Scott Haag

Background

About Scott Haag

I lead a data science team made up of Computer Scientists and Bioinformaticians to solve big data problems at the Children's Hospital of Philadelphia. My team uses best practices in software development and Continuous Integration/Development (CICD) to support over 150 research projects (and counting). I also represent the CHOP Research Institute providing leadership in AI Ethics, Governance, and Strategic Planning. On the side I am an Assistant Professor of Computer Science at Drexel University where I have active research on Synthetic Medical Data Generation, methods to embed medical records in vector space, and the development of novel algorithms to support environmental modeling. I also teach courses on Data Structures and Algorithms. My team at CHOP uses Large Language Models and Natural Language processing to extract knowledge from the Electronic Health Record at scale (100s of millions of clinical notes) in cloud computational environments. We normalize thousands of genetic sequences (Whole Genome, Whole Exome and single nucleotide polymorphism SNP) from across the hospital system into a single research database. We support scientific research using Geo-spatial Data and Actigraphy (the study of wearable sensors). We build software environments using Git, Docker, K8s, and scientific workflow management systems (Argo) to build reproducible and secure data processing pipelines at scale. All software we build is version controlled and includes an extensive Security and Design Review.