0009-0002-5162-8730 About
I’m a data-driven digital health researcher and data engineer passionate about using technology to improve healthcare delivery and equity. My work focuses on integrating large-scale health data, developing privacy-preserving frameworks, and applying artificial intelligence (AI) to enhance disease management and care coordination.
At CGD Health Pvt. Ltd., I design and maintain secure, scalable healthcare data infrastructures that manage millions of patient records while ensuring data quality, interoperability, and compliance with health data standards. I’ve also contributed to several peer-reviewed publications on using large language models for de-identification and privacy protection in electronic health records, in collaboration with researchers from UNSW Sydney and Academia Sinica.
I hold a Master’s degree in Bioinformatics and a Bachelor’s degree in Biotechnology from the University of Mumbai. My technical expertise includes Python, SQL, R, and cloud platforms such as Google Cloud, AWS, and Azure, along with healthcare data standards like OMOP, HL7, SNOMED CT, and ICD-10-AM. I’m particularly interested in designing digital health solutions that strengthen primary care and community health systems through data-driven, patient-centered approaches.
Employment
-
CGD Health Pvt. Ltd. Data Engineer2022 - Present
Education
-
University of Mumbai Master of Science in Bioinformatics2020 - 2022
-
University of Mumbai Bachelors of Science in Biotechnology2017 - 2020
Projects & Funding
Projects & funding information is unavailable.
Publications (7)
- Benchmarking large language models for de-identification of electronic health record notes Save
- Leveraging State-of-the-Art LLMs for the De-identification of Sensitive Health Information in Clinical Speech Save
- A Clinical Speech Corpus with Temporally Aligned Sensitive Health Information Save
- Deidentification and Temporal Normalization of the Electronic Health Record Notes Using Large Language Models: The 2023 SREDH/AI-Cup Competition for Deidentification of Sensitive Health Information Save
- Evaluation of OpenDeID Pipeline in the 2023 SREDH/AI-Cup Competition for Deidentification of Sensitive Health Information Save
- Leveraging large language models for the deidentification and temporal normalization of sensitive health information in electronic health records Save
- Utilizing Large Language Models for Privacy Protection and Advancing Medical Digitization Save