BACKGROUND: Hospital emergency department (ED) use by patients from residential aged care facilities (RACFs) is not always appropriate, and this calls for interventions to avoid some unnecessary uses. This study aims to compare patterns of ED use by RACF patients with and without a Hospital in the Nursing Home (HiNH) program. METHODS: RACF patients presenting to EDs of a hospital with and a hospital without this program during pre- and post-intervention periods were included. Data on patient demographics and ED presentation characteristics were obtained from the Emergency Department Information System database, and were analysed by descriptive and comparative statistics. RESULTS: In both hospitals, most RACF residents presenting to EDs were aged between 75–94 years, female, triaged at scale 3 to 5, and transferred on weekdays and during working hours. Almost half of them were subsequently admitted to hospitals. In accordance with the ICD-10-AM diagnostic coding system, diagnoses that consistently ranked among the top three reasons for visiting the two hospitals before and after intervention included Chapter XIX: injury and poisoning and Chapter X: respiratory diseases. Associated with the intervention, significant decreases in the numbers of presentations per 1000 RACF beds were identified among patients diagnosed with Chapter XI: digestive diseases [rate ratio (95％CI): 0.09 (0.04, 0.22);P<0.0001] and Chapter XXI: factors influencing health status and contact with health services [rate ratio (95％CI): 0.22 (0.07, 0.66);P=0.007]. CONCLUSION: The HiNH program may reduce the incidence of RACF residents visiting EDs for diagnoses of Chapter XI and Chapter XXI.

Objective : To develop an endoscopic automatic detection system in early gastric cancer (EGC) based on a region-based convolutional neural network ( Mask R-CNN) ． Methods : A total of 3 579 and 892 white light images (WLI) of EGC were obtained from the First Affiliated Hospital of Anhui Medical University for training and testing，respectively．Then，10 WLI videos were obtained prospectively to test dynamic performance of the RCNN system．In addition，400 WLI images were randomly selected for comparison with the Mask R-CNN system and endoscopists．Diagnostic ability was assessed by accuracy，sensitivity，specificity，positive predictive value ( PPV) ， and negative predictive value (NPV) . Results : The accuracy，sensitivity and specificity of the Mask R-CNN system in diagnosing EGC in WLI images were 90. 25% ，91. 06% and 89. 01% ，respectively，and there was no significant statistical difference with the results of pathological diagnosis．Among WLI real-time videos，the diagnostic accuracy was 90. 27%．The speed of test videos was up to 35 frames / s in real time．In the controlled experiment， the sensitivity of Maks R-CNN system was higher than that of the experts (93. 00% vs 80. 20% ，χ2 = 7. 059，P < 0. 001) ，and the specificity was higher than that of the juniors (82. 67% vs 71. 87% ，χ2 = 9. 955，P＜0. 001) ， and the overall accuracy rate was higher than that of the seniors (85. 25% vs 78. 00% ，χ2 = 7. 009，P＜0. 001) . Conclusion The Mask R-CNN system has excellent performance for detection of EGC under WLI，which has great potential for practical clinical application.