ABSTRACT
Background and study aims Artificial intelligence (AI)-assisted image classification has been shown to have high accuracy on endoscopic diagnosis. We evaluated the potential effects of use of an AI-assisted image classifier on training of junior endoscopists for histological prediction of gastric lesions. Methods An AI image classifier was built on a convolutional neural network with five convolutional layers and three fully connected layers A Resnet backbone was trained by 2,000 non-magnified endoscopic gastric images. The independent validation set consisted of another 1,000 endoscopic images from 100 gastric lesions. The first part of the validation set was reviewed by six junior endoscopists and the prediction of AI was then disclosed to three of them (Group A) while the remaining three (Group B) were not provided this information. All endoscopists reviewed the second part of the validation set independently. Results The overall accuracy of AI was 91.0â% (95â% CI: 89.2-92.7â%) with 97.1â% sensitivity (95â% CI: 95.6-98.7%), 85.9â% specificity (95â% CI: 83.0-88.4â%) and 0.91 area under the ROC (AUROC) (95â% CI: 0.89-0.93). AI was superior to all junior endoscopists in accuracy and AUROC in both validation sets. The performance of Group A endoscopists but not Group B endoscopists improved on the second validation set (accuracy 69.3â% to 74.7â%; P â=â0.003). Conclusion The trained AI image classifier can accurately predict presence of neoplastic component of gastric lesions. Feedback from the AI image classifier can also hasten the learning curve of junior endoscopists in predicting histology of gastric lesions.
ABSTRACT
BACKGROUND: Influenza causes excessive hospitalizations and deaths. The study assessed the efficacy and safety of a clarithromycin-naproxen-oseltamivir combination for treatment of serious influenza. METHODS: From February to April 2015, we conducted a prospective open-label, randomized, controlled trial. Adult patients hospitalized for A(H3N2) influenza were randomly assigned to a 2-day combination of clarithromycin 500 mg, naproxen 200 mg, and oseltamivir 75 mg twice daily, followed by 3 days of oseltamivir or to oseltamivir 75 mg twice daily without placebo for 5 days as a control method (1:1). The primary end point was 30-day mortality. The secondary end points were 90-day mortality, serial nasopharyngeal aspirate (NPA) virus titer, percentage of neuraminidase-inhibitor-resistant A(H3N2) virus (NIRV) quasispecies, pneumonia severity index (PSI), and duration of hospital stay. RESULTS: Among the 217 patients with influenza A(H3N2) enrolled, 107 were randomly assigned to the combination treatment. The median age was 80 years, and 53.5% were men. Adverse events were uncommon. Ten patients died during the 30-day follow-up. The combination treatment was associated with lower 30-day mortality (P = .01), less frequent high dependency unit admission (P = .009), and shorter hospital stay (P < .0001). The virus titer and PSI (days 1-3; P < .01) and the NPA specimens with NIRV quasispecies ≥ 5% (days 1-2; P < .01) were significantly lower in the combination treatment group. Multivariate analysis showed that combination treatment was the only independent factor associated with lower 30-day mortality (OR, 0.06; 95% CI, 0.004-0.94; P = .04). CONCLUSIONS: Combination treatment reduced both 30- and 90-day mortality and length of hospital stay. Further study of the antiviral and immunomodulatory effects of this combination treatment of severe influenza is warranted. TRIAL REGISTRY: BioMed Central; No.: ISRCTN11273879 DOI 10.1186/ISRCTN11273879; URL: www.isrctn.com/ISRCTN11273879.