INTRODUCTION: In this study, we aimed to compare the performance of a convolutional neural network (CNN)-based deep learning model that was trained on a dataset of normal and abnormal paediatric elbow radiographs with that of paediatric emergency department (ED) physicians on a binomial classification task. METHODS: A total of 1,314 paediatric elbow lateral radiographs (patient mean age 8.2 years) were retrospectively retrieved and classified based on annotation as normal or abnormal (with pathology). They were then randomly partitioned to a development set (993 images); first and second tuning (validation) sets (109 and 100 images, respectively); and a test set (112 images). An artificial intelligence (AI) model was trained on the development set using the EfficientNet B1 network architecture. Its performance on the test set was compared to that of five physicians (inter-rater agreement: fair). Performance of the AI model and the physician group was tested using McNemar test. RESULTS: The accuracy of the AI model on the test set was 80.4% (95% confidence interval [CI] 71.8%-87.3%), and the area under the receiver operating characteristic curve (AUROC) was 0.872 (95% CI 0.831-0.947). The performance of the AI model vs. the physician group on the test set was: sensitivity 79.0% (95% CI: 68.4%-89.5%) vs. 64.9% (95% CI: 52.5%-77.3%; P = 0.088); and specificity 81.8% (95% CI: 71.6%-92.0%) vs. 87.3% (95% CI: 78.5%-96.1%; P = 0.439). CONCLUSION The AI model showed good AUROC values and higher sensitivity, with the P-value at nominal significance when compared to the clinician group.
Humans ; Deep Learning ; Child ; Retrospective Studies ; Male ; Female ; Radiography/methods* ; ROC Curve ; Elbow/diagnostic imaging* ; Neural Networks, Computer ; Child, Preschool ; Elbow Joint/diagnostic imaging* ; Emergency Service, Hospital ; Adolescent ; Infant ; Artificial Intelligence

INTRODUCTIONThis study evaluates determinants, expectations, association with quality of life (QOL) and doctor's awareness of Complementary and Alternative Medicine (CAM) use in Singapore cancer patients.

MATERIAL AND METHODSWe interviewed 316 patients visiting the Cancer Centre of the National University Hospital on behaviour, attitudes and expectations towards CAM and assessed QOL via Euroqol Questionnaire (EQ-5D). Medical information was obtained from oncologists.

RESULTSOne hundred and seventy-three patients (55%) reported CAM use after cancer diagnosis. Chinese ethnicity, tertiary education, age <65 years and previous CAM use were independent predictors of CAM use. Fifty-one per cent of CAM users informed their doctors about their use and 15% of doctors reported to be aware of CAM use in these patients. Thirty-seven per cent believed CAM to be equally or more effective than conventional cancer therapies and 78% expected at least basic knowledge about CAM from their oncologists. Twenty-fi ve per cent of patients reported concurrent use of oral CAM and chemotherapy, of which oncologists were unaware in 86% of cases. CAM users had higher EuroQol utility scores than non-CAM users (0.79 versus 0.73, respectively, P = 0.03), in particularly those aged >or=65 years and those with stage IV disease.

CONCLUSIONSingapore cancer patients show high prevalence of CAM use, high expectations regarding its effectiveness and doctors' knowledge on CAM and many use it concurrently with chemotherapy or radiotherapy. Since oncologists are generally unaware of CAM use in their patients, doctor-patient communication on CAM use needs to be improved. The association of CAM use and higher QOL scores in some subgroups deserves further exploration.

Adolescent ; Adult ; Aged ; Aged, 80 and over ; Complementary Therapies ; utilization ; Female ; Humans ; Interviews as Topic ; Male ; Middle Aged ; Neoplasms ; therapy ; Quality of Life ; Singapore ; Surveys and Questionnaires ; Young Adult