published online; they have not yet been assigned to a journal issue. When these articles are published in an issue, they will be removed. Online First articles are copy-edited, typeset and approved by the authors before publication.

We aimed to determine the effect of optic disc tilt on deep learning-based optic disc classification. Image annotation was performed to label pathologic changes of the optic disc (normal, glaucomatous optic disc changes, disc swelling, and disc pallor) and note the appearance of a tilted optic disc (non-tilted versus tilted). Deep learning-based classification modeling was implemented to develop an optic-disc appearance classification. We acquired 2,507 fundus photographs from 2,236 subjects. Of the 2,507 data, 1,010 (40.3%) had tilted optic discs. The AUC of the models trained and tested using the non-tilted disc dataset was 0.988 ± 0.002, 0.991 ± 0.003, and 0.986 ± 0.003 for VGG16, VGG19, and DenseNet121, respectively. The AUC of the models trained and tested using the tilted disc dataset was 0.924 ± 0.046, 0.928 ± 0.017, and 0.935 ± 0.008. The model performance indicated by the AUC was better for non-tilted discs, regardless of the dataset used for training. In each pathologic change, non-tilted disc models showed better sensitivity than the tilted disc model. In the groups of glaucoma, disc pallor, and disc swelling, non-tilted disc models showed better specificity than the tilted disc model. We developed deep learning-based optic disc appearance classification systems using the fundus photographs of patients with and without tilted optic discs. The classification accuracy was lower in patients with the appearance of tilted discs compared to non-tilted discs, suggesting the need for identifying and adjusting for the effect of optic disc tilt on the optic disc classification algorithm in future development.

Abstract Background Reduced skeletal muscle mass and obesity worsens cardiometabolic risk factors. However, the combined effect of pre-sarcopenia and obesity on overt and subclinical cardiovascular disease (CVD) has yet to be explored. We aimed to investigate the interaction of reduced skeletal muscle mass and abdominal obesity on coronary artery calcification (CAC). Methods A total of 19,728 adults free of CVD who contemporaneously underwent cardiac tomography for estimating CAC scores and bioelectrical impedance analysis (BIA) at baseline were enrolled in the cross-sectional study. Among them, 5,401 subjects who had one and more follow-up CAC score were included in the longitudinal analysis. Skeletal muscle mass was presented using the skeletal muscle mass index (SMI) [SMI (%) = total appendicular muscle mass (kg)/body weight (kg) x 100] according to sex. CAC presence or incidence was defined as CAC score > 0, and CAC progression was defined as the square root-transformed difference between baseline and follow-up CAC scores > 2.5. Pre-sarcopenia was defined as SMI ≤ –1.0 standard deviation of the sex-specific mean of a young reference group (20-39 years). Abdominal obesity was defined as waist circumference ≥ 90 cm for men and ≥ 85 cm for women. All subjects were further classified into four groups: normal, abdominal obesity alone, pre-sarcopenia alone, and pre-sarcopenic obesity. Results In total subjects, the normal group was the most common at 57.8%, the abdominal obesity group was 20.4%, the pre-sarcopenic obesity group was 14.3%, and the pre-sarcopenia group was the lowest at 7.5%. The pre-sarcopenic obesity group showed the highest adjusted hazard ratios (AHRs) for CAC presence (AHR 2.16, 95% confident interval [CI]: 1.98-2.36, P <0.001) as well as total events of CAC incidence and progression (AHR 1.54, 95% CI: 1.37 – 1.75, P < 0.001), and the risks were significant compared with those of normal subjects. Pre-sarcopenic obesity significantly increased the risk of CAC incidence and progression compared to either pre-sarcopenia or abdominal obesity alone.Conclusions The coexistence of pre-sarcopenia and abdominal obesity was significantly associated with a higher risk of CAC presence and increases the risk of CAC incidence and progression independent of traditional CVD risk factors.