Towards an automated classification method for ureteroscopic kidney stone images using ensemble learning.

Urolithiasis is a common disease around the world and its incidence has been growing every year. There are various diagnosis techniques based on kidney stone identification aiming to find the formation cause. However, most of them are time consuming, tedious and expensive. The accuracy of the diagnosis is crucial for the prescription of an appropriate treatment that can eliminate the stones and diminish future relapses. This paper presents two effective supervised learning methods to automate and improve the accuracy of the classification of kidney stones; as well as a dataset consisting of kidney stone images captured with ureteroscopes. In the proposed methods, the image features that are visually exploited by urologists to distinguish the type of kidney stones are analyzed and encoded as vectors. Then, the classification is performed on these feature vectors through Random Forest and ensemble K Nearest Neighbor classifiers. The overall classification accuracy obtained was 89%, outperforming previous methods by more than 10%. The details of the classifier implementation, as well as their performance and accuracy, are presented and discussed. Finally, future work and improvements are proposed.

Enhancing recovery in pediatric major abdominal surgery: a narrative review of the literature / Recuperación intensificada en cirugía abdominal mayor en pediatría: revisión narrativa de la literatura

Abstract Introduction: Enhanced recovery after surgery (ERAS) programs in adults have positively impacted morbidity, mortality, and healthcare costs. Its effects on the pediatric population is recognized. Objective: To prepare a narrative review on the current evidence of the various strategies within the framework of enhancing recovery after pediatric surgery, in the context of major abdominal surgery. Methods: A search was conducted on the scientific evidence available in databases (Pubmed/Medline, Science Direct, OVID, SciELO), in order to prepare a narrative literature review. Conclusion: Notwithstanding the limited evidence on the practicality of the ERAS protocols in the pediatric population undergoing major abdominal surgery, better results could be accomplished if these strategies are adopted.

Resumen Introducción: Los programas de recuperación intensificada después de cirugía (ERAS, por sus siglas del inglés enhanced recovery after surgery) en adultos han impactado positivamente en morbilidad, mortalidad y costos en salud. Es conocido su efecto respecto a su efectividad en población pediátrica. Objetivo: Elaborar una revisión narrativa respecto a la evidencia actual de las diferentes estrategias en el marco de programas de recuperación intensificada en cirugía pediátrica (ERPS, por sus siglas del inglés enhancing recovery in pediatric surgery), en el contexto de cirugía abdominal mayor. Métodos: Se realizó una búsqueda sobre la evidencia científica disponible en bases de datos (Pubmed/Medline, Science Direct, OVID, SciELO) para elaborar una revisión narrativa de la literatura. Conclusiones: Aunque existe evidencia limitada sobre la utilidad de los protocolos ERAS en la población pediátrica sometida a cirugía abdominal mayor, podrían lograrse mejores resultados si se adoptan estas estrategias en pacientes pediátricos.

Measurement of open apices in tooth roots in Colombian children as a tool for human identification in asylum and criminal proceedings.

Dental age estimation was recognized as an imperative issue in clinical and medico-legal practice. However, very few studies on dental age estimation in children have been published in Colombia. This study evaluated the accuracy of Cameriere's method of measurement of open apices on tooth roots in a sample of 526 digital panoramic radiographs (OPTs) of children (274 boys and 252 girls), aged between 6 and 14 years, from Bogotá, Valle del Cauca, Buga and Villavicencio, in Southwest Colombia. Only first seven permanent lower teeth, except third molar, from the left side of mandible were studied. Difference between dental age and chronological age was evaluated for boys and girls across nine age classes. Intra-class correlation coefficient and Kappa score was used to test intra- and inter-observer agreement error rate. Dental age was overestimated by 0.08 years and standard deviation (±SD) of 0.68 years in boys which was not statistically significant (p = 0.06), while in girls dental age underestimated by -0.25 ± 0.65 years which was statistically significant difference (p < 0.001). The absolute difference between DA and CA or mean prediction error (ME) was 0.57 ± 0.38 years in boys and 0.57 ± 0.41 in girls (p = 0.966) which implies that Cameriere's European formula is similarly accurate in both sexes in this sample of Colombian children.

Accuracy of cut-off value by measurement of third molar index: Study of a Colombian sample.

The aim of this cross-sectional study was to test the accuracy of cut-off value of 0.08 by measurement of third molar index (I3M) in assessing legal adult age of 18 years in a sample of Colombian children and young adults. Digital orthopantomographs of 288 Colombian children and young adults (163 girls and 125 boys), aged between 13 and 22 years, were analysed. Concordance correlation coefficient (ρc) and κ statistics (Cohen's Kappa coefficient) showed that repeatability and reproducibility are high for both intra- and inter-observer error. κ statistics for intra- and inter-observer agreement in decision on adult or minor was 0.913 and 0.877, respectively. Age distribution gradually decreases as I3M increases in both girls and boys. For girls, the sensitivity test was 95.1% (95% CI 87.1%-95%) and specificity was 93.8% (95% CI 87.1%-98.8%). The proportion of correctly classified individuals was 95.1%. For boys, the sensitivity test was 91.7% (95% CI 85.1%-96.8%) and specificity was 90.6% (95% CI 82.1%-97.8%). The proportion of correctly classified individuals was 89.7%. The cut-off value of 0.08 is highly useful to determine if a subject is 18 years of age or older or not.