Prediction of 30-Day Mortality after a Hip Fracture Surgery Using Neural and Bayesian Networks

Abstract : Osteoporotic hip fractures have a significant morbidity and excess mortality among the elderly and have imposed huge health and economic burdens on societies worldwide. A medical database of 349 patients that have been operated for hip fracture has been analyzed. Two models of data were used in Multi-Layer Perceptrons, Radial Basis Function and Naïve Bayes networks, in order to predict the 30-day mortality after a hip fracture surgery and also to investigate which is the most appropriate risk factor between the New Mobility Score and Institution factor for the Greek population. The proposed method may be used as a screening tool that will assist orthopedics in the surgery of the hip fracture according to each different patient.
Document type :
Conference papers
Complete list of metadatas

Cited literature [27 references]  Display  Hide  Download

https://hal.inria.fr/hal-01391361
Contributor : Hal Ifip <>
Submitted on : Thursday, November 3, 2016 - 11:07:28 AM
Last modification on : Friday, August 9, 2019 - 4:12:12 PM
Long-term archiving on : Saturday, February 4, 2017 - 1:33:13 PM

File

978-3-662-44654-6_56_Chapter.p...
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Dimitrios Galiatsatos, George Anastassopoulos, Georgios Drosos, Athanasios Ververidis, Konstantinos Tilkeridis, et al.. Prediction of 30-Day Mortality after a Hip Fracture Surgery Using Neural and Bayesian Networks. 10th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2014, Rhodes, Greece. pp.566-575, ⟨10.1007/978-3-662-44654-6_56⟩. ⟨hal-01391361⟩

Share

Metrics

Record views

168

Files downloads

364