|Publication type:||Conference paper|
|Type of review:||Peer review (abstract)|
|Title:||Bayesian networks to disentangle the interplay of intracranial aneurysm rupture risk factors|
Spinner, Georg Ralph
Friedrich, Christoph M.
|Proceedings:||CMBE 2022 : 7th International Conference on Computational & Mathematical Biomedical Engineering|
|Editors of the parent work:||Nithiarasu, Perumal|
|Conference details:||7th International Conference on Computational and Mathematical Biomedical Engineering (CMBE22), Milan, Italy, 27-29 June 2022|
|Publisher / Ed. Institution:||Computational and scientific consultancy services|
|Publisher / Ed. Institution:||United Kingdom|
|Subjects:||Intracranial aneurysm; Probabilistic graphical model; Bayesian network|
|Subject (DDC):||003: Systems |
362.11: Hospitals and related institutions
|Abstract:||Various intracranial aneurysm (IA) rupture risk factors are used for risk assessment, but little is understood about their complex interactions leading to IA rupture. In this study, Bayesian networks (BN) were learned on data of nine risk factors from 790 patients and compared to standard descriptive and regression analyses. The results from standard methods agreed with previous studies and could be extended with BNs by uncovering additional associations in the data. The graphical representation of the IA rupture risk factors in BNs facilitated the result understanding and provided new hypotheses on the risk factor interdependencies.|
|Fulltext version:||Published version|
|License (according to publishing contract):||Licence according to publishing contract|
|Departement:||Life Sciences and Facility Management|
|Organisational Unit:||Institute of Computational Life Sciences (ICLS)|
|Published as part of the ZHAW project:||Datengetriebene Entscheidungsunterstützung bei intrakraniellen Aneurysmen und in der Spitalgastronomie mittels Bayes'schen Netzwerken|
PhD Network in Data Science
|Appears in collections:||Publikationen Life Sciences und Facility Management|
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.