Predicting non-attendance in hospital outpatient appointments using deep learning approach

The hospital outpatient non-attendance imposes a substantial financial burden on hospitals and roots in multiple diverse reasons. This research aims to build an advanced predictive model for predicting non-attendance regarding the whole spectrum of probable contributing factors to non-attendance tha...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Health Systems Jg. 11; H. 3; S. 189 - 210
Hauptverfasser: Dashtban, M., Li, Weizi
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Taylor & Francis 03.07.2022
Informa UK Limited
Schlagworte:
deep learning
electronic patients records
health care
machine learning
No-show patients
Original
Original Articles
outpatient appointment
prediction
ISSN:2047-6965, 2047-6973
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The hospital outpatient non-attendance imposes a substantial financial burden on hospitals and roots in multiple diverse reasons. This research aims to build an advanced predictive model for predicting non-attendance regarding the whole spectrum of probable contributing factors to non-attendance that could be collated from heterogeneous sources including electronic patients records and external non-hospital data. We proposed a new non-attendance prediction model based on deep neural networks and machine learning models. The proposed approach works upon sparse stacked denoising autoencoders (SDAEs) to learn the underlying manifold of data and thereby compacting information and providing a better representation that can be utilised afterwards by other learning models as well. The proposed approach is evaluated over real hospital data and compared with several well-known and scalable machine learning models. The evaluation results reveal the proposed approach with softmax layer and logistic regression outperforms other methods in practice.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2047-6965
2047-6973
DOI:10.1080/20476965.2021.1924085