Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Cascading Adverse Drug Event Detection in Electronic Health Records
Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
2015 (English)In: 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA): Proceedings, IEEE Computer Society, 2015Conference paper, Published paper (Refereed)
Abstract [en]

The ability to detect adverse drug events (ADEs) in electronic health records (EHRs) is useful in many medical applications, such as alerting systems that indicate when an ADE-specific diagnosis code should be assigned. Automating the detection of ADEs can be attempted by applying machine learning to existing, labeled EHR data. How to do this in an effective manner is, however, an open question. The issues addressed in this study concern the granularity of the classification task: (1) If we wish to predict the occurrence of ADE, is it advantageous to conflate the various ADE class labels prior to learning, or should they be merged post prediction? (2) If we wish to predict a family of ADEs or even a specific ADE, can the predictive performance be enhanced by dividing the classification task into a cascading scheme: predicting first, on a coarse level, whether there is an ADE or not, and, in the former case, followed by a more specific prediction on which family the ADE belongs to, and then finally a prediction on the specific ADE within that particular family? In this study, we conduct a series of experiments using a real, clinical dataset comprising healthcare episodes that have been assigned one of eight ADE-related diagnosis codes and a set of randomly extracted episodes that have not been assigned any ADE code. It is shown that, when distinguishing between ADEs and non-ADEs, merging the various ADE labels prior to learning leads to significantly higher predictive performance in terms of accuracy and area under ROC curve. A cascade of random forests is moreover constructed to determine either the family of ADEs or the specific class label; here, the performance is indeed enhanced compared to directly employing a one-step prediction. This study concludes that, if predictive performance is of primary importance, the cascading scheme should be the recommended approach over employing a one-step prediction for detecting ADEs in EHRs.

Place, publisher, year, edition, pages
IEEE Computer Society, 2015.
Keyword [en]
electronic health records, adverse drug events, predictive modeling, cascading
National Category
Information Systems
Research subject
Computer and Systems Sciences
Identifiers
URN: urn:nbn:se:su:diva-122795DOI: 10.1109/DSAA.2015.7344869ISBN: 978-1-4673-8272-4 (print)ISBN: 978-1-4673-8273-1 (electronic)OAI: oai:DiVA.org:su-122795DiVA: diva2:868653
Conference
2015 IEEE International Conference on Data Science and Advanced Analytics, Paris, France, 19-21 October, 2015
Available from: 2015-11-11 Created: 2015-11-10 Last updated: 2017-01-30Bibliographically approved
In thesis
1. Learning Predictive Models from Electronic Health Records
Open this publication in new window or tab >>Learning Predictive Models from Electronic Health Records
2017 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

The ongoing digitization of healthcare, which has been much accelerated by the widespread adoption of electronic health records, generates unprecedented amounts of clinical data in a readily computable form. This, in turn, affords great opportunities for making meaningful secondary use of clinical data in the endeavor to improve healthcare, as well as to support epidemiology and medical research. To that end, there is a need for techniques capable of effectively and efficiently analyzing large amounts of clinical data. While machine learning provides the necessary tools, learning effective predictive models from electronic health records comes with many challenges due to the complexity of the data. Electronic health records contain heterogeneous and longitudinal data that jointly provides a rich perspective of patient trajectories in the healthcare process. The diverse characteristics of the data need to be properly accounted for when learning predictive models from clinical data. However, how best to represent healthcare data for predictive modeling has been insufficiently studied. This thesis addresses several of the technical challenges involved in learning effective predictive models from electronic health records.

Methods are developed to address the challenges of (i) representing heterogeneous types of data, (ii) leveraging the concept hierarchy of clinical codes, and (iii) modeling the temporality of clinical events. The proposed methods are evaluated empirically in the context of detecting adverse drug events in electronic health records. Various representations of each type of data that account for its unique characteristics are investigated and it is shown that combining multiple representations yields improved predictive performance. It is also demonstrated how the information embedded in the concept hierarchy of clinical codes can be exploited, both for creating enriched feature spaces and for decomposing the predictive task. Moreover, incorporating temporal information leads to more effective predictive models by distinguishing between event occurrences in the patient history. Both single-point representations, using pre-assigned or learned temporal weights, and multivariate time series representations are shown to be more informative than representations in which temporality is ignored. Effective methods for representing heterogeneous and longitudinal data are key for enhancing and truly enabling meaningful secondary use of electronic health records through large-scale analysis of clinical data.

Place, publisher, year, edition, pages
Stockholm: Department of Computer and Systems Sciences, Stockholm University, 2017. 82 p.
Series
Report Series / Department of Computer & Systems Sciences, ISSN 1101-8526 ; 17-001
Keyword
Data Science, Machine Learning, Predictive Modeling, Data Representation, Health Informatics, Electronic Health Records
National Category
Computer Science
Research subject
Computer and Systems Sciences
Identifiers
urn:nbn:se:su:diva-137936 (URN)978-91-7649-682-4 (ISBN)978-91-7649-683-1 (ISBN)
Public defence
2017-03-02, Lilla hörsalen, NOD-huset, Borgarfjordsgatan 12, Kista, 13:00 (English)
Opponent
Supervisors
Available from: 2017-02-07 Created: 2017-01-13 Last updated: 2017-02-08Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full text

Search in DiVA

By author/editor
Zhao, JingHenriksson, AronBoström, Henrik
By organisation
Department of Computer and Systems Sciences
Information Systems

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 22 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf