An explanatory machine learning framework for studying pandemics: The case of COVID-19 emergency department readmissions

Basit Öğe Kaydı
dc.authorid0000-0001-8857-5148
dc.authorid0000-0003-2885-6014
dc.authorscopusid57189870930
dc.authorscopusid56016604600
dc.authorscopusid55887961100
dc.authorwosidDTU-5282-2022
dc.authorwosidGJX-7858-2022
dc.authorwosidDVE-7234-2022
dc.contributor.authorDelen, Dursun
dc.contributor.authorDelen, Dursun
dc.contributor.authorDavazdahemami, Behrooz
dc.contributor.authorZolbanin, Hamed M.
dc.contributor.authorDelen, Dursun
dc.contributor.otherYönetim Bilimleri Fakültesi, İşletme Bölümü
dc.contributor.otherYönetim Bilimleri Fakültesi, İşletme Bölümü
dc.date.accessioned2022-01-31T13:31:29Z
dc.date.available2022-01-31T13:31:29Z
dc.date.issued2022
dc.departmentİHÜ, Yönetim Bilimleri Fakültesi, İşletme Bölümü
dc.description.abstractOne of the major challenges that confront medical experts during a pandemic is the time required to identify and validate the risk factors of the novel disease and to develop an effective treatment protocol. Traditionally, this process involves numerous clinical trials that may take up to several years, during which strict preventive measures must be in place to control the outbreak and reduce the deaths. Advanced data analytics techniques, however, can be leveraged to guide and speed up this process. In this study, we combine evolutionary search algorithms, deep learning, and advanced model interpretation methods to develop a holistic exploratory- predictive-explanatory machine learning framework that can assist clinical decision-makers in reacting to the challenges of a pandemic in a timely manner. The proposed framework is showcased in studying emergency department (ED) readmissions of COVID-19 patients using ED visits from a real-world electronic health records database. After an exploratory feature selection phase using genetic algorithm, we develop and train a deep artificial neural network to predict early (i.e., 7-day) readmissions (AUC = 0.883). Lastly, a SHAP model is formulated to estimate additive Shapley values (i.e., importance scores) of the features and to interpret the magnitude and direction of their effects. The findings are mostly in line with those reported by lengthy and expensive clinical trial studies.
dc.identifier.citationDavazdahemami, B., Zolbanin, H. M. ve Delen, D. (2022). An explanatory machine learning framework for studying pandemics: The case of COVID-19 emergency department readmissions. Decision Support Systems, 161. https://doi.org/10.1016/j.dss.2022.113730
dc.identifier.doi10.1016/j.dss.2022.113730
dc.identifier.issn0167-9236
dc.identifier.issn1873-5797
dc.identifier.pmid35068629
dc.identifier.scopus2-s2.0-85123197338
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.1016/j.dss.2022.113730
dc.identifier.urihttps://hdl.handle.net/20.500.12154/1698
dc.identifier.volume161
dc.identifier.wosWOS:000848756600003
dc.identifier.wosqualityQ1
dc.indekslendigikaynakPubMed
dc.indekslendigikaynakScopus
dc.indekslendigikaynakWeb of Science
dc.institutionauthorDelen, Dursun
dc.institutionauthorid0000-0001-8857-5148
dc.language.isoen
dc.publisherElsevier
dc.relation.ihupublicationcategory114
dc.relation.ispartofDecision Support Systems
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectMachine Learning
dc.subjectPandemic
dc.subjectCOVID-19
dc.subjectSHAP
dc.subjectDeep Learning
dc.subjectGenetic Algorithm
dc.titleAn explanatory machine learning framework for studying pandemics: The case of COVID-19 emergency department readmissions
dc.typeArticle
dspace.entity.typePublication
relation.isAuthorOfPublicationde384c43-bcde-4ccb-a0b7-39ead0e59bd0
relation.isAuthorOfPublication.latestForDiscoveryde384c43-bcde-4ccb-a0b7-39ead0e59bd0
relation.isOrgUnitOfPublicationc9253b76-6094-4836-ac99-2fcd5392d68f
relation.isOrgUnitOfPublication.latestForDiscoveryc9253b76-6094-4836-ac99-2fcd5392d68f

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
delen_d.pdf
Boyut:
1.69 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
İsim:
license.txt
Boyut:
1.52 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

İşletme Bölümü Koleksiyonu
PubMed İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu