File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: A clinically actionable and explainable real-time risk assessment framework for stroke-associated pneumonia

TitleA clinically actionable and explainable real-time risk assessment framework for stroke-associated pneumonia
Authors
KeywordsContinuous prediction
Deep learning
Early disease detection
Integrated gradients
Transformer
Issue Date20-Jan-2024
PublisherElsevier
Citation
Artificial Intelligence in Medicine, 2024, v. 149 How to Cite?
Abstract

The current medical practice is more responsive rather than proactive, despite the widely recognized value of early disease detection, including improving the quality of care and reducing medical costs. One of the cornerstones of early disease detection is clinically actionable predictions, where predictions are expected to be accurate, stable, real-time and interpretable. As an example, we used stroke-associated pneumonia (SAP), setting up a transformer-encoder-based model that analyzes highly heterogeneous electronic health records in real-time. The model was proven accurate and stable on an independent test set. In addition, it issued at least one warning for 98.6 % of SAP patients, and on average, its alerts were ahead of physician diagnoses by 2.71 days. We applied Integrated Gradient to glean the model's reasoning process. Supplementing the risk scores, the model highlighted critical historical events on patients' trajectories, which were shown to have high clinical relevance.

    ​​​​​​​

Persistent Identifierhttp://hdl.handle.net/10722/340095
ISSN
2023 Impact Factor: 6.1
2023 SCImago Journal Rankings: 1.723
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorDai, Lutao-
dc.contributor.authorYang, Xin-
dc.contributor.authorLi, Hao-
dc.contributor.authorZhao, Xingquan-
dc.contributor.authorLin, Lin-
dc.contributor.authorJiang, Yong-
dc.contributor.authorWang, Yongjun-
dc.contributor.authorLi, Zixiao-
dc.contributor.authorShen, Haipeng-
dc.date.accessioned2024-03-11T10:41:37Z-
dc.date.available2024-03-11T10:41:37Z-
dc.date.issued2024-01-20-
dc.identifier.citationArtificial Intelligence in Medicine, 2024, v. 149-
dc.identifier.issn0933-3657-
dc.identifier.urihttp://hdl.handle.net/10722/340095-
dc.description.abstract<p>The current <a href="https://www-sciencedirect-com.eproxy.lib.hku.hk/topics/computer-science/medical-practice" title="Learn more about medical practice from ScienceDirect's AI-generated Topic Pages">medical practice</a> is more responsive rather than proactive, despite the widely recognized value of early disease detection, including improving the quality of care and reducing medical costs. One of the cornerstones of early disease detection is clinically actionable predictions, where predictions are expected to be accurate, stable, real-time and interpretable. As an example, we used stroke-associated pneumonia (SAP), setting up a transformer-encoder-based model that analyzes highly heterogeneous <a href="https://www-sciencedirect-com.eproxy.lib.hku.hk/topics/medicine-and-dentistry/electronic-health-record" title="Learn more about electronic health records from ScienceDirect's AI-generated Topic Pages">electronic health records</a> in real-time. The model was proven accurate and stable on an independent test set. In addition, it issued at least one warning for 98.6 % of SAP patients, and on average, its alerts were ahead of physician diagnoses by 2.71 days. We applied Integrated Gradient to glean the model's reasoning process. Supplementing the risk scores, the model highlighted critical historical events on patients' trajectories, which were shown to have high clinical relevance.</p><ul>​​​​​​​</ul>-
dc.languageeng-
dc.publisherElsevier-
dc.relation.ispartofArtificial Intelligence in Medicine-
dc.subjectContinuous prediction-
dc.subjectDeep learning-
dc.subjectEarly disease detection-
dc.subjectIntegrated gradients-
dc.subjectTransformer-
dc.titleA clinically actionable and explainable real-time risk assessment framework for stroke-associated pneumonia-
dc.typeArticle-
dc.identifier.doi10.1016/j.artmed.2024.102772-
dc.identifier.scopuseid_2-s2.0-85183968072-
dc.identifier.volume149-
dc.identifier.eissn1873-2860-
dc.identifier.isiWOS:001175491200001-
dc.identifier.issnl0933-3657-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats