Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorBardak B.-
dc.contributor.authorTan, Mehmet-
dc.identifier.citationBardak, B., & Tan, M. (2021, October). Using Clinical Drug Representations for Improving Mortality and Length of Stay Predictions. In 2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB) (pp. 1-8). IEEE.en_US
dc.description2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2021 -- 13 October 2021 through 15 October 2021 -- -- 176925en_US
dc.description.abstractDrug representations have played an important role in cheminformatics. However, in the healthcare domain, drug representations have been underused relative to the rest of Electronic Health Record (EHR) data, due to the complexity of high dimensional drug representations and the lack of proper pipeline that will allow to convert clinical drugs to their representations. Time-varying vital signs, laboratory measurements, and related time-series signals are commonly used to predict clinical outcomes. In this work, we demonstrated that using clinical drug representations in addition to other clinical features has significant potential to increase the performance of mortality and length of stay (LOS) models. We evaluate the two different drug representation methods (Extended-Connectivity Fingerprint-ECFP and SMILES-Transformer embedding) on clinical outcome predictions. The results have shown that the proposed multimodal approach achieves substantial enhancement on clinical tasks over baseline models. Using clinical drug representations as additional features improve the LOS prediction for Area Under the Receiver Operating Characteristics (AUROC) around %6 and for Area Under Precision-Recall Curve (AUPRC) by around %5. Furthermore, for the mortality prediction task, there is an improvement of around %2 over the time series baseline in terms of AUROC and %3.5 in terms of AUPRC. The code for the proposed method is available at © 2021 IEEE.en_US
dc.description.sponsorship:120E173; Türkiye Bilimsel ve Teknolojik Araştirma Kurumu, TÜBITAKen_US
dc.description.sponsorshipThis study has been partially funded by The Scientific and Technological Research Council of Turkey (TUBITAK), Grant Number:120E173.en_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartof2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2021en_US
dc.subjectClinical drug representationen_US
dc.subjectClinical tasken_US
dc.subjectDeep learningen_US
dc.subjectDeep learningen_US
dc.subjectTime seriesen_US
dc.subjectClinical drug representationen_US
dc.subjectClinical drugsen_US
dc.subjectClinical outcomeen_US
dc.subjectClinical tasksen_US
dc.subjectDeep learningen_US
dc.subjectHealthcare domainsen_US
dc.subjectLength of stayen_US
dc.subjectReceiver operating characteristicsen_US
dc.subjectHealth careen_US
dc.titleUsing clinical drug representations for improving mortality and length of stay predictionsen_US
dc.typeConference Objecten_US
dc.departmentFakülteler, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümüen_US
dc.departmentFaculties, Faculty of Engineering, Department of Computer Engineeringen_US
dc.institutionauthorTan, Mehmet-
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
item.fulltextNo Fulltext-
item.openairetypeConference Object- Department of Computer Engineering-
Appears in Collections:Bilgisayar Mühendisliği Bölümü / Department of Computer Engineering
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection
Show simple item record

CORE Recommender

Page view(s)

checked on Mar 27, 2023

Google ScholarTM



Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.