIT's #Aggregate2026 in Philadelphia, Oct 6-8! We're excited to talk about evidence-based clinical decision support, medication use policy, shared decision making, and precision medicine. #RealWorldEvidence
Atropos Health has been named a 2026 Digital Health & AI Awards Quarterfinalist in Transformative Care Delivery by @DigiHlthHubFdn! We're honored to be recognized, and we look forward to the next round of the competition! digitalhealthhub.org/awards/… #DigitalHealth #healthcareAI
AI now captures nearly every clinical encounter. What can it do with that context to shape the next decision? Find out at this year's @HITHealthIMPACT.
📍 Microsoft,Times Square
🗓 Tue, Oct 6 | 2:30 to 3:15 PM ET
Full agenda: healthimpactlive.com/fallfor…
#ClinicalAI #RWE
How does gender-affirming hormone therapy affect the liver?
Researchers from @Stanford, @UChicagoMed, @MayoClinic, @HopkinsMedicine, and @AtroposHealth analyzed 16,379 adults – 15X the largest prior related study in the US. 🧵
Understudied patient populations exist throughout medicine. By helping researchers answer questions that existing studies have left open, observational research can give clinicians better evidence for treatment decisions and, ultimately, improve patient outcomes.
Atropos helps make that research possible across a wide range of patient populations. Read the full study in @FrontGastro_BMJ: fg.bmj.com/content/early/202…
#RealWorldEvidence #RWE #Hepatology #Healthcare
