papers

Publications (6)

cs.CL2018

Development of deep learning algorithms to categorize free-text notes pertaining to diabetes: convolution neural networks achieve higher accuracy than support vector machines

Boyi Yang, Adam Wright

Health professionals can use natural language processing (NLP) technologies when reviewing electronic health records (EHR). Machine learning free-text classifiers can help them ide…

astro-ph.CO2014

Robust Weak-lensing Mass Calibration of Planck Galaxy Clusters

Anja von der Linden, Adam Mantz, Steven W. Allen +9

In light of the tension in cosmological constraints reported by the Planck team between their SZ-selected cluster counts and Cosmic Microwave Background (CMB) temperature anisotrop…

astro-ph.CO2021

Cosmological Constraints from Gas Mass Fractions of Massive, Relaxed Galaxy Clusters

Adam B. Mantz, Steven W. Allen, Rebecca E. A. Canning +14

We present updated cosmological constraints from measurements of the gas mass fractions () of massive, dynamically relaxed galaxy clusters. Our new data set has greater le…

cs.AI2026

An artificial intelligence framework for end-to-end rare disease phenotyping from clinical notes using large language models

Cathy Shyr, Yan Hu, Rory J. Tinker +8

Phenotyping is fundamental to rare disease diagnosis, but manual curation of structured phenotypes from clinical notes is labor-intensive and difficult to scale. Existing artificia…

astro-ph.CO2014

Weighing the Giants IV: Cosmology and Neutrino Mass

Adam B. Mantz, Anja von der Linden, Steven W. Allen +14

We employ robust weak gravitational lensing measurements to improve cosmological constraints from measurements of the galaxy cluster mass function and its evolution, using X-ray se…

cs.AI2026

Teaching agentic AI to learn expert reasoning for rare disease diagnosis

Minh-Ha Nguyen, Erica Gray, Bryce A. Schuler +16

Rare disease diagnosis depends on expert reasoning that is scarce and difficult to transfer; off-the-shelf large language models (LLMs) rank the correct disease first in only 35.4%…