Sex and stature estimation are critical components in determining the biological profile in forensic anthropology. This study aimed to estimate sex and stature using machine learning (ML) algorithms based on the morphometric data of the triticeal cartilage (TrC) obtained from autopsied cases. A prospective examination of the TrC was conducted on 137 autopsied cases (72 male, 65 female), aged between 18 and 90 years, at the Tokat Forensic Medicine Institution. A total of 209 TrC samples, located on the right and left sides of the neck, were measured for length, width, depth, and weight. Additionally, the cases were categorized into three groups based on stature (< 164 cm, 164–176 cm, and > 176 cm) for further analysis. These measurements were used as input features in ML models to predict sex and stature. As a result of the ML input of the obtained measurements, the highest accuracy rate of 97% was obtained with the Multilayer Perceptron (MLP) algorithm for sex estimation. The accuracy rates of other algorithms ranged between 91% and 96%. Regarding stature, the highest accuracy rate was 90% with the Random Forest (RF) algorithm. The accuracy rates of the other algorithms were found to vary between 82% and 89%. SHAP (Shapley Additive Explanations) analysis applied to MLP and RF algorithms showed that the TrC length parameter had the highest effect on sex and stature prediction, respectively. The results of our study showed that TrC has high accuracy and precision in sex and stature prediction.