AIM: This systematic review aimed to investigate the performance of AI systems in identifying dental anomalies in paediatric dentistry and compare it with human performance.
DESIGN: A systematic search of Scopus, PubMed and Google Scholar was conducted from 2012 to 2022. Inclusion criteria were based on problem/patient/population, intervention/indicator, comparison and outcome scheme and specific keywords related to AI, DL, paediatric dentistry, dental anomalies, supernumerary and mesiodens. Six of 3918 initial pool articles were included, assessing nine DL sub-systems that used panoramic radiographs or cone-beam computed tomography. Article quality was assessed using QUADAS-2.
RESULTS: Artificial intelligence systems based on DL algorithms showed promising potential in enhancing the speed and accuracy of dental anomaly detection, with an average of 85.38% accuracy and 86.61% sensitivity. Human performance, however, outperformed AI systems, achieving 95% accuracy and 99% sensitivity. Limitations included a limited number of articles and data heterogeneity.
CONCLUSION: The potential of AI systems employing DL algorithms is highlighted in detecting dental anomalies in paediatric dentistry. Further research is needed to address limitations, explore additional anomalies and establish the broader applicability of AI in paediatric dentistry.
MATERIALS AND METHODS: One hundred and twelve mice were given incision wounds and infected with methicillin-resistant Staphylococcus aureus (MRSA). The study used a factorial design with two factors: The type of therapy (n = 7) and irradiation time (days 1, 2, 4, and 6). The mice were divided into seven therapy groups: Control group with NaCl, control with Sofra-tulle® treatment, red-laser therapy (650 nm, 3.5 J/cm2), blue-laser therapy (405 nm, 3.5 J/cm2), ozone therapy, red-laser therapy (650 nm, 3.5 J/cm2) with ozone, and blue-laser therapy (405 nm, 3.5 J/cm2) with ozone. This therapy was performed using irradiation perpendicular to the wound area. The photosensitizer used was curcumin 10 mg/mL, which was applied to the wound area before exposure to a laser and ozone. The ozone concentration was 0.011 mg/L with a flow time of 80 s. The test parameters were the number of collagens, bacterial colonies, lymphocytes, monocytes, and wound length measurement to determine their acceleration effects on wound healing. Data were analyzed by a two-way (factorial) analysis of variance test.
RESULTS: Acceleration of wound healing was significantly different between treatments with a laser or a laser-ozone combination and treatment using 95% sodium chloride (NaCl) and Sofra-tulle®. On day 6, the blue-laser with ozone treatment group had efficiently increased the number of bacteria and reduced the wound length, and the red-laser treatment with ozone increased the amount of collagen. In addition, the red-laser also reduced the number of lymphocytes and monocytes, which can have an impact on accelerating wound healing. Blue-laser therapy was very effective for increasing the number of epithelia.
CONCLUSION: The blue- and red-laser combined with ozone treatments effectively accelerated the healing of incisional wounds infected with MRSA bacteria.
METHODS: Blood and saliva samples were collected from 27 patients diagnosed with acute leukemia in Riyadh City, KSA. DNA was extracted, and 15 STR loci were amplified.
RESULTS: Approximately 59.3% of patients with leukemia exhibited mutations at the STR loci. Loss of heterozygosity (LOH) occurred in 40.7% of the patients at D19S433, D16S539, vWA, D13S317, TH01, FGA, and D2S1338. Microsatellite instability (MSI) was detected in 22.2% of patients at TPOX, vWA, D19S433, D16S539, and D18S51. D19S433 and D16S539 were the most affected loci, exhibiting an alteration percentage of 18.52%, followed by vWA (11.11%); in contrast, D2S1338, D18S51, and TPOX were the least affected loci, showing a mutation percentage of 3.7%. D13S317, TH01, and FGA showed moderate genetic mutation (7.41%). CSF1PO, D21S11, D3S1358, D5S818, D7S820, D8S1179, and amelogenin did not show genetic changes in all samples. The overall genetic variability between saliva and blood samples significantly differed (P