Selected Publications
You can also find my full list of papers on Google Scholar.
Recent Highlight
 | First, Do NOHARM: Towards Clinically Safe Large Language Models David Wu*, Fateme Nateghi*, et al. arXiv preprint, 2025 *Co-first authors We introduce NOHARM, a large-scale benchmark for evaluating the clinical safety of large language models using real physician-to-physician consultation cases. NOHARM is the foundation of MAST (Medical AI Superintelligence Test), a new suite of realistic clinical benchmarks for medical AI. [Live Benchmark] | [Paper] |
 | SAGE – Specialist AI for Guiding Experts Fateme Nateghi, Jonathan H. Chen, et al. Ongoing Project [Live Demo] / [GitHub] SAGE is a specialist-trained AI system that enhances electronic consultations (eConsults) by: • Retrieving similar EHR patient cases • Recommending clinical actions based on real-world data • Pre-filling templates using LLMs • Supporting retrieval-augmented generation (RAG) The goal is to scale access to specialty care and promote guideline-aligned decision-making. |
Selected Publications under SAGE
Automated Evaluation of Large Language Model Response Concordance with Human Specialist Responses on Physician-to-Physician eConsult Cases
DJH Wu*, Fateme Nateghi*, D Wu, V Ravi, LG McCoy, Y Weng, K Chopra, JH Chen
medRxiv preprint, 2025
*Equal contribution
[Paper]
Asking the Right Questions: Benchmarking Large Language Models in the Development of Clinical Consultation Templates
LG McCoy*, Fateme Nateghi*, K Chopra, D Wu, DJH Wu, A Conteh, JH Chen
arXiv preprint, 2025
*Equal contribution
[arXiv]
 | Retrieval-Augmented Guardrails for AI-Drafted Patient-Portal Messages: Error Taxonomy Construction and Large-Scale Evaluation W. Chen, Fateme Nateghi, K.C. Black, F. Grolleau, E. Alsentzer, J.H. Chen, et al. arXiv preprint, 2025 [arXiv] |
 | A Multi-Site Machine Learning Model for Predicting Treatment Retention in Opioid Use Disorder Fateme Nateghi, Sajjad Fouladvand, Steven Tate, Min Min Chan, Joannas Jie Lin Yeow, Kira Griffiths, Ivan Lopez, Jeremiah W. Bertz, Adam Miner, Tina Hernandez-Boussard, Chwen-Yuen Angie Chen, Huiqiong Deng, Keith Humphreys, Anna Lembke, Alexander Vance, Jonathan H. Chen Addiction, 2024 [Paper] / [GitHub] / [WebApp] |
 | Predicting Outcomes of Acute Kidney Injury Using Machine Learning Fateme Nateghi, Liesbeth Viaene, Hans Pottel, Wouter De Corte, Celine Vens Scientific Reports, 2023 [Paper] / [GitHub] |
 | Predicting Survival Outcomes in the Presence of Unlabeled Data Fateme Nateghi, Celine Vens Machine Learning, 2022 [Paper] / [GitHub] |
 | Clinical Entity-Augmented Retrieval for Clinical Information Extraction (CLEAR) I. Lopez, A. Swaminathan, K. Vedula, S. Narayanan, Fateme Nateghi npj Digital Medicine, 2025 [Paper] / [GitHub] |
 | Embedding-Driven Diversity Sampling to Improve Few-Shot Synthetic Data Generation I. Lopez, Fateme Nateghi, K. Caoili, J.H. Chen, A. Chaudhari arXiv preprint, 2025 [arXiv] |
 | MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks Suhana Bedi, ..., Fateme Nateghi, Jonathan H. Chen, Nigam H. Shah, et al. arXiv, 2025 [Paper] / [Med-HELM Docs] / [Live Benchmark] |
 | Deconver: A Deconvolutional Network for Medical Image Segmentation P. Ashtari, S. Noei, Fateme Nateghi, J.H. Chen, G. Jurman, A. Pizurica arXiv preprint, 2025 [arXiv] / [GitHub] |
 | Quantization-Free Lossy Image Compression Using Integer Matrix Factorization P. Ashtari, P. Behmandpoor, Fateme Nateghi, J.H. Chen, P. Patrinos arXiv preprint, 2024 [arXiv] / [GitHub] |
 | Supervised Fuzzy Partitioning P. Ashtari, Fateme Nateghi, H. Beigy Pattern Recognition, 2020 [Paper] |