File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Development of an open-access and explainable machine learning prediction system to assess the mortality and recurrence risk factors of Clostridioides difficile infection patients

TitleDevelopment of an open-access and explainable machine learning prediction system to assess the mortality and recurrence risk factors of Clostridioides difficile infection patients
Authors
KeywordsClostridioides difficile
diarrhea
infections
machine learning
pseudomembranous colitis
Issue Date2021
PublisherWiley-VCH Verlag GmbH & Co. KGaA. The Journal's web site is located at https://onlinelibrary.wiley.com/journal/26404567
Citation
Advanced Intelligent Systems, 2021, v. 3 n. 1, p. article no. 2000188 How to Cite?
AbstractIdentifying Clostridioides difficile infection (CDI) patients at risk of mortality or recurrence facilitates prevention, timely treatment, and improves clinical outcomes. The aim herein is to establish an open‐access web‐based prediction system, which estimates CDI patients’ mortality and recurrence outcomes and explains machine learning prediction with patients’ characteristics. Prognostic models are developed using four various types of machine learning algorithms and the statistical logistics regression model utilizing over 15 000 CDI patients from 41 hospitals in Hong Kong. The boosting‐based machine learning algorithm gradient boosting machine (GBM) (Mortality AUC: 0.7878; Recurrence AUC: 0.7076) outperforms statistical models (Mortality AUC: 0.7573; Recurrence AUC: 0.6927) and other machine learning algorithms. As the difficulty to interpret complex machine learning results limits their use in the medical area, Shapley additive explanations (SHAP) are adapted to identify which features are crucial to the machine learning models and associate them with clinical findings. SHAP analysis shows that older age, reduced albumin levels, higher creatinine levels, and higher white blood cell count are the most highly associated mortality features, which is consistent with existing clinical findings. The open‐access prediction system for clinicians to assess and interpret the risk factors of CDI patients is now available at https://www.cdiml.care/.
Persistent Identifierhttp://hdl.handle.net/10722/290592
ISSN
2023 Impact Factor: 6.8
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorNG, YL-
dc.contributor.authorLO, MCK-
dc.contributor.authorLEE, KH-
dc.contributor.authorXie, X-
dc.contributor.authorKWONG, TNY-
dc.contributor.authorIP, M-
dc.contributor.authorZHANG, L.-
dc.contributor.authorYU, J-
dc.contributor.authorSUNG, JJY-
dc.contributor.authorWU, WKK-
dc.contributor.authorWONG, SH-
dc.contributor.authorKwok, KW-
dc.date.accessioned2020-11-02T05:44:25Z-
dc.date.available2020-11-02T05:44:25Z-
dc.date.issued2021-
dc.identifier.citationAdvanced Intelligent Systems, 2021, v. 3 n. 1, p. article no. 2000188-
dc.identifier.issn2640-4567-
dc.identifier.urihttp://hdl.handle.net/10722/290592-
dc.description.abstractIdentifying Clostridioides difficile infection (CDI) patients at risk of mortality or recurrence facilitates prevention, timely treatment, and improves clinical outcomes. The aim herein is to establish an open‐access web‐based prediction system, which estimates CDI patients’ mortality and recurrence outcomes and explains machine learning prediction with patients’ characteristics. Prognostic models are developed using four various types of machine learning algorithms and the statistical logistics regression model utilizing over 15 000 CDI patients from 41 hospitals in Hong Kong. The boosting‐based machine learning algorithm gradient boosting machine (GBM) (Mortality AUC: 0.7878; Recurrence AUC: 0.7076) outperforms statistical models (Mortality AUC: 0.7573; Recurrence AUC: 0.6927) and other machine learning algorithms. As the difficulty to interpret complex machine learning results limits their use in the medical area, Shapley additive explanations (SHAP) are adapted to identify which features are crucial to the machine learning models and associate them with clinical findings. SHAP analysis shows that older age, reduced albumin levels, higher creatinine levels, and higher white blood cell count are the most highly associated mortality features, which is consistent with existing clinical findings. The open‐access prediction system for clinicians to assess and interpret the risk factors of CDI patients is now available at https://www.cdiml.care/.-
dc.languageeng-
dc.publisherWiley-VCH Verlag GmbH & Co. KGaA. The Journal's web site is located at https://onlinelibrary.wiley.com/journal/26404567-
dc.relation.ispartofAdvanced Intelligent Systems-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.subjectClostridioides difficile-
dc.subjectdiarrhea-
dc.subjectinfections-
dc.subjectmachine learning-
dc.subjectpseudomembranous colitis-
dc.titleDevelopment of an open-access and explainable machine learning prediction system to assess the mortality and recurrence risk factors of Clostridioides difficile infection patients-
dc.typeArticle-
dc.identifier.emailKwok, KW: kwokkw@hku.hk-
dc.identifier.authorityKwok, KW=rp01924-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1002/aisy.202000188-
dc.identifier.hkuros318449-
dc.identifier.volume3-
dc.identifier.issue1-
dc.identifier.spagearticle no. 2000188-
dc.identifier.epagearticle no. 2000188-
dc.identifier.isiWOS:000669799200009-
dc.publisher.placeGermany-
dc.identifier.issnl2640-4567-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats