Výsledky vyhledávání - "Madhumita Sushil"

Akademický článek

Evaluating large language models as agents in the clinic

Autor: Nikita Mehandru, Brenda Y. Miao, Eduardo Rodriguez Almaraz, Madhumita Sushil, Atul J. Butte, Ahmed Alaa

Publikováno v: npj Digital Medicine, Vol 7, Iss 1, Pp 1-3 (2024)

Recent developments in large language models (LLMs) have unlocked opportunities for healthcare, from information synthesis to clinical decision support. These LLMs are not just capable of modeling language, but can also act as intelligent “agents�

Externí odkaz: https://doaj.org/article/d5c48901ff664ec585eb34e9723b1362

Zobrazit plný text záznamu

Bottom-up and top-down paradigms of artificial intelligence research approaches to healthcare data science using growing real-world big data

Autor: Michelle Wang, Madhumita Sushil, Brenda Y Miao, Atul J Butte

Publikováno v: Journal of the American Medical Informatics Association : JAMIA, vol 30, iss 7

Objectives As the real-world electronic health record (EHR) data continue to grow exponentially, novel methodologies involving artificial intelligence (AI) are becoming increasingly applied to enable efficient data-driven learning and, ultimately, to

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cf54caa4f3b17276c823c6b98d7ad24b
https://escholarship.org/uc/item/4gw936w8

Zobrazit plný text záznamu

Contextual explanation rules for neural clinical classifiers

Autor: Walter Daelemans, Madhumita Sushil, Simon Suster

Publikováno v: Proceedings of the 20th Workshop on Biomedical Language Processing
BioNLP@NAACL-HLT

Several previous studies on explanation for recurrent neural networks focus on approaches that find the most important input segments for a network as its explanations. In that case, the manner in which these input segments combine with each other to

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f04594589036ec34f51338fc17a1cee1
https://hdl.handle.net/10067/1836150151162165141

Zobrazit plný text záznamu

Are we there yet? Exploring clinical domain knowledge of BERT models

Autor: Simon Suster, Walter Daelemans, Madhumita Sushil

Publikováno v: BioNLP@NAACL-HLT
Proceedings of the 20th Workshop on Biomedical Language Processing

We explore whether state-of-the-art BERT models encode sufficient domain knowledge to correctly perform domain-specific inference. Although BERT implementations such as BioBERT are better at domain-based reasoning than those trained on general-domain

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a3ace79b598cb6a0b4eff1147ab6d866
https://doi.org/10.18653/v1/2021.bionlp-1.5

Zobrazit plný text záznamu

Counting trees in Random Forests: Predicting symptom severity in psychiatric intake reports

Autor: Stéphan Tulkens, Walter Daelemans, Elyne Scheurwegs, Kim Luyckx, Madhumita Sushil

Publikováno v: Journal of biomedical informatics

The CEGS N-GRID 2016 Shared Task (Filannino et al., 2017) in Clinical Natural Language Processing introduces the assignment of a severity score to a psychiatric symptom, based on a psychiatric intake report. We present a method that employs the inher

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::14de715a60e8ac1c3fe41111368e6f8f
https://doi.org/10.1016/j.jbi.2017.06.007

Zobrazit plný text záznamu

Patient representation learning and interpretable evaluation using clinical notes

Autor: Walter Daelemans, Kim Luyckx, Madhumita Sushil, Simon Suster

Publikováno v: Journal of biomedical informatics

We have three contributions in this work: 1. We explore the utility of a stacked denoising autoencoder and a paragraph vector model to learn task-independent dense patient representations directly from clinical notes. To analyze if these representati

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::73252f8f70954842eb88bf3ae9ec1aa5

Zobrazit plný text záznamu

Revisiting neural relation classification in clinical notes with external information

Autor: Simon Suster, Madhumita Sushil, Walter Daelemans

Publikováno v: Louhi@EMNLP
University of Antwerp
Workshop on Health Text Mining and Information Analysis (LOUHI), workshop at EMNLP

Recently, segment convolutional neural networks have been proposed for end-to-end relation extraction in the clinical domain, achieving results comparable to or outperforming the approaches with heavy manual feature engineering. In this paper, we ana

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::001b28b2c0488ee66bcaf1f38f016372
https://doi.org/10.18653/v1/w18-5603

Zobrazit plný text záznamu

Unsupervised patient representations from clinical notes with interpretable classification decisions

Autor: Madhumita Sushil, Simon Šuster, Kim Luyckx, Walter Daelemans

Publikováno v: University of Antwerp

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::7e21a1293b50819ba1cb763156542d0b
https://hdl.handle.net/10067/1478370151162165141

Zobrazit plný text záznamu

Rule induction for global explanation of trained models

Autor: Walter Daelemans, Madhumita Sushil, Simon Suster

Publikováno v: University of Antwerp
BlackboxNLP@EMNLP
Analyzing and interpreting neural networks for NLP (BlackBoxNLP), workshop at EMNLP

Understanding the behavior of a trained network and finding explanations for its outputs is important for improving the network's performance and generalization ability, and for ensuring trust in automated systems. Several approaches have previously

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::acdbe25e4f419f3687c3400bcc4188a2
https://hdl.handle.net/10067/1560850151162165141

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání