TY  - CONF
AU  - Vulović, Aleksandra
AU  - Geroski, Tijana
AU  - Filipović, Nenad
PY  - 2023
UR  - https://belbi.bg.ac.rs/
UR  - https://imagine.imgge.bg.ac.rs/handle/123456789/1979
AB  - Experimental studies have shown that lower shear stress values lead to better femoral
bone – hip implant connection. Numerical simulations have provided option to reduce
the number of experimental studies through analysis of different hip implant surface
topographies. However, this approach takes time as there are different model parameters
that should be considered in order to understand how they affect the obtained shear
stress values. The use of classification algorithms is an approach that could reduce the
time required for simulation by providing information about models with biggest potential.
Eleven model parameters related to model and surface topography were considered
in combination with four classification algorithms - Support Vector Machines (SVM), K
- Nearest Neighbor (KNN), Decision Tree (DT), and Random Forest (RF). The considered
parameters were: Number of half-cylinders lengthwise (>0); Number of half-cylinder rows
(≥0); Half cylinders added or removed from the surface (0 – removed; 1 - added); Distance
between half-cylinders lengthwise (≥0); Distance between half-cylinders widthwise
(≥0); Number of different radius values (1 or 2); Radius 1 value (>0); Radius 2 value (≥0);
Distance from the edge where loading is located (≥0); Distance from the other edge of the
model (≥0); Model includes trabecular bone (0 – not included; 1 - included). The aim was
to apply previously mentioned algorithms to obtain information if the maximum shear
stress value was above or below user-defined threshold. The obtained results show that
this approach can be useful to obtain preliminary information about models that should
be numerically analyzed.
PB  - Belgrade : Institute of molecular genetics and genetic engineering
C3  - 4th Belgrade Bioinformatics Conference
T1  - Application of classification algorithms for hip implant surface topographies
EP  - 41
SP  - 41
VL  - 4
UR  - https://hdl.handle.net/21.15107/rcub_imagine_1979
ER  - 

@conference{
author = "Vulović, Aleksandra and Geroski, Tijana and Filipović, Nenad",
year = "2023",
abstract = "Experimental studies have shown that lower shear stress values lead to better femoral
bone – hip implant connection. Numerical simulations have provided option to reduce
the number of experimental studies through analysis of different hip implant surface
topographies. However, this approach takes time as there are different model parameters
that should be considered in order to understand how they affect the obtained shear
stress values. The use of classification algorithms is an approach that could reduce the
time required for simulation by providing information about models with biggest potential.
Eleven model parameters related to model and surface topography were considered
in combination with four classification algorithms - Support Vector Machines (SVM), K
- Nearest Neighbor (KNN), Decision Tree (DT), and Random Forest (RF). The considered
parameters were: Number of half-cylinders lengthwise (>0); Number of half-cylinder rows
(≥0); Half cylinders added or removed from the surface (0 – removed; 1 - added); Distance
between half-cylinders lengthwise (≥0); Distance between half-cylinders widthwise
(≥0); Number of different radius values (1 or 2); Radius 1 value (>0); Radius 2 value (≥0);
Distance from the edge where loading is located (≥0); Distance from the other edge of the
model (≥0); Model includes trabecular bone (0 – not included; 1 - included). The aim was
to apply previously mentioned algorithms to obtain information if the maximum shear
stress value was above or below user-defined threshold. The obtained results show that
this approach can be useful to obtain preliminary information about models that should
be numerically analyzed.",
publisher = "Belgrade : Institute of molecular genetics and genetic engineering",
journal = "4th Belgrade Bioinformatics Conference",
title = "Application of classification algorithms for hip implant surface topographies",
pages = "41-41",
volume = "4",
url = "https://hdl.handle.net/21.15107/rcub_imagine_1979"
}

Vulović, A., Geroski, T.,& Filipović, N.. (2023). Application of classification algorithms for hip implant surface topographies. in 4th Belgrade Bioinformatics Conference
Belgrade : Institute of molecular genetics and genetic engineering., 4, 41-41.
https://hdl.handle.net/21.15107/rcub_imagine_1979

Vulović A, Geroski T, Filipović N. Application of classification algorithms for hip implant surface topographies. in 4th Belgrade Bioinformatics Conference. 2023;4:41-41.
https://hdl.handle.net/21.15107/rcub_imagine_1979 .

Vulović, Aleksandra, Geroski, Tijana, Filipović, Nenad, "Application of classification algorithms for hip implant surface topographies" in 4th Belgrade Bioinformatics Conference, 4 (2023):41-41,
https://hdl.handle.net/21.15107/rcub_imagine_1979 .