scholarly journals Identifying intentional injuries among children and adolescents based on Machine Learning

PLoS ONE ◽  
2021 ◽  
Vol 16 (1) ◽  
pp. e0245437
Author(s):  
Xiling Yin ◽  
Dan Ma ◽  
Kejing Zhu ◽  
Deyun Li
Keyword(s):  
Machine Learning ◽  
Children And Adolescents ◽  
Research Literature ◽  
Intentional Injuries ◽  
Discrimination Model ◽  
Comprehensive Comparison ◽  
Self Harm ◽  
Stability And Consistency ◽  
Chinese Children And Adolescents

Background Compared to other studies, the injury monitoring of Chinese children and adolescents has captured a low level of intentional injuries on account of self-harm/suicide and violent attacks. Intentional injuries in children and adolescents have not been apparent from the data. It is possible that there has been a misclassification of existing intentional injuries, and there is a lack of research literature on the misclassification of intentional injuries. This study aimed to discuss the feasibility of discriminating the intention of injury based on Machine Learning (ML) modelling and provided ideas for understanding whether there was a misclassification of intentional injuries. Methods Information entropy was used to determine the correlation between variables and the intention of injury, and Naive Bayes (NB), Decision Tree (DT), Random Forest (RF), Adaboost algorithms and Deep Neural Networks (DNN) were used to create an intention of injury discrimination model. The models were compared by comprehensively testing the discrimination effect to determine stability and consistency. Results For the area under the ROC curve with different intentions of injuries, the NB model was 0.891, 0.880, and 0.897, respectively; the DT model was 0.870, 0.803, and 0.871, respectively; the RF model was 0.850, 0.809, and 0.845, respectively; the Adaboost model was 0.914, 0.846, and 0.914, respectively; the DNN model was 0.927, 0.835, and 0.934, respectively. In a comprehensive comparison of the five models, DNN and Adaboost models had higher values for the determination of the intention of injury. A discrimination of cases with unclear intentions of injury showed that on average, unintentional injuries, violent attacks, and self-harm/suicides accounted for 86.57%, 6.81%, and 6.62%, respectively. Conclusion It was feasible to use the ML algorithm to determine the injury intention of children and adolescents. The research suggested that the DNN and Adaboost models had higher values for the determination of the intention of injury. This study could build a foundation for transforming the model into a tool for rapid diagnosis and excavating potential intentional injuries of children and adolescents by widely collecting the influencing factors, extracting the influence variables characteristically, reducing the complexity and improving the performance of the models in the future.

scholarly journals Temporal trends in annual incidence rates for psychiatric disorders and self-harm among children and adolescents in the UK, 2003–2018

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Lukasz Cybulski ◽  
Darren M. Ashcroft ◽  
Matthew J. Carr ◽  
Shruti Garg ◽  
Carolyn A. Chew-Graham ◽  
...  
Keyword(s):  
Eating Disorders ◽  
Young People ◽  
Anxiety Disorders ◽  
Children And Adolescents ◽  
Autism Spectrum ◽  
Incidence Rates ◽  
Annual Incidence ◽  
Health Crisis ◽  
Self Harm ◽  
The Uk

Abstract Background There has been growing concern in the UK over recent years that a perceived mental health crisis is affecting children and adolescents, although published epidemiological evidence is limited. Methods Two population-based UK primary care cohorts were delineated in the Aurum and GOLD datasets of the Clinical Practice Research Datalink (CPRD). We included data from 9,133,246 individuals aged 1–20 who contributed 117,682,651 person-years of observation time. Sex- and age-stratified annual incidence rates were estimated for attention-deficit/hyperactivity disorder (ADHD) and autism spectrum disorder (ASD) (age groups: 1–5, 6–9, 10–12, 13–16, 17–19), depression, anxiety disorders (6–9, 10–12, 13–16, 17–19), eating disorders and self-harm (10–12, 13–16, 17–19) during 2003–2018. We fitted negative binomial regressions to estimate incidence rate ratios (IRRs) to examine change in incidence between the first (2003) and final year (2018) year of observation and to examine sex-specific incidence. Results The results indicated that the overall incidence has increased substantially in both boys and girls in between 2003 and 2018 for anxiety disorders (IRR 3.51 95% CI 3.18–3.89), depression (2.37; 2.03–2.77), ASD (2.36; 1.72–3.26), ADHD (2.3; 1.73–3.25), and self-harm (2.25; 1.82–2.79). The incidence for eating disorders also increased (IRR 1.3 95% CI 1.06–1.61), but less sharply. The incidence of anxiety disorders, depression, self-harm and eating disorders was in absolute terms higher in girls, whereas the opposite was true for the incidence of ADHD and ASD, which were higher among boys. The largest relative increases in incidence were observed for neurodevelopmental disorders, particularly among girls diagnosed with ADHD or ASD. However, in absolute terms, the incidence was much higher for depression and anxiety disorders. Conclusion The number of young people seeking help for psychological distress appears to have increased in recent years. Changes to diagnostic criteria, reduced stigma, and increased awareness may partly explain our results, but we cannot rule out true increases in incidence occurring in the population. Whatever the explanation, the marked rise in demand for healthcare services means that it may be more challenging for affected young people to promptly access the care and support that they need.

scholarly journals Relationship of Sodium Intake with Overweight/Obesity among Chinese Children and Adolescents: Data from the CNNHS 2010–2012

2021 ◽  
Vol 18 (9) ◽  
pp. 4551
Author(s):  
Kehong Fang ◽  
Yuna He ◽  
Yuehui Fang ◽  
Yiyao Lian
Keyword(s):  
Children And Adolescents ◽  
Abdominal Obesity ◽  
Sodium Intake ◽  
Saturated Fatty Acids ◽  
Positive Association ◽  
Chinese Children ◽  
Weighing Method ◽  
Relationship Of ◽  
The Relationship ◽  
Chinese Children And Adolescents

This study aims to examine association between sodium intake and overweight/obesity among Chinese children and adolescents. Data were obtained from China National Nutrition and Health Surveillance (CNNHS), 2010–2012. All participants recruited in this study aged 7–18 years old and provided complete dietary data on three-day consecutive 24 h dietary recalls combining with the household weighing method. Body Mass Index (BMI) was used to define overweight/obesity, and waist-to-height ratio (WHtR) was used to define abdominal obesity. Sodium intake showed association with risk of overweight/obesity assessed by BMI in the highest tertile group with OR of 1.48 (95%CI 1.13–1.94) and 1.89 (95%CI 1.33–2.67) for WHtR. After adjusted for gender, age, household income, area, energy, carbohydrates, protein, fat, saturated fatty acids, and fiber intake, the relationship between sodium intake and overweight/obesity and abdominal obesity are not changed. The same results were founded in subjects aged 10–18 years old. Our results reveal a positive association between sodium intake and overweight/obesity in Chinese children and adolescents, independent of energy consumption.

Repetition of self-harm and suicide following self-harm in children and adolescents: findings from the Multicentre Study of Self-harm in England

2012 ◽  
Vol 53 (12) ◽  
pp. 1212-1219 ◽  
Author(s):  
Keith Hawton ◽  
Helen Bergen ◽  
Navneet Kapur ◽  
Jayne Cooper ◽  
Sarah Steeg ◽  
...  
Keyword(s):  
Multicentre Study ◽  
Children And Adolescents ◽  
Self Harm

scholarly journals Efficiency of Machine Learning Algorithms for the Determination of Macrovesicular Steatosis in Frozen Sections Stained with Sudan to Evaluate the Quality of the Graft in Liver Transplantation

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 1993
Author(s):  
Fernando Pérez-Sanz ◽  
Miriam Riquelme-Pérez ◽  
Enrique Martínez-Barba ◽  
Jesús de la Peña-Moral ◽  
Alejandro Salazar Nicolás ◽  
...  
Keyword(s):  
Machine Learning ◽  
Liver Transplantation ◽  
Learning Algorithms ◽  
Selection Procedure ◽  
Machine Learning Algorithms ◽  
Liver Biopsies ◽  
Convenient Technique ◽  
End Stage ◽  
Macrovesicular Steatosis

Liver transplantation is the only curative treatment option in patients diagnosed with end-stage liver disease. The low availability of organs demands an accurate selection procedure based on histological analysis, in order to evaluate the allograft. This assessment, traditionally carried out by a pathologist, is not exempt from subjectivity. In this sense, new tools based on machine learning and artificial vision are continuously being developed for the analysis of medical images of different typologies. Accordingly, in this work, we develop a computer vision-based application for the fast and automatic objective quantification of macrovesicular steatosis in histopathological liver section slides stained with Sudan stain. For this purpose, digital microscopy images were used to obtain thousands of feature vectors based on the RGB and CIE L*a*b* pixel values. These vectors, under a supervised process, were labelled as fat vacuole or non-fat vacuole, and a set of classifiers based on different algorithms were trained, accordingly. The results obtained showed an overall high accuracy for all classifiers (>0.99) with a sensitivity between 0.844 and 1, together with a specificity >0.99. In relation to their speed when classifying images, KNN and Naïve Bayes were substantially faster than other classification algorithms. Sudan stain is a convenient technique for evaluating ME in pre-transplant liver biopsies, providing reliable contrast and facilitating fast and accurate quantification through the machine learning algorithms tested.

Sign in / Sign up

Export Citation Format

Share Document