Jose Posada

Dr. Posada is the Lead Biomedical Informatics Data Scientist at Stanford Health Care,
where he architects enterprise-grade data pipelines that transform multi-hospital Epic data into
OMOP-CDM databases covering millions of patients. With 17+ years of experience spanning
clinical data science, software engineering, and clinical NLP, he holds a PhD and MS in Biomedical
Informatics from the University of Pittsburgh. Previously, he earned an MS in Mechanical
Engineering and a BS in Electronic Engineering from Universidad del Norte (Colombia). He has
held roles as a Clinical NLP Scientist at Abridge AI, Sr. Clinical Data Scientist at Stanford University
School of Medicine, and adjunct/assistant professor positions in Colombia. He is a Fulbright
fellow, was the Lead for the Latin America (LATAM) Working Group at OHDSI, and served as the
Stanford Liaison for the OHDSI Network.

Being part of Pitt DBMI was a transformative experience that defined the
trajectory of my career. During my joint MS (’16) and PhD (’18) journey, I explored the full
breadth of biomedical informatics: from clinical natural language processing to predictive
modeling of infant mortality in Allegheny County. Under the guidance of my research mentor, Dr.
Rich Tsui, my dissertation, Semantics Enhanced Deep Learning Medical Text Classifier, embedded
the meaning of clinical concepts from biomedical ontologies into the loss function of a deep
learning text classifier and adapted a semi-supervised approach to learn from large unlabeled
datasets — reducing the need for costly expert annotation so that clinical NLP could scale across
institutions. That work taught me to bridge the gap between messy, real-world clinical data and
rigorous machine learning, a foundation I apply every day leading clinical data science at
Stanford Health Care. I am deeply grateful to the DBMI leadership and professors who shaped
me: Dr. Rebecca Jacobson, Dr. Harry Hochheiser, and Dr. Shyam Visweswaran. Their mentorship
and generosity made my time at Pitt truly extraordinary. Hail to Pitt!