Research

My research focuses reliablity and fairness for AI in clinical applications. I work at the intersection of academic research and industry applications, I'm excited about solving problems and building systems that deliver a *magic* experience to the user.

Prior to my focus on clinical-NLP. I worked on a wide range of deep-learning and healthcare problems including: molecular models for clinical diagnosis, representation learning for fMRI data, and resource-constrained ML models for signals data.

Publications

2025

Evaluation of large language model (LLM)-based clinical abstraction of electronic health records (EHRs) for non-small cell lung cancer (NSCLC) patients
Kabir Manghnani, Katie Mo, Kunal Nagpal, Xifeng Wang, Kaitlynn Cunnea, Bridget Bax, Michael Bodker, Arpita Saha, Chelsea Kendall Osterman, Riccardo Miotto, and others
American Society of Clinical Oncology (ASCO) 2025

2024

Concurrent tissue and circulating tumor DNA molecular profiling to detect guideline-based targeted mutations in a multicancer cohort
Wade T Iams, Matthew Mackay, Rotem Ben-Shachar, Joshua Drews, Kabir Manghnani, Adam J Hockenberry, Massimo Cristofanilli, Halla Nimeiri, Justin Guinney, Al B Benson
JAMA Network Open, 7(1), e2351700

2023

Large language models with retrieval-augmented generation for zero-shot disease phenotyping
Will E Thompson, David M Vidmar, Jessica K De Freitas, John M Pfeifer, Brandon K Fornwalt, Ruijun Chen, Gabriel Altay, Kabir Manghnani, Andrew C Nelsen, Kellie Morland, and others
arXiv preprint arXiv:2312.06457
Validation of a transcriptome-based assay for classifying cancers of unknown primary origin
Jackson Michuda, Alessandra Breschi, Joshuah Kapilivsky, Kabir Manghnani, Calvin McCarter, Adam J Hockenberry, Brittany Mineo, Catherine Igartua, Joel T Dudley, Martin C Stumpe, and others
Molecular Diagnosis & Therapy, 27(4), 499-511
Abstract P5-05-08: Dual ctDNA and tissue sequencing improves detection of actionable variants in breast cancer patients
Matthew Mackay, Kabir Manghnani, Adam Hockenberry, Joshua Drews, James Chen, Rotem Ben-Shachar, Justin Guinney
Cancer Research, 83(5_Supplement), P5-05

2022

Clinico-molecular real world data demonstrates prognostic significance of a three-gene biomarker for colorectal liver oligometastases
Kabir Manghnani, Ben Terdich, Sun Hae Hong, Justin Guinney, Halla Nimeiri, Martin Stumpe, Timothy Taxter, Kyle A Beauchamp
Cancer Research, 82(23)
Real-world data to enable large-scale assessment of WHO CNS5 glioma classification
Joshuah Kapilivsky, Kimmo J Hatanpaa, Kabir Manghnani, Timothy J Taxter, Martin Stumpe, Justin Guinney, Kyle A Beauchamp, Robin Arthur Buerki, Alessandra Breschi
American Society of Clinical Oncology (ASCO) 2022
Dual tissue and plasma testing to improve detection of actionable variants in patients with solid cancers
Matthew Mackay, Nicholas Mitsiades, Young Kwang Chae, Andrew A Davis, Philip Edward Lammers, James F Maher, Dan Theodorescu, Peter Rubin, Timothy J Pluard, Lee Langer, and others
American Society of Clinical Oncology (ASCO) 2022

2021

Systems and Methods for Self-Learning IoT Devices
Kabir Manghnani (Co-Inventor)
Patent no. 20210133607 | Assignee Shoreline AI
Patent

2019

Adapting sequence to sequence models for text normalization in social media
Ismini Lourentzou, Kabir Manghnani, ChengXiang Zhai
Proceedings of the International AAAI Conference on Web and Social Media, 13, 335-345

2018

METCC: METric learning for Confounder Control Making distance matter in high dimensional biological analysis
Kabir Manghnani, Adam Drake, Nathan Wan, Imran Haque
arXiv preprint arXiv:1812.03188