Abstract
Within the pelvis the iliac crest and ischial tuberosity display delayed ossification and fusion, thus, presenting as reliable maturity indicators. Amongst the different iliac crest and ischial tuberosity age estimation methods, the modified Kreitner-Kellinghaus stages constitute one of the more promising methods. The present study was directed towards establishing the applicability of the modified Kreitner-Kellinghaus method using five supervised machine learning approaches. Clinical CT scans of consenting individuals were collected and scored using the modified Kreitner-Kellinghaus method for the iliac crest and ischial tuberosity, independently. Age was subsequently estimated using different machine learning models. Cumulative scores computed from both markers were additionally employed for age estimation using machine learning. For iliac crest age estimation, Random Forest and Gradient Boosting Regression furnished lowest mean absolute error (2.42 years) and root mean square error (3.06 years). For ischial tuberosity age estimation, Gradient Boosting Regression garnered the lowest computations of mean absolute error (2.60 years) and root mean square error (3.09 years). For cumulative score based age estimation, Support Vector Regression and Gradient Boosting Regression yielded lowest mean absolute error (2.48 years) and root mean square error (3.07 years). Obtained error computations indicate that the iliac crest is a more accurate age marker in comparison to the ischial tuberosity. Additionally, cumulative score-based approaches garnered similar/ marginally more precise results in comparison to the iliac crest with all five models. This marginal improvement is not sufficient to justify employing the relatively more complicated cumulative score-based approach for age estimation. Hence, whenever available, the iliac crest should be preferred over the ischial tuberosity/ cumulative score-based approaches for age estimation.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have