Random forest and Self Organizing Maps application for analysis of pediatric fracture healing time of the lower limb

Citation data:

Neurocomputing, ISSN: 0925-2312, Vol: 272, Page: 55-62

Publication Year:
Usage 24
Abstract Views 24
Captures 1
Readers 1
Social Media 122
Shares, Likes & Comments 122
Citations 2
Citation Indexes 2
Sorayya Malek; S. Y. Kedija; C. F. Lau; Mogeeb A.A. Mosleh; Pozi Milow; R. Gunalan; S. A. Lee; A. Saw
Elsevier BV
Computer Science; Neuroscience
article description
In this study, we examined the lower limb fracture healing time in children using random forest (RF) and Self Organizing feature Maps (SOM) methods. The study sample was obtained from the pediatric orthopedic unit in University Malaya Medical Centre. Radiographs of long bones of lower limb fractures involving the femur, tibia and fibula from children ages 0–12 years, with ages recorded from the date and time of initial injury. Inputs assessment extracted from radiographic images included the following features: type of fracture, angulation of the fracture, contact area percentage of the fracture, age, gender, bone type, type of fracture, and number of bone involved. RF is initially used to rank the most important variables that effecting bone healing time. Then, SOM was applied for analysis of the relationship between the selected variables with fracture healing time. Due to the limitation of available dataset, leave one out technique was applied to enhance the reliability of RF. Results showed that age and contact area percentage of fracture were identified as the most important variables in explaining the fracture healing time. RF and SOM applications have not been reported in the field of pediatric orthopedics. We concluded that the combination of RF and SOM techniques can be used to assist in the analysis of pediatric fracture healing time efficiently.