Nikita Mehandru

Joint with David Bamman

Scholar LinkedIn Twitter/X Website

Nikita Mehandru is a Ph.D. candidate at the UC Berkeley School of Information with a Designated Emphasis in Computational Precision Health (CPH) and an affiliation with Berkeley Artificial Intelligence Research (BAIR). She received her M.S. in Computer Science from UC Berkeley EECS, and bachelor’s degree from Claremont McKenna College. Her work develops and applies machine learning methods for clinical reasoning and disease progression modeling using unstructured text and time series data from electronic health records.

Publications

ER-Reason: A Benchmark Dataset for LLM Clinical Reasoning in the Emergency Room

Nikita Mehandru, Niloufar Golchini, Namrata Garg, Kathy LeSaint, Christopher Nash, Anu Ramachandran, Travis Zack, Liam McCoy, Adam Rodman, David Bamman, Melanie Molina†, Ahmed Alaa† (†Co-senior authors)

arXiv preprint · 2026

Paper Code Data

State-Space Modeling in Natural Language

Nikita Mehandru, Marie-Laure Charpignon, Kaihua Hou, David Bamman, Ahmed Alaa

ICLR Workshop on Time Series in the Age of Large Models · 2026

Paper

BioAgents: Bridging the Gap in Bioinformatics Analysis with Multi-Agent Systems

Nikita Mehandru, A.K. Hall, O. Melnichenko, Y. Dubinina, D. Tsirulnikov, Ahmed Alaa, et al.

Scientific Reports · 2025

Paper

Viability of Machine Translation for Healthcare in Low-Resourced Languages

H.H. Nigatu, Nikita Mehandru, N.H. Abadi, B. Gebremeskel, Ahmed Alaa, et al.

EMNLP · 2025

Paper

Physician-versus Large Language Model-Generated Summaries in the Emergency Department

Niloufar Golchini, Nikita Mehandru, Ahmed Alaa†, Melanie Molina† (†Co-senior authors)

medRxiv · 2025

Paper

Evaluating Large Language Models as Agents in the Clinic

Nikita Mehandru, Brenda Miao, Eduardo Rodriguez Almaraz, Madhumita Sushil, Atul Butte, Ahmed Alaa

NPJ Digital Medicine · 2024

Paper