University of Michigan School of Information

Menu
UMSI logo
A headshot of Neha Bhomia

Neha Bhomia

Adjunct Lecturer in Information, Applications Programmer/Analyst, School of Information and Data Lead, Michigan Collaborative for Type 2 Diabetes and Technical Assistant Email: [email protected] Phone: 734/764-5876
Office: School of Information/3450 Leinweber Comp Sci & Info Bd Staff Unit: UMSI IT News About Neha Bhomia

Research Areas

Biography

Neha Bhomia is an Application Systems Programmer Analyst at Michigan Medicine and an Adjunct Lecturer at the School of Information, University of Michigan. She is also a developer and analyst for the UMSI Computing Services unit. Leveraging her background as a healthcare provider, Dr. Bhomia converges healthcare and technology to improve quality of patient care. She manages complex data flows, designs robust data pipelines, and provides technical direction for Collaborative Quality Initiatives (CQIs) like the Michigan Radiation Oncology Quality Consortium (MROQC) and the Michigan Collaborative for Type 2 Diabetes (MCT2D). Along with several MADS courses, she also teaches Healthcare Data Analysis and Introduction to Applied Data Science at the School of Information.

Pronouns

She/Her

Areas of interest

Healthcare Equity, Health Technology Integration, Software Development, Data Management, Collaborative Quality Initiatives (CQIs), Technology-Enhanced Patient Care

News about Neha Bhomia

Dallas Card, Sabina Tomkins and Jeff Sheng
UMSI welcomes new 2021-22 faculty

Three new assistant professors and 16 lecturers will join the University of Michigan School of Information faculty this academic year, including five 2021 grads of UMSI degree programs.

More Info
Healthcare workers walking down a corridor with superimposed text "Machine learning in healthcare"
MADS capstone team works toward more nuanced predictive tools for healthcare

By opening up complex black box models, four UMSI Master of Applied Data Science grads are helping the healthcare industry move away from a strong preference for simple predictive models and into the future of machine learning.

More Info