Dental Artificial Intelligence Systems: A Review of Various Data Types

Abstract

With the rapid development of dental artificial intelligence systems (DAIS), a new field known as "Data Dentistry", proposed by Schwendicke in 2021, has successfully bridged the gap between medicine and engineering. This literature review introduces advanced techniques in data collection, outlines the current state of DAIS in data processing, and anticipates the future of DAIS by emphasizing the importance of more extensive and enhanced datasets. The key findings include: Versatility of imaging data: Various types of imaging data, such as X-ray, cone beam computed tomography (CBCT), facial photos, and face and oral scans, can be transformed into datasets used by artificial intelligence systems. Uniform rules in electronic dental record (EDR) systems: EDR systems require standardized rules for general use in DAIS, ensuring compatibility and seamless integration. Potential of wearable device data: Data from wearable devices, including bioelectric signals (such as electromyography), stress sensors, AR glasses, etc., show great potential for enhancing DAIS capabilities. Current DAIS performance focus: Presently, DAIS demonstrate superior performance in object location and disease diagnosis compared to information integration and clinical decision-making. Need for data quality and quantity improvement: Further improvements are needed in both the quality and quantity of data for DAIS.