Predicting acute brain lesions on magnetic resonance imaging in acute carbon monoxide poisoning: a multicenter prospective observational study.

An acute brain lesion (ABL) identified by brain magnetic resonance imaging (MRI) after acute carbon monoxide (CO) poisoning is a strong prognostic factor for the development of delayed neuropsychiatric syndrome (DNS). This study aimed to identify predictors of ABLs on MRI in patients with acute CO poisoning. This was a multicenter prospective registry-based observational study conducted at two tertiary hospitals. A total of 1,034 patients were included. Multivariable logistic regression analysis showed that loss of consciousness (LOC) (adjusted odds ratio [aOR] 2.68, 95% Confidence Interval [CI]: 1.49-5.06), Glasgow Coma Scale (GCS) score < 9 (aOR 2.41, 95% CI: 1.49-3.91), troponin-I (TnI) (aOR 1.22, 95% CI: 1.08-1.41), CO exposure duration (aOR 1.09, 95% CI: 1.05-1.13), and white blood cell (WBC) (aOR 1.05, 95% CI: 1.01-1.09) were independent predictors of ABLs on MRI. LOC, GCS score, TnI, CO exposure duration, and WBC count can be useful predictors of ABLs on MRI in patients with acute CO poisoning, helping clinicians decide the need for an MRI scan or transfer the patient to an appropriate institution for MRI or hyperbaric oxygen therapy.

Classification of Central Venous Catheter Tip Position on Chest X-ray Using Artificial Intelligence.

Recent studies utilizing deep convolutional neural networks (CNN) have described the central venous catheter (CVC) on chest radiography images. However, there have been no studies for the classification of the CVC tip position with a definite criterion on the chest radiograph. This study aimed to develop an algorithm for the automatic classification of proper depth with the application of automatic segmentation of the trachea and the CVC on chest radiographs using a deep CNN. This was a retrospective study that used plain chest supine anteroposterior radiographs. The trachea and CVC were segmented on images and three labels (shallow, proper, and deep position) were assigned based on the vertical distance between the tracheal carina and CVC tip. We used a two-stage approach model for the automatic segmentation of the trachea and CVC with U-net++ and automatic classification of CVC placement with EfficientNet B4. The primary outcome was a successful three-label classification through five-fold validations with segmented images and a test with segmentation-free images. Of a total of 808 images, 207 images were manually segmented and the overall accuracy of the five-fold validation for the classification of three-class labels (mean (SD)) of five-fold validation was 0.76 (0.03). In the test for classification with 601 segmentation-free images, the average accuracy, precision, recall, and F1-score were 0.82, 0.73, 0.73, and 0.73, respectively. We achieved the highest accuracy value of 0.91 in the shallow position label, while the highest F1-score was 0.82 in the deep position label. A deep CNN can achieve a comparative performance in the classification of the CVC position based on the distance from the carina to the CVC tip as well as automatic segmentation of the trachea and CVC on plain chest radiographs.