Change search
ReferencesLink to record
Permanent link

Direct link
Ensembles of randomized trees using diverse distributed representations of clinical events
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.
Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
2016 (English)In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 16, 69Article in journal (Refereed) Published
Abstract [en]

Background: Learning deep representations of clinical events based on their distributions in electronic health records has been shown to allow for subsequent training of higher-performing predictive models compared to the use of shallow, count-based representations. The predictive performance may be further improved by utilizing multiple representations of the same events, which can be obtained by, for instance, manipulating the representation learning procedure. The question, however, remains how to make best use of a set of diverse representations of clinical events – modeled in an ensemble of semantic spaces – for the purpose of predictive modeling. Methods: Three different ways of exploiting a set of (ten) distributed representations of four types of clinical events – diagnosis codes, drug codes, measurements, and words in clinical notes – are investigated in a series of experiments using ensembles of randomized trees. Here, the semantic space ensembles are obtained by varying the context window size in the representation learning procedure. The proposed method trains a forest wherein each tree is built from a bootstrap replicate of the training set whose entire original feature set is represented in a randomly selected set of semantic spaces – corresponding to the considered data types – of a given context window size. Results: The proposed method significantly outperforms concatenating the multiple representations of the bagged dataset; it also significantly outperforms representing, for each decision tree, only a subset of the features in a randomly selected set of semantic spaces. A follow-up analysis indicates that the proposed method exhibits less diversity while significantly improving average tree performance. It is also shown that the size of the semantic space ensemble has a significant impact on predictive performance and that performance tends to improve as the size increases. Conclusions: The strategy for utilizing a set of diverse distributed representations of clinical events when constructing ensembles of randomized trees has a significant impact on predictive performance. The most successful strategy – significantly outperforming the considered alternatives – involves randomly sampling distributed representations of the clinical events when building each decision tree in the forest.

Place, publisher, year, edition, pages
2016. Vol. 16, 69
Keyword [en]
Random forest, Distributional semantics, Heterogeneous data, Electronic health records, Pharmacovigilance, Adverse drug events
National Category
Information Systems
Research subject
Computer and Systems Sciences
Identifiers
URN: urn:nbn:se:su:diva-136587DOI: 10.1186/s12911-016-0309-0OAI: oai:DiVA.org:su-136587DiVA: diva2:1055451
Conference
IEEE International Conference on Bioinformatics and Biomedicine 2015, Washington, DC, USA, 9-12 November 2015
Available from: 2016-12-12 Created: 2016-12-12 Last updated: 2016-12-15Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full text

Search in DiVA

By author/editor
Henriksson, AronZhao, JingDalianis, HerculesBoström, Henrik
By organisation
Department of Computer and Systems Sciences
In the same journal
BMC Medical Informatics and Decision Making
Information Systems

Search outside of DiVA

GoogleGoogle Scholar

Altmetric score

Total: 6 hits
ReferencesLink to record
Permanent link

Direct link