Development of Surrogate Models of Orthopedic Screws to Improve Biomechanical Performance: Comparisons of Artificial Neural Networks and Multiple Linear Regressions

Development of Surrogate Models of Orthopedic Screws to Improve Biomechanical Performance: Comparisons of Artificial Neural Networks and Multiple Linear Regressions

Ching-Chi Hsu (Graduate Institute of Applied Science and Technology, National Taiwan University of Science and Technology, Taiwan)
DOI: 10.4018/978-1-4666-1803-9.ch009
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

An optimization approach was applied to improve the design of the lag screws used in double screw nails. However, finite element analyses with an optimal algorithm may take a long time to find the best design. Thus, surrogate methods, either artificial neural networks or multiple linear regressions, were used to substitute for the finite element models. The results showed that an artificial neural network method can accurately develop the objective functions of the lag screws for both the bending strength and the pullout strength. A multiple linear regression method can successfully develop the objective function of the lag screws for the pullout strength, but it failed to construct the objective function for the bending strength. The optimal design of the lag screws could be obtained using the artificial neural network method and genetic algorithms.
Chapter Preview
Top

Background

Dynamic hip screws or gamma nails are used to treat patients with proximal femoral fractures (Bellabarba, Herscovici, Ricci, & Hudanich, 2003; Hartford, Patel, & Powell, 2005; Hesse & Gächter, 2004; Willoughby, 2005). A dynamic hip screw consists of a metal plate, a lag screw, and locking screws, and has the advantage of a sliding lag screw in the barrel of the side plate that facilitates fracture impaction and healing and prevents lag screw cut-out (Bucholz, Heckman, & Court-Brown, 2006; Lorich, Geller, & Nielson, 2004; Schipper, Steyerberg, & Castelein, 2004). A gamma nail consists of a nail, a proximal lag screw, distal locking screws, and a set screw, and has the advantage of a lower risk of implant failure and prevents femoral shortening and hip deformity. These implants have been successfully applied to treat subtrochanteric fractures, intertrochanteric fractures, and basal neck fractures. However, a dynamic hip screw with excessive sliding of the lag screw may cause limb shortening and lag screw cut-out (Lin, 2006). In addition, gamma nails have the drawbacks of postoperative femoral shaft fracture via the nail tip due to stress concentration and intraoperative splintering because of the bulky proximal part (Pervez & Parker, 2001).

To solve the above problems, a double screw nail design, which consists of a nail, two proximal lag screws, and distal locking screws, is presented (Lin, 2006). Double screw nails can avoid postoperative femoral fracture and intraoperative splintering because of a long nail length and a small nail diameter on the proximal part, respectively. Although double screw nails have been demonstrated to have greater biomechanical performance than dynamic hip screws and gamma nails (C. C. Hsu, Lin, Amaritsakul, Antonius, & Chao, 2009), the failure of fracture fixation for double screw nails still exists (Banan, Al-Sabti, Jimulia, & Hart, 2002). Fatigue failure and screw loosening of the lag screws were the main problems found for double screw nails. Thus, improving the design of double screw nails might solve these two clinical problems.

Complete Chapter List

Search this Book:
Reset