Search

Background: Artificial intelligence (AI) has taken hold in public health because more and more people are looking to make a diagnosis using technology that allows them to work faster and more accurately, reducing costs and the number of medical errors. Methods: In the present study, 120 panoramic X-rays (OPGs) were randomly selected from the Department of Oral and Maxillofacial Sciences of Sapienza University of Rome, Italy. The OPGs were acquired and analyzed using Apox, which takes a panoramic X-rayand automatically returns the dental formula, the presence of dental implants, prosthetic crowns, fillings and root remnants. A descriptive analysis was performed presenting the categorical variables as absolute and relative frequencies. Results: In total, the number of true positive (TP) values was 2.195 (19.06%); true negative (TN), 8.908 (77.34%); false positive (FP), 132 (1.15%); and false negative (FN), 283 (2.46%). The overall sensitivity was 0.89, while the overall specificity was 0.98. Conclusions: The present study shows the latest achievements in dentistry, analyzing the application and credibility of a new diagnostic method to improve the work of dentists and the patients’ care.

A minimally invasive implant treatment approach for future full arch implant prosthetic rehabilitations of trophic jaws represents a challenge. An optimal implant planning is strongly related with an accurate merge of the prosthetic information and the radiographic data. To comply with that, most computer aided implantology (CAI) systems require additional steps, as radiographic stents or fiducial markers to overlap digital jaw scans to cone beam computed tomography (CBCT) data. Using dynamic CAI, residual teeth (up to three) make it possible for the merge to avoid new radiographic scans. An additional challenge is the treatment involving immediate implants compared with delayed implants placed into healed bone. As for other static CAI systems, the operator&rsquo, s experience and the quality of the CBCT data make the planning affordable and secure the entire implants placement procedure. The literature reports accuracies in terms of comparison between placed implants and planned implants, following a double CBCT approach, based on radiographic volume overlapping. Thirteen consecutive future totally edentulous patients (77 implants), divided into two groups (group A: 3&ndash, 4 teeth traced, group B: 5&ndash, 6 teeth traced) requiring a full arch implant prosthetic rehabilitation were included in the reported case series. A dynamic CAI was used to plan and to place all implants following all the recommended digital steps. The software used provided a tool (Trace and Place) that made the merge between X-ray views of the residual teeth and their own positions possible. This method definitely registered that teeth positions comply with the required accuracy live check. After implants placement, a post-operative CBCT was taken in order to evaluate the deviations of the achieved implants at coronal, apical, and depth level as well as angular deviations. Statistically significant radiological mean difference between the two groups was found in the coronal position of implants (0.26 mm, p &lt, 0.001), in the apical position of implants (0.29 mm, p &lt, 0.001), in the depth of implants (0.16 mm, p = 0.022), and in the angular deviation (0.7, p = 0.004). The use of the TaP technology for the treatment of the patients with at least three stable teeth that need to be removed for a totally implant prosthetic treatment is a promising technique. The performed accuracy analysis demonstrated that this digital protocol can be used without a loss of accuracy of the achieved implants compared to planned ones.