File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: An Integrated Approach of Machine Learning and Systems Thinking for Waiting Time Prediction in an Emergency Department

TitleAn Integrated Approach of Machine Learning and Systems Thinking for Waiting Time Prediction in an Emergency Department
Authors
Keywordsemergency departments
waiting time
machine learning
artificial intelligence
systems thinking
Issue Date2020
PublisherElsevier Ireland Ltd. The Journal's web site is located at http://www.elsevier.com/locate/ijmedinf
Citation
International Journal of Medical Informatics, 2020, v. 139, p. article no. 104143 How to Cite?
AbstractObjective: The objective of this study is to apply machine learning algorithms for real-time and personalized waiting time prediction in emergency departments. We also aim to introduce the concept of systems thinking to enhance the performance of the prediction models. Methods: Four popular algorithms were applied: (i) stepwise multiple linear regression; (ii) artificial neural networks; (iii) support vector machines; and (iv) gradient boosting machines. A linear regression model served as a baseline model for comparison. We conducted computational experiments based on a dataset collected from an emergency department in Hong Kong. Model diagnostics were performed, and the results were cross-validated. Results: All the four machine learning algorithms with the use of systems knowledge outperformed the baseline model. The stepwise multiple linear regression reduced the mean-square error by almost 15%. The other three algorithms had similar performances, reducing the mean-square error by approximately 20%. Reductions of 17 – 22% in mean-square error due to the utilization of systems knowledge were observed. Discussion: The multi-dimensional stochasticity arising from the ED environment imposes a great challenge on waiting time prediction. The introduction of the concept of systems thinking led to significant enhancements of the models, suggesting that interdisciplinary efforts could potentially improve prediction performance. Conclusion: Machine learning algorithms with the utilization of the systems knowledge could significantly improve the performance of waiting time prediction. Waiting time prediction for less urgent patients is more challenging.
Persistent Identifierhttp://hdl.handle.net/10722/282918
ISSN
2020 Impact Factor: 4.046
2020 SCImago Journal Rankings: 1.124
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorKuo, YH-
dc.contributor.authorChan, NB-
dc.contributor.authorLeung, JMY-
dc.contributor.authorMeng, H-
dc.contributor.authorSo, AMC-
dc.contributor.authorTsoi, KKF-
dc.contributor.authorGraham, CA-
dc.date.accessioned2020-06-05T06:23:03Z-
dc.date.available2020-06-05T06:23:03Z-
dc.date.issued2020-
dc.identifier.citationInternational Journal of Medical Informatics, 2020, v. 139, p. article no. 104143-
dc.identifier.issn1386-5056-
dc.identifier.urihttp://hdl.handle.net/10722/282918-
dc.description.abstractObjective: The objective of this study is to apply machine learning algorithms for real-time and personalized waiting time prediction in emergency departments. We also aim to introduce the concept of systems thinking to enhance the performance of the prediction models. Methods: Four popular algorithms were applied: (i) stepwise multiple linear regression; (ii) artificial neural networks; (iii) support vector machines; and (iv) gradient boosting machines. A linear regression model served as a baseline model for comparison. We conducted computational experiments based on a dataset collected from an emergency department in Hong Kong. Model diagnostics were performed, and the results were cross-validated. Results: All the four machine learning algorithms with the use of systems knowledge outperformed the baseline model. The stepwise multiple linear regression reduced the mean-square error by almost 15%. The other three algorithms had similar performances, reducing the mean-square error by approximately 20%. Reductions of 17 – 22% in mean-square error due to the utilization of systems knowledge were observed. Discussion: The multi-dimensional stochasticity arising from the ED environment imposes a great challenge on waiting time prediction. The introduction of the concept of systems thinking led to significant enhancements of the models, suggesting that interdisciplinary efforts could potentially improve prediction performance. Conclusion: Machine learning algorithms with the utilization of the systems knowledge could significantly improve the performance of waiting time prediction. Waiting time prediction for less urgent patients is more challenging.-
dc.languageeng-
dc.publisherElsevier Ireland Ltd. The Journal's web site is located at http://www.elsevier.com/locate/ijmedinf-
dc.relation.ispartofInternational Journal of Medical Informatics-
dc.subjectemergency departments-
dc.subjectwaiting time-
dc.subjectmachine learning-
dc.subjectartificial intelligence-
dc.subjectsystems thinking-
dc.titleAn Integrated Approach of Machine Learning and Systems Thinking for Waiting Time Prediction in an Emergency Department-
dc.typeArticle-
dc.identifier.emailKuo, YH: yhkuo@hku.hk-
dc.identifier.authorityKuo, YH=rp02314-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.ijmedinf.2020.104143-
dc.identifier.pmid32330853-
dc.identifier.scopuseid_2-s2.0-85083437884-
dc.identifier.hkuros310031-
dc.identifier.volume139-
dc.identifier.spagearticle no. 104143-
dc.identifier.epagearticle no. 104143-
dc.identifier.isiWOS:000569077400004-
dc.publisher.placeIreland-
dc.identifier.issnl1386-5056-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats