No abstract

Objectives: In this proof-of-concept study, we aimed to develop deep-learning-based classifiers to identify rib fractures on frontal chest radiographs in children under two years of age. Methods: This retrospective study included 1311 frontal chest radiographs (radiographs with rib fractures, n = 653) from 1231 unique patients (median age: 4 m). Patients with more than one radiograph were included only in the training set. A binary classification was performed to identify the presence or absence of rib fractures using transfer learning and Resnet-50 and DenseNet-121 architectures. The area under the receiver operating characteristic curve (AUC-ROC) was reported. Gradient-weighted class activation mapping was used to highlight the region most relevant to the deep learning models’ predictions. Results: On the validation set, the ResNet-50 and DenseNet-121 models obtained an AUC-ROC of 0.89 and 0.88, respectively. On the test set, the ResNet-50 model demonstrated an AUC-ROC of 0.84 with a sensitivity of 81% and specificity of 70%. The DenseNet-50 model obtained an AUC of 0.82 with 72% sensitivity and 79% specificity. Conclusions: In this proof-of-concept study, a deep learning-based approach enabled the automatic detection of rib fractures in chest radiographs of young children with performances comparable to pediatric radiologists. Further evaluation of this approach on large multi institutional datasets is needed to assess the generalizability of our results. Advances in knowledge: In this proof-of-concept study, a deep learning-based approach performed well in identifying chest radiographs with rib fractures. These findings provide further impetus to develop deep learning algorithms for identifying rib fractures in children, especially those with suspected physical abuse or non-accidental trauma.

Objectives Death Anxiety is prevalent among people, and it is more prominent in the middle and late stages of life. Furthermore, the increasing number of elderly and consequently, their growing residence in nursing homes have impacted their mental health. The prevalence rate of death anxiety in up to (16%) in people; while (3.3%) of them are suffering from severe types of it. The present study determined the relationship between the fear of death, and religious beliefs, as well as mental disorders in the elderly living in nursing homes. Methods & Materials One-hundred elderly (61% females and 39% males), with the Mean±SD age of 70.88±8.93 years living in nursing homes in Karaj City, Iran were studied. They were non-randomly and voluntarily selected to participate in this correlational study. The research tools included Templer Death Anxiety Scale (DAS, 1970), SCL90 neurological, intellectual and emotional dysfunction inventory, and Golriz-Barahani Religious Attitude Questionnaire. Furthermore, Pearson's correlation and multiple regression techniques were adopted for data analysis. The obtained data were analyzed in SPSS. Results The Mean±SD scores of death anxiety, religious beliefs, and mental disorders in the elderly population at nursing homes in Karaj were respectively 6.30 ±3.12, 16.04±3.88 and 99.51±57.96. No relationship was observed between death anxiety and religious beliefs. Additionally, Pearson's correlation coefficient suggested a significant inverse relationship between religious beliefs, psychosis, and obsession. Furthermore, the findings suggested a significant correlation between the fear of death and religious beliefs in older adults with mental disorders. Moreover, the correlation coefficient between the fear of death and mental disorders was 0.499 (r=0.499, P<0.01); suggesting a significant correlation between these variables. Thus, the higher the death-anxiety level in the elderly, the more their mental disorders will be. Conclusion It is possible to reduce the occurrence or intensification of mental disorders. This could be done by arranging and implementing psychological programs to diminish death anxiety in the elderly.

No abstract