Applications of artificial intelligence in age estimation: a review

Abstract

Age estimation is a legally significant issue, particularly in underdeveloped and developing countries, due to factors such as inadequate civil registration systems and irregular migration. While various techniques are employed for age estimation using traditional methods, it is known that factors including age, gender, chronic illness, race, and geographical region can result in discrepancies between skeletal age and chronological age. This complicates the process of achieving accurate age estimation. This review aims to discuss recent research on artificial intelligence applications in light of current literature. Artificial intelligence and machine learning have enabled machines to acquire human-like capabilities in thinking, learning, problem solving, and decision making, leading to significant progress in achieving faster and accurate results. In the field of forensic medicine, methods such as linear discriminant analysis, K-Nearest Neighbors, support vector machines, random forests, and artificial neural networks have been employed to classify data and conduct studies on age estimation. Research has focused on five regions: the carpal bones, ossification centers, the middle phalanx of the hand, the third metacarpal, and the radius and ulna. Additionally, facial angles and width obtained through tomographic examinations, as well as measurements of the calcaneus and cuboid bones, panoramic dental radiographs, volumetric analysis of teeth and pulp using Cone Beam Computed Tomography, and analysis of bloodstains on microRNAs, have been analyzed for their distribution across different age. The results demonstrate that artificial intelligence applications can be utilized in age estimation with a high accuracy rate (85-95%). Age estimation using artificial intelligence enhances data-driven decision-making processes, improves the quality of services, and contributes to societal benefit. Therefore, we believe that incorporating artificial intelligence applications alongside traditional methods in age estimation will yield more meaningful outcomes.