OBJECTIVE: Deep learning artificial intelligence can determine the sex using only fundus photographs. However, the factors used by deep learning to determine the sex are not visible. Therefore, the purpose of the study was to determine whether the sex of an older individual can be determined by regression analysis of their color fundus photographs (CFPs).
METHODS: Forty-two parameters were analyzed by regression analysis using 1653 CFPs of normal subjects in the Kumajima study. The parameters included the mean values of red, green, and blue intensities; the tessellation fundus index; the optic disc ovality ratio; the papillomacular angle; and the retinal vessel angles. Finally, the L2 regularized binomial logistic regression was used to predict the sex using all the parameters, and the diagnostic ability was assessed through the leave-one-cross-validation.
RESULTS: The mean age of the 838 men and 815 women were 52.8 and 54.0 years, respectively. The ovality ratio and retinal artery angles in women were significantly smaller than that in men. The green intensity at all locations for the women were significantly higher than that of men (P < 0.001). The discrimination accuracy rate assessed by the area-under-the-curve was 80.4%.
CONCLUSIONS: Our methods can determine the sex from the CFPs of the adult with an accuracy of 80.4%. The ovality ratio, retinal vessel angles, tessellation, and the green intensities of the fundus are important factors to identify the sex in individuals over 40 years old.

Natural sciences provide several modern methodologies that could be successfully applied in archaeological studies. In this pilot study, archaeological human remains from two Iron Age cemeteries (7th-twelfth centuries AD), Lejasbitēni and Čunkāni-Dreņģeri, which are located in different regions of Latvia, were studied. We applied ancient DNA (aDNA) and tooth enamel peptide analysis to determine the biological sex of the individuals. In addition, aDNA analysis was used to perform mtDNA haplogroup analysis. In most cases, the results of aDNA analysis regarding the biological sex of individuals coincided with the gender assigned based on grave orientation and grave goods. The results of sex determination using peptide analysis in all four individuals for whom data were available matched the possible gender. Of the 17 samples that had sufficient DNA for sequencing, seven samples had enough reads to perform mtDNA haplogroup analysis. The H2a2a, I4a1, H2a2a1, and H16c mtDNA haplogroups were identified in the individuals from the Lejasbitēni cemetery, while the T2b and K1a + 150 mtDNA haplogroups were identified in the individuals from the Čunkāni-Dreņģeri cemetery. Overall, the obtained results demonstrated the feasibility of applying aDNA and tooth enamel peptide analysis for biological sex determination within archaeological studies. The availability of human aDNA data will be highly useful for investigating the demographic history and social structures in Iron Age Latvia.

BACKGROUND: The femur is one of the most researched bones in the human anatomy and forensic medicine. As the longest bone in the human body, it is well preserved in skeletal remains. The sex estimation of human remains is one of the most important research steps for physical and forensic anthropologists. However, osteometric standards built on unburned human remains and contemporary cremated series are often inadequate for the analysis, frequently resulting in a significant number of misclassifications.
METHODS: In our study, we present the anthropometric data from 500 skeletons in Northern Greece, including 232 males and 198 females, as well as 430 of known age. The diameters of the femur were measured as well as the indices of robustness. For the statistical interpretation of the results, we have used the discriminant analysis.
RESULTS: From the interpretation of the data, we concluded that all the mean values, diameters and indices of the males were greater compared with those of the females. Also, we concluded that the probability of error is quite high in all cases except the vertical diameter of femur\'s head, which has an acceptable percentage of error of 14.39% and can be used as a safe criterion for sex identification.
CONCLUSIONS: With the aid of statistics, we came to the conclusion that the vertical diameter of the femur\'s head is a safe variable for sex estimation in skeletal remains.

Predicting sex is an important problem in forensic medicine. The femur, patella, mandible and calcaneus bones are frequently used in predicting sex. In our study, we aimed to use the artificial neural network (ANN) technique to predict sex by measuring the values of the phalanges of the first and fifth toes and the first and fifth metatarsal bones.
All bone measurements were conducted on the direct X-ray images of 176 males and 178 females in the age range of 24-60 years. The multilayer perceptron classifier (MLPC) input layer included parameters on the bone length measurements of phalanx proximalis I, phalanx distalis I, metatarsal I, phalanx proximalis V, phalanx medialis V, phalanx distalis V and metatarsal V. The output layer contained two neurons to define the male and female sexes. The present study used an MLPC model that had two hidden layers, and the first and second hidden layers contained 14 and 7 nodes, respectively.
The model had an overall accuracy (Acc) of 0.95, specificity (Spe) of 0.97, sensitivity (Sen) of 0.95 and Matthews correlation coefficient (Mcc) of 0.92. While the sex prediction success of our proposed model was higher in women, the results were more specific in men and more sensitive in women (AccMale = 0.93, AccFemale = 0.98, SenMale = 0.93, SpeMale = 0.98, SenFemale = 0.98 and SpeFemale = 0.93).
This study demonstrated that the ANN model for length measurements on small bones is a highly effective instrument for sex prediction.

Demographic assessment of skeletal remains in forensic investigations includes identification of sex. The present study aimed to develop population-specific, sex-discriminating anthropometric standards for the mastoid triangle of a documented Saudi population using computed tomographic (CT) images of the lateral aspect of the skull. The present study was performed on 206 CT images of a documented Saudi population of known sex and age. The clinical CT images of subjects visiting the Department of Radiology, Dammam Medical Complex, Dammam, Saudi Arabia (KSA) were evaluated to know the validity of the metric assessment of the mastoid triangle for identification of sex in a Saudi population. The distance between asterion to porion (AP), asterion to mastoidale (AM), porion to mastoidale (PM) were measured and the area of the mastoid triangle (AMT) was calculated using these measurements. Discriminant function procedure was used to analyze the data for sexual dimorphism. In conclusion, the results of the present study indicate that all the 3 sides of the mastoid triangle and AMT were sexually dimorphic in the sampled Saudi population with PM being the best individual parameter in discriminating sex with an accuracy of 69.4%. Whereas, all the parameters combined showed the highest accuracy (71.4%).