Telescreening satisfaction: disparities between individuals with diabetic retinopathy and community health center staff

Ultrasound-guided caudal anaesthesia combined with epidural anaesthesia for caesarean section: a randomized controlled clinical trial

BACKGROUND

Although epidural anaesthesia and spinal anaesthesia are currently the general choices for patients undergoing caesarean section, these two neuraxial anaesthesia methods still have drawbacks. Caudal anaesthesia has been considered to be more appropriate for gynaecological surgery. The purpose of this study was to compare epidural anaesthesia combined with caudal anaesthesia, spinal anaesthesia and single-space epidural anaesthesia for caesarean section with respect to postoperative comfort and intraoperative anaesthesia quality.

METHODS

In this clinical trial, 150 patients undergoing elective caesarean section were recruited and randomized into three groups according to a ratio of 1:1:1to receive epidural anaesthesia only, spinal anaesthesia only or epidural anaesthesia combined with caudal anaesthesia. The primary outcome was postoperative comfort in the three groups. Secondary outcomes included intraoperative anaesthesia quality and the incidences of nausea, vomiting, postdural puncture headache, maternal bradycardia, or hypotension.

RESULTS

More patients were satisfied with the intraoperative anaesthesia quality in the EAC group than in the EA group (P = 0.001). The obstetrician was more significantly satisfied with the intraoperative anaesthesia quality in the SA and EAC groups than in the EA group (P = 0.004 and 0.020, respectively). The parturients felt more comfortable after surgery in the EA and EAC groups (P = 0.007). The incidence of maternal hypotension during caesarean section was higher in the SA group than in the EA and EAC groups (P = 0.001 and 0.019, respectively).

CONCLUSIONS

Epidural anaesthesia combined with caudal anaesthesia may be a better choice for elective caesarean section. Compared with epidural anaesthesia and spinal anaesthesia, it has a higher quality of postoperative comfort and intraoperative anaesthesia.

Deep learning-based analysis of infrared fundus photography for automated diagnosis of diabetic retinopathy with cataracts

PURPOSE

To develop deep learning-based networks for the diagnosis of diabetic retinopathy (DR) with cataracts based on infrared fundus images.

SETTING

Shanghai General Hospital, Shanghai Eye Disease Prevention & Treatment Center, Shanghai, China.

DESIGN

Development and evaluation of an artificial intelligence (AI) diagnostic method.

METHODS

A total of 10 665 infrared fundus images from 4553 patients with diabetes were used to train and test the model. For image quality assessment, left and right eye classification, DR diagnosis and grading, and segmentation of 3 DR lesions, an end-to-end software using EfficientNet and UNet was developed. The accuracy and performance of the software in comparison to human experts was evaluated.

RESULTS

The model achieved an accuracy of 75.31% for left and right eye classification, 100% for DR grading and diagnosis tasks, and 73.67% for internal test set, with corresponding areas under the curve (AUCs) of 0.88, 1.00, and 0.89, respectively. For DR lesion segmentation, the AUCs of hemorrhagic, microangioma, and exudative lesions were 0.86, 0.66, and 0.84, respectively. In addition, a contrast test of human-machine film reading confirmed the software's high sensitivity (96.3%) and specificity (90.0%) and consistency with the manual film reading group (κ = 0.869, P < .001). This easily deployable software generated reports quickly and promoted efficient DR screening with cataracts in clinical and community settings.

CONCLUSIONS

AI-assisted software can perform automatic analysis of infrared fundus images and has substantial application value for the diagnosis of DR patients with cataracts.