Efficacy of the methods of age determination using artificial intelligence in panoramic radiographs - a systematic review.

The aim of this systematic review is to analyze the literature to determine whether the methods of artificial intelligence are effective in determining age in panoramic radiographs. Searches without language and year limits were conducted in PubMed/Medline, Embase, Web of Science, and Scopus databases. Hand searches were also performed, and unpublished manuscripts were searched in specialized journals. Thirty-six articles were included in the analysis. Significant differences in terms of root mean square error and mean absolute error were found between manual methods and artificial intelligence techniques, favoring the use of artificial intelligence (p < 0.00001). Few articles compared deep learning methods with machine learning models or manual models. Although there are advantages of machine learning in data processing and deep learning in data collection and analysis, non-comparable data was a limitation of this study. More information is needed on the comparison of these techniques, with particular emphasis on time as a variable.

A prospective non-fatal injuries assessment: A multivariate analysis in medical-legal examinations.

OBJECTIVE: To prospectively determine injury recovery time in the medical-legal examinations of non-fatal injuries and their associated factors, carried out by the National Institute of Legal Medicine and Forensic Sciences of Colombia to create a multivariate analysis. METHODS: A prospective medical-legal assessment of non-fatal injuries was carried out on 281 individuals with complete follow-up, in which the observational unit of analysis was the most serious injury. Variables, such as sex, circumstances of the injury, the mechanism that caused the injury, medical certificate of incapacity to work, among others were related to the injury recovery time, measured in days. The Kruskal Wallis (K-W) ANOVA and a multivariate analysis using the ordinal regression model were applied. RESULTS: In the multivariate analysis, the factors most associated with longer recovery time were the extent of joint damage (CR95%:1.47-5.94,p = 0.0001) and bone damage (CR95%:2.92-7.42,p < 0.001). In terms of circumstances of the injury, traffic accidents (CR95%:1.03-2.96,p < 0.001), medical-legal impairments (CR95%:0.34-2.19,p = 0.007), and complications of the primary injury (CR95%: 1.18-2.57,p < 0.001) had the greatest impact on recovery time. Others factors that significantly impacted injury recovery time are surgical treatments (IC95%: 0.33-3.26,p = 0.0164) and delayed treatment (CR95%:1.41-4.72,p < 0.001). A direct correlation (significant and moderately strong) was found between the recovery time of the injury and the days of incapacity for work (r = 0.802, p < 0.001). CONCLUSION: This prospective analysis determined which variables were most strongly related to the medical-legal assessment of non-fatal injuries and the recovery time of said injuries. Further studies aimed at improving the strategies to help individuals complete the legal process are required.