T
Tristan Naumann
Researcher at Microsoft
Publications - 47
Citations - 3893
Tristan Naumann is an academic researcher from Microsoft. The author has contributed to research in topics: Health care & Computer science. The author has an hindex of 21, co-authored 46 publications receiving 1878 citations. Previous affiliations of Tristan Naumann include Massachusetts Institute of Technology & Tufts University.
Papers
More filters
Proceedings ArticleDOI
Publicly Available Clinical BERT Embeddings
Emily Alsentzer,John Murphy,William Boag,Wei-Hung Weng,Di Jindi,Tristan Naumann,Matthew B. A. McDermott +6 more
TL;DR: This paper explored and released BERT models for clinical text: one for generic clinical text and another for discharge summaries specifically, and demonstrated that using a domain-specific model yields performance improvements on 3/5 clinical NLP tasks, establishing a new state-of-the-art on the MedNLI dataset.
Journal ArticleDOI
Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing
Yu Gu,Robert Tinn,Hao Cheng,Michael Lucas,Naoto Usuyama,Xiaodong Liu,Tristan Naumann,Jianfeng Gao,Hoifung Poon +8 more
TL;DR: It is shown that for domains with abundant unlabeled text, such as biomedicine, pretraining language models from scratch results in substantial gains over continual pretraining of general-domain language models.
Posted Content
Publicly Available Clinical BERT Embeddings
Emily Alsentzer,John Murphy,Willie Boag,Wei-Hung Weng,Di Jin,Tristan Naumann,Matthew B. A. McDermott +6 more
TL;DR: This work explores and releases two BERT models for clinical text: one for generic clinical text and another for discharge summaries specifically, and demonstrates that using a domain-specific model yields performance improvements on 3/5 clinical NLP tasks, establishing a new state-of-the-art on the MedNLI dataset.
Proceedings ArticleDOI
Unfolding physiological state: mortality modelling in intensive care units
Marzyeh Ghassemi,Tristan Naumann,Finale Doshi-Velez,Nicole J. Brimmer,Rohit Joshi,Anna Rumshisky,Peter Szolovits +6 more
TL;DR: This work examined the use of latent variable models to decompose free-text hospital notes into meaningful features, and found that latent topic-derived features were effective in determining patient mortality under three timelines: in-hospital, 30 day post- Discharge, and 1 year post-discharge mortality.
Proceedings Article
A multivariate timeseries modeling approach to severity of illness assessment and forecasting in ICU with sparse, heterogeneous clinical data
Marzyeh Ghassemi,Marco A. F. Pimentel,Tristan Naumann,Thomas Brennan,David A. Clifton,Peter Szolovits,Mengling Feng +6 more
TL;DR: This work evaluates the use of multivariate timeseries modeling with the multi-task Gaussian process (GP) models using noisy, incomplete, sparse, heterogeneous and unevenly-sampled clinical data, including both physiological signals and clinical notes to assess and forecast patient acuity.