Bio
I’m a computational scientist, and for two decades I’ve worked on the same core problem in different forms — finding the signal hidden in noisy, complex data — from the physics of proteins and molecular machines, to the genomics of cancer, to the unstructured clinical text of patient records. At Norstella I’ve turned that into production AI at scale: reliably extracting the clinical facts buried in messy notes to build disease-specific datasets, with predictive triggers and patient-identification tools layered on top, now relied on by pharma teams across the drug lifecycle.
What makes Norstella’s AI different?
Two things: the data and the people. We build on the deepest, broadest real-world data footprint in the industry — multimodal data spanning clinical notes, EHR, claims, and genomics — using AI to extract exceptionally deep clinical detail and turn it into datasets, solutions, and platforms that let pharma teams answer real questions across the drug lifecycle. And we build it to be trusted: a human-in-the-loop methodology validated on expert-reviewed samples, a team of strong data and AI scientists, engineers, and clinical experts, and the ultimate proof — pharma clients relying on our work every day.
What can pharma teams do now that was not possible two years ago?
They can identify the right patients and characterize how disease actually progresses — reading the deep clinical reality buried in unstructured notes and multimodal data at population scale, in near real time. Questions that once required months of manual chart review or a retrospective study can now be answered on demand, across any therapeutic area.
How can AI accelerate the journey from pipeline to patient?
Two forces have converged to make this possible: real-world data has become far richer, and LLMs — now agentic AI — can uncover hidden clinical signal and assemble holistic insight faster and more precisely than ever before. What turns that into real acceleration across the pipeline-to-patient journey is expertise — the domain knowledge, clinical understanding, and technical judgment to direct these tools well and stand behind what they produce — so pharma teams get insight they can move on with confidence.