Get your ticket or log in to build your agenda.

KEYNOTE (AI): Lumiata -- Lessons Learned in Building an AI Platform for Healthcare

- PDT
AI DevWorld -- Main Stage
Join on Hopin

Saurav Chatterjee
Lumiata, VP of Engineering

Saurav leads the engineering team at Lumiata. Lumiata builds an AI platform to help healthcare companies create better predictive models. Earlier he led Asurion Labs, where his team built a conversational NLP bot platform. Prior to his time at Asurion, he was Chief Architect for Visa Inc., developing their first direct-to-consumer product called Visa Checkout. He was also Chief Architect at Orative Corp., which developed mobile enterprise messaging and VoIP solutions; Orative was acquired by Cisco. He was also Chief Scientist at AlterEgo Networks, which developed a platform to dynamically transform desktop web content for mobile screens; this work was based on his research work at Stanford Research Institute (SRI). AlterEgo Networks was acquired by Macromedia/Adobe. He received his Ph.D. in computer engineering from Carnegie Mellon University.


Applying AI to healthcare is a great opportunity — better predictions on who is more likely to develop diabetes, back pain, and other chronic diseases, better predictions on which patients will require hospital re-admissions — not only in saving money but also improving patient health. In this talk, we will discuss our technology solution and our challenges in building AI/ML solutions in this domain:

* We built a data ingestion and extraction process using Apache Beam and Google Cloud DataFlow. We will describe our obstacles around joining and normalizing disparate patient datasets and our heuristics to solve this problem. We will also talk about performance and scalability obstacles and our solutions.
* We built model training and serving pipelines using Kubeflow (TensorFlow on Kubernetes and Istio). We will talk about how we built a HIPAA/SOC2 compliant infrastructure with these technologies and our experience using Katib for model tuning.