Background: Collateral status is an important predictor for the outcome of acute ischemic stroke with large vessel occlusion. Multiphase computed-tomography angiography (mCTA) is useful to evaluate the collateral status, but visual evaluation of this examination is time-consuming. This study aims to use an artificial intelligence (AI) technique to develop an automatic AI prediction model for the collateral status of mCTA. Methods: This retrospective study enrolled subjects with acute ischemic stroke receiving endovascular thrombectomy between January 2015 and June 2020 in a tertiary referral hospital. The demographic data and images of mCTA were collected. The collateral status of all mCTA was visually evaluated. Images at the basal ganglion and supraganglion levels of mCTA were selected to produce AI models using the convolutional neural network (CNN) technique to automatically predict the collateral status of mCTA. Results: A total of 82 subjects were enrolled. There were 57 cases randomly selected for the training group and 25 cases for the validation group. In the training group, there were 40 cases with a positive collateral result (good or intermediate) and 17 cases with a negative collateral result (poor). In the validation group, there were 21 cases with a positive collateral result and 4 cases with a negative collateral result. During training for the CNN prediction model, the accuracy of the training group could reach 0.999 ± 0.015, whereas the prediction model had a performance of 0.746 ± 0.008 accuracy on the validation group. The area under the ROC curve was 0.7. Conclusions: This study suggests that the application of the AI model derived from mCTA images to automatically evaluate the collateral status is feasible.

The study's aim was to determine if there was an association between gastric morphology and gastroesophageal reflux (GER). Few published studies have investigated the relationship between gastric morphology and the risk of GER. A total of 777 patients were randomly selected from 3000 to 3300 patients who presented at a medical center in Taipei for annual health checkups from early 2008 through to late 2010 and underwent a series of radiographs of the upper gastrointestinal tract (UGI). GER was recorded during the real-time fluoroscopic study. Thirty-nine participants had a follow-up endoscopy, and another 164 participants were followed up by a second UGI series 12 +/ −1.5 months later, from late 2008 through to early 2022. All participants completed a lifestyle and symptom questionnaire. The variables included current smoking and alcohol consumption. Participants who had heartburn and dysphagia were included in the study. Additionally, all participants underwent a limited physical examination which recorded age, sex, body mass index, and total cholesterol and triglyceride levels. All participants were classified into types 1 to 6 based on the gastric morphology determined from the first UGI. Cascade stomach is recognized by characteristic findings on UGI. Gastric types 2 and 3 tend to appear as cascade stomachs and were significantly associated with GER ( P < .05) compared with the other groups. Morphologic type 5 appeared as an elongated sac extending downward into the pelvic cavity and was less likely to develop GER ( P < .001). The results of follow-up studies by UGI and endoscopy were similar to those of the first UGI. Gastric morphologic type 2 was significantly associated, and type 5 was usually not associated, with GER and erosive esophagitis ( P < .05) compared with the other groups, by both UGI and endoscopy. Gastric morphologic types 2 and 3, with cascade stomach, might provide a relatively easy method for the development of the GER phenomenon. Gastric morphologic type 5 appeared as an elongated sac that might reduce the incidence of the GER phenomenon. The study suggested that gastric morphologic type could influence the occurrence of GER.

No abstract