Neighborhood Optimization for Therapy Decision Support
This work targets the development of a neighborhood-based Collaborative Filtering therapy recommender system for clinical decision support. The proposed algorithm estimates outcome of pharmaceutical therapy options in order to derive recommendations. Two approaches, namely a Relief-based algorithm a...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
De Gruyter
2019-09-01
|
Series: | Current Directions in Biomedical Engineering |
Subjects: | |
Online Access: | https://doi.org/10.1515/cdbme-2019-0001 |
_version_ | 1797989282115223552 |
---|---|
author | Gräßer Felix Malberg Hagen Zaunseder Sebastian |
author_facet | Gräßer Felix Malberg Hagen Zaunseder Sebastian |
author_sort | Gräßer Felix |
collection | DOAJ |
description | This work targets the development of a neighborhood-based Collaborative Filtering therapy recommender system for clinical decision support. The proposed algorithm estimates outcome of pharmaceutical therapy options in order to derive recommendations. Two approaches, namely a Relief-based algorithm and a metric learning approach are investigated. Both adapt similarity functions to the underlying data in order to determine the neighborhood incorporated into the filtering process. The implemented approaches are evaluated regarding the accuracy of the outcome estimations. The metric learning approach can outperform the Relief-based algorithms. It is, however, inferior regarding explainability of the generated recommendations. |
first_indexed | 2024-04-11T08:17:46Z |
format | Article |
id | doaj.art-255fefeecadf40b690efe2b3cce67f9d |
institution | Directory Open Access Journal |
issn | 2364-5504 |
language | English |
last_indexed | 2024-04-11T08:17:46Z |
publishDate | 2019-09-01 |
publisher | De Gruyter |
record_format | Article |
series | Current Directions in Biomedical Engineering |
spelling | doaj.art-255fefeecadf40b690efe2b3cce67f9d2022-12-22T04:35:04ZengDe GruyterCurrent Directions in Biomedical Engineering2364-55042019-09-01511410.1515/cdbme-2019-0001cdbme-2019-0001Neighborhood Optimization for Therapy Decision SupportGräßer Felix0Malberg Hagen1Zaunseder Sebastian2Institute of Biomedical Engineering, Technical University Dresden,Dresden, GermanyInstitute of Biomedical Engineering, Technical University Dresden,Dresden, GermanyDepartment of Information Technology, University of Applied Sciences and Arts Dortmund,Dortmund, GermanyThis work targets the development of a neighborhood-based Collaborative Filtering therapy recommender system for clinical decision support. The proposed algorithm estimates outcome of pharmaceutical therapy options in order to derive recommendations. Two approaches, namely a Relief-based algorithm and a metric learning approach are investigated. Both adapt similarity functions to the underlying data in order to determine the neighborhood incorporated into the filtering process. The implemented approaches are evaluated regarding the accuracy of the outcome estimations. The metric learning approach can outperform the Relief-based algorithms. It is, however, inferior regarding explainability of the generated recommendations.https://doi.org/10.1515/cdbme-2019-0001clinical decision support systemcdsstherapy recommender systemneighborhood optimization |
spellingShingle | Gräßer Felix Malberg Hagen Zaunseder Sebastian Neighborhood Optimization for Therapy Decision Support Current Directions in Biomedical Engineering clinical decision support system cdss therapy recommender system neighborhood optimization |
title | Neighborhood Optimization for Therapy Decision Support |
title_full | Neighborhood Optimization for Therapy Decision Support |
title_fullStr | Neighborhood Optimization for Therapy Decision Support |
title_full_unstemmed | Neighborhood Optimization for Therapy Decision Support |
title_short | Neighborhood Optimization for Therapy Decision Support |
title_sort | neighborhood optimization for therapy decision support |
topic | clinical decision support system cdss therapy recommender system neighborhood optimization |
url | https://doi.org/10.1515/cdbme-2019-0001 |
work_keys_str_mv | AT graßerfelix neighborhoodoptimizationfortherapydecisionsupport AT malberghagen neighborhoodoptimizationfortherapydecisionsupport AT zaunsedersebastian neighborhoodoptimizationfortherapydecisionsupport |