Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/26489
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jochems, Arthur | - |
dc.contributor.author | Deist, Timo M. | - |
dc.contributor.author | Van Soest, Johan | - |
dc.contributor.author | Eble, Michael | - |
dc.contributor.author | BULENS, Paul | - |
dc.contributor.author | Coucke, Philippe | - |
dc.contributor.author | Dries, Wim | - |
dc.contributor.author | Lambin, Philippe | - |
dc.contributor.author | Dekker, Andre | - |
dc.date.accessioned | 2018-07-30T15:23:38Z | - |
dc.date.available | 2018-07-30T15:23:38Z | - |
dc.date.issued | 2016 | - |
dc.identifier.citation | RADIOTHERAPY AND ONCOLOGY, 121(3), p. 459-467 | - |
dc.identifier.issn | 0167-8140 | - |
dc.identifier.uri | http://hdl.handle.net/1942/26489 | - |
dc.description.abstract | Purpose: One of the major hurdles in enabling personalized medicine is obtaining sufficient patient data to feed into predictive models. Combining data originating from multiple hospitals is difficult because of ethical, legal, political, and administrative barriers associated with data sharing. In order to avoid these issues, a distributed learning approach can be used. Distributed learning is defined as learning from data without the data leaving the hospital. Patients and methods: Clinical data from 287 lung cancer patients, treated with curative intent with chemoradiation (CRT) or radiotherapy (RT) alone were collected from and stored in 5 different medical institutes (123 patients at MAASTRO (Netherlands, Dutch), 24 at Jessa (Belgium, Dutch), 34 at Liege (Belgium, Dutch and French), 48 at Aachen (Germany, German) and 58 at Eindhoven (Netherlands, Dutch)). A Bayesian network model is adapted for distributed learning (watch the animation: http://youtu.bei nQpqMIuHyOk). The model predicts dyspnea, which is a common side effect after radiotherapy treatment of lung cancer. Results: We show that it is possible to use the distributed learning approach to train a Bayesian network model on patient data originating from multiple hospitals without these data leaving the individual hospital. The AUC of the model is 0.61 (95%Cl, 0.51-0.70) on a 5-fold cross-validation and ranges from 0.59 to 0.71 on external validation sets. Conclusion: Distributed learning can allow the learning of predictive models on data originating from multiple hospitals while avoiding many of the data sharing barriers. Furthermore, the distributed learning approach can be used to extract and employ knowledge from routine patient data from multiple hospitals while being compliant to the various national and European privacy laws. (C) 2016 The Author(s). Published by Elsevier Ireland Ltd. | - |
dc.description.sponsorship | Authors acknowledge financial support from the Interreg grant euroCAT, the Dutch technology Foundation STW (grant no 10696 DuCAT & no P14-19 Radiomics STRaTegy), which is the applied science division of NWO, and the Technology Programme of the Ministry of Economic Affairs. Authors also acknowledge financial support from the EU 7th framework program (ARTFORCE - no 257144, REQUITE - no 601826), SME Phase 2 (EU proposal 673780 - RAIL), the European Program H2020-2015-17 (BD2Decide - PHC30-689715 and ImmunoSABR - no 733008), EUROSTARS (SeDI, CloudAtlas, DART), Kankeronderzoekfonds Limburg from the Health Foundation Limburg, Alpe d'HuZes-KWF (DESIGN) and the Dutch Cancer Society. We would like to thank Varian for providing the distributed learning manager and Wolfgang Wiessler for his dedicated support. | - |
dc.language.iso | en | - |
dc.rights | (C) 2016 The Author(s). Published by Elsevier Ireland Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). | - |
dc.subject.other | Bayesian networks; distributed learning; privacy preserving data-mining; dyspnea; machine learning | - |
dc.title | Distributed learning: Developing a predictive model based on data from multiple hospitals without data leaving the hospital - A real life proof of concept | - |
dc.type | Journal Contribution | - |
dc.identifier.epage | 467 | - |
dc.identifier.issue | 3 | - |
dc.identifier.spage | 459 | - |
dc.identifier.volume | 121 | - |
local.bibliographicCitation.jcat | A1 | - |
local.type.refereed | Refereed | - |
local.type.specified | Article | - |
local.class | dsPublValOverrule/internal_author_not_expected | - |
local.class | IncludeIn-ExcludeFrom-List/ExcludeFromFRIS | - |
dc.identifier.doi | 10.1016/j.radonc.2016.10.002 | - |
dc.identifier.isi | 000391905200018 | - |
item.contributor | Jochems, Arthur | - |
item.contributor | Deist, Timo M. | - |
item.contributor | Van Soest, Johan | - |
item.contributor | Eble, Michael | - |
item.contributor | BULENS, Paul | - |
item.contributor | Coucke, Philippe | - |
item.contributor | Dries, Wim | - |
item.contributor | Lambin, Philippe | - |
item.contributor | Dekker, Andre | - |
item.fulltext | With Fulltext | - |
item.accessRights | Open Access | - |
item.fullcitation | Jochems, Arthur; Deist, Timo M.; Van Soest, Johan; Eble, Michael; BULENS, Paul; Coucke, Philippe; Dries, Wim; Lambin, Philippe & Dekker, Andre (2016) Distributed learning: Developing a predictive model based on data from multiple hospitals without data leaving the hospital - A real life proof of concept. In: RADIOTHERAPY AND ONCOLOGY, 121(3), p. 459-467. | - |
crisitem.journal.issn | 0167-8140 | - |
crisitem.journal.eissn | 1879-0887 | - |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
JOchems.pdf | Published version | 821.65 kB | Adobe PDF | View/Open |
SCOPUSTM
Citations
50
checked on Sep 3, 2020
WEB OF SCIENCETM
Citations
117
checked on Oct 12, 2024
Page view(s)
76
checked on Sep 5, 2022
Download(s)
114
checked on Sep 5, 2022
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.