Faces of Geneia: Geneia Data Scientist Sri Bandhakavi | Geneia

Faces of Geneia: Geneia Data Scientist Sri Bandhakavi

February 05, 2020
Fred Rahmanian, Chief Analytics and Technology Officer


Another PhD-level data scientist joins the Geneia Data Intelligence Lab.
“Sri chose EBTC data analytics project as a Capstone project in Northeastern University Experiential Learning program in 2018 and stuck with it after the course ended, taking the project forward and expanding its scope, using his data analytics skills and applying them to the field of toxicology and mechanistic data analysis. Sri is creative, curious, agile and flexible in his work, and on top of it fun to work with. He would be a great asset in any environment that needs data analytics, and that would provide him with intellectual stimulation.”

So wrote Katya Tsaioun, the director of the Evidence-Based Technology Collaboration (EBTC), about one of the Geneia Data Intelligence Lab’s (GDI Lab) newest principal data scientists, Sri Bandhakavi.

I wholeheartedly agree. Sri is creative, curious, agile and flexible, and fun to work with – a definitive plus given we now have five principal data scientists working in one small office in New Hampshire.

It’s my pleasure to introduce Sri to Geneia blog readers. He joins a robust team of carefully vetted and trained PhD- and masters-level data scientists, analysts and engineers dedicated to building predictive and increasingly prescriptive models to lower healthcare costs and improve health outcomes.

ICYMI, using leading-edge data science, the GDI Lab creates elegant, refined and novel predictive models that are easy to use, faster than, and as accurate as or more accurate than traditional models. The GDI Lab prioritizes projects that address major cost drivers and health complications with the goal of enabling health plans, hospitals and physician organizations to better identify and manage complex and expensive claimants for all-causes or chronic conditions such as heart failure and diabetes.

Meet Sri

Sri is a mid-career professional, bringing a rich professional history to his Geneia projects. He worked in the diagnostics industry for seven years, most recently as research and development leader at PerkinElmer, Inc. While there, he led research teams through the development of FDA-approved, mass spectrometry-based diagnostic tests and instrumentation for use in newborn screening.

More importantly, his work at PerkinElmer, Inc. connected him with statisticians from whom he discovered the thrill of playing with numbers. This discovery led him to pursue an advanced degree in data analytics.

In Sri’s words, “I didn’t know exactly what I would get out of my master’s program, but I was confident it would enable me to solve new interesting questions I hadn’t yet dabbled with or find new answers to existing questions.” During the master’s program, Sri was formally trained in the mechanics of data mining, predictive modeling and machine learning. Sri also has a PhD in biochemistry and molecular biology from the University of Georgia. Athens, Georgia is where in Sri’s words, he learned to love University of Georgia football.

Sri’s Work at EBTC

While working on his master’s degree in data analytics at Northeastern University, Sri was paired with the Evidence-Based Technology Collaboration, a nonprofit affiliated with Johns Hopkins University that has access to varied data sources. For more than two years – currently as a member of EBTC’s Scientific Advisory Council – Sri has worked with EBTC to define the questions to ask and try to answer with its data.

One project became, in Sri’s words, an obsession – can we predict which drugs approved by the FDA will cause liver toxicity? In short, Sri’s answer is to this pivotal question is yes - with machine learning. 

Sri’s Work at Geneia

Sri started at Geneia in September, and to date, his work has focused on identifying care gaps for patients with chronic diseases. Among the questions he’s working to answer are:

  • Which patients are being treated for chronic diseases but not diagnosed for the same condition?
  • Which patients are diagnosed but not treated? Or, not treated using evidence-based practices?
  • Can we predict patients likely to develop care gaps, and therefore manage them better?

Stay tuned for upcoming blogs about other members of the Geneia Data Intelligence Lab team and the important work they’re doing to mitigate future health costs.


Related Blogs