Tooth agenesis is among the most prevalent congenital anomalies affecting human dentition, characterized by the developmental absence of one or more teeth. This condition may be present in either syndromic or non-syndromic forms, with significant implications for oral function, aesthetics, and craniofacial development. This narrative review aims to provide a comprehensive overview of tooth agenesis, defining its classification, genetic underpinnings, epidemiological aspects, phenotypic features, and therapeutic approaches. Recent advances in genetic research have identified numerous causative genes, notably EDA, MSX1, WNT10A, and PAX9, each associated with specific patterns of missing teeth and involved in isolated and/or syndromic forms. Additionally, genes such as TSPEAR, LRP6, PITX2, and GREM2 contribute to varying degrees of severity and tooth distribution, often blurring the lines between syndromic and isolated cases. The genotype-phenotype correlations underscore the complexity of the underlying molecular pathways involved in odontogenesis. From a therapeutic perspective, the management of tooth agenesis requires a multidisciplinary approach, often involving orthodontic, prosthetic, and surgical interventions tailored to the severity of tooth loss and patient age. Early diagnosis represents a crucial role in treatment planning, facilitating timely intervention during growth and enhancing long-term outcomes. In conclusion, tooth agenesis remains a complex clinical condition with a strong genetic basis. A patient-centered and interdisciplinary strategy is essential to address both functional and psychosocial needs.

Artificial intelligence (AI) has penetrated many aspects of orthodontic clinical practice over the past decade. This narrative review aims to highlight all the areas where AI has already entered clinical routine and how it can further improve orthodontic practice in the future. AI is present in diagnostic procedures, facilitating record keeping and supporting the study of patient radiographic and photographic image characteristics. It also underpins the creation and analysis of digital impressions. AI has also become part of patient communication processes, helping to share treatment decisions and facilitating treatment monitoring. Technology and the availability of clinical data also enable the use of AI in diagnostic processes. Currently, clinicians must evaluate AI-provided clinical suggestions before accepting them, as is the case with clear aligner treatments, for example. Research on AI in dentistry, reported in this article, promises to increase the precision of diagnostic measurements and facilitate clinicians’ treatment decisions.

(1) The purpose of this study is to relate the bidimensional and tridimensional measures of the palate to the vertical facial pattern defined by the angle “SN-MP” between the mandibular plane and the anterior cranial base (Sella–Nasion/mandibular plane angle) in skeletal Class II untreated patients. Furthermore, the same palatal measures were used to compare Class II with Class I subjects. (2) A sample of 197 Class II Caucasian subjects (112 females and 85 males) with untreated skeletal Class II was collected retrospectively (from a private dental clinic specialized in orthodontics) and divided into two main groups according to the ANB angle: 74 Class I patients (0° ≤ ANB ≤ 4°) and 123 Class II patients (ANB > 4°). Class II subjects were furthermore divided into three groups depending on the angle SN-MP. Lateral cephalograms and digital 3D maxillary dental scans were available. Bidimensional and tridimensional measures were taken on each maxillary dental scan. The differences among the groups were analyzed for significance using a variance analysis. (3) A decrease in the posterior palatal height and an increase in the palatal surface area in Class I subjects were reported. The results showed a change in upper arch form, with a greater intermolar width in patients with a low SN-MP angle and a smaller one in high-angle patients. The more a Class II subject tended towards high-angle divergence, the narrower the palate was. (4) A greater posterior palatal height was found in Class II malocclusion, while greater surface area was noted in Class I malocclusion. In addition to this result, another statistical significance was detected in Class II malocclusion: the intermolar distance was greater in hypodivergent than in hyperdivergent patients. Similar volume values were noted across different malocclusions and vertical divergence groups. Palatal width seemed to be related to vertical facial pattern, while palatal height and area seemed to be related to sagittal malocclusions. These findings underscore the importance of considering palatal morphology variations in designing individualized orthodontic treatments, thereby improving patient-specific outcomes and broadening our understanding of skeletal Class II malocclusion.