Clinical decision support systems based on machine learning are a rising application in healthcare. Early detection of deteriorating conditions provide the opportunity for medical intervention in hospital patients. Recent approaches increasingly rely on Large Language Models such as BERT, because patient data is often in the form of structured temporal data. These models are notoriously hard to interpret and therefore to trust, while precisely trust is an essential principle for technology in healthcare. We develop a visual analytics system to inspect, compare, and explain pre-trained transformer models for a given clinical outcome prediction task. The work is developed on the basis of a large hospital patient dataset and prediction tasks for acute kidney injury and heart failure. Discussion with healthcare professionals confirms that our system can lead to a faster decision process and improved modeling results.
Description
Multi-Task Transformer Visualization to build Trust for Clinical Outcome Prediction | IEEE Conference Publication | IEEE Xplore
%0 Conference Paper
%1 10356804
%A Antweiler, Dario
%A Gallusser, Florian
%A Fuchs, Georg
%B 2023 Workshop on Visual Analytics in Healthcare (VAHC)
%D 2023
%K myown clinical_outcome_prediction from:fgallusser
%P 21-26
%R 10.1109/VAHC60858.2023.00010
%T Multi-Task Transformer Visualization to build Trust for Clinical Outcome Prediction
%X Clinical decision support systems based on machine learning are a rising application in healthcare. Early detection of deteriorating conditions provide the opportunity for medical intervention in hospital patients. Recent approaches increasingly rely on Large Language Models such as BERT, because patient data is often in the form of structured temporal data. These models are notoriously hard to interpret and therefore to trust, while precisely trust is an essential principle for technology in healthcare. We develop a visual analytics system to inspect, compare, and explain pre-trained transformer models for a given clinical outcome prediction task. The work is developed on the basis of a large hospital patient dataset and prediction tasks for acute kidney injury and heart failure. Discussion with healthcare professionals confirms that our system can lead to a faster decision process and improved modeling results.
@inproceedings{10356804,
abstract = {Clinical decision support systems based on machine learning are a rising application in healthcare. Early detection of deteriorating conditions provide the opportunity for medical intervention in hospital patients. Recent approaches increasingly rely on Large Language Models such as BERT, because patient data is often in the form of structured temporal data. These models are notoriously hard to interpret and therefore to trust, while precisely trust is an essential principle for technology in healthcare. We develop a visual analytics system to inspect, compare, and explain pre-trained transformer models for a given clinical outcome prediction task. The work is developed on the basis of a large hospital patient dataset and prediction tasks for acute kidney injury and heart failure. Discussion with healthcare professionals confirms that our system can lead to a faster decision process and improved modeling results.},
added-at = {2024-04-19T03:25:11.000+0200},
author = {Antweiler, Dario and Gallusser, Florian and Fuchs, Georg},
biburl = {https://www.bibsonomy.org/bibtex/203e1ef662a9f41abb3d295ac669f20cb/dmir},
booktitle = {2023 Workshop on Visual Analytics in Healthcare (VAHC)},
description = {Multi-Task Transformer Visualization to build Trust for Clinical Outcome Prediction | IEEE Conference Publication | IEEE Xplore},
doi = {10.1109/VAHC60858.2023.00010},
interhash = {b9be64661151ecc91657c52c4442adcb},
intrahash = {03e1ef662a9f41abb3d295ac669f20cb},
issn = {2771-6538},
keywords = {myown clinical_outcome_prediction from:fgallusser},
month = {10},
pages = {21-26},
timestamp = {2024-04-19T03:25:11.000+0200},
title = {Multi-Task Transformer Visualization to build Trust for Clinical Outcome Prediction},
year = 2023
}