RESUMO
Soluble triggering receptor expressed on myeloid cells (sTREM-1) is a new biomarker that can be used for the diagnosis and monitoring of urinary system infections. This study aimed to evaluate the diagnostic performance of serum sTREM-1 in patients with a diagnosis of acute stone pyelonephritis (ASP). This prospective study included 46 patients with a diagnosis of ASP and a control group of 23 individuals without urinary system infection. Blood samples were taken from participants upon hospital admission, and basal serum sTREM-1 levels were analyzed using the ELISA method. Serum sTREM-1 concentrations were measured after treatment of ASP patients. Basal leukocyte counts, C-reactive protein (CRP) levels, procalcitonin (PCT), and sTREM-1 (98.6 vs. 68.4 pg/mL, p < 0.001) levels were higher in the ASP group compared to the control group. After treatment, the median leukocyte counts, PCT, and sTREM-1 levels decreased and were similar to those of the control group. The median CRP level also decreased after treatment, but it remained higher than that of the control group. In predicting patients with ASP, the baseline sTREM-1 exhibited a sensitivity of 74.6% and a specificity of 78.2%, while its diagnostic performance was lower than that of leukocyte counts, CRP, and PCT. Despite the findings that levels of sTREM-1 were higher upon hospital admission in patients with ASP and significantly decreased after treatment, the utility of sTREM-1 as a biomarker for predicting patients with ASP remains constrained when compared to established inflammatory markers.
RESUMO
Purpose: Predict central 10° global and local visual field (VF) measurements from macular optical coherence tomography (OCT) volume scans with deep learning (DL). Methods: This study included 1121 OCT volume scans and 10-2 VFs from 289 eyes (257 patients). Macular scans were used to estimate 10-2 VF mean deviation (MD), threshold sensitivities (TS), and total deviation (TD) values at 68 locations. A three-dimensional (3D) convolutional neural network based on the 3D DenseNet121 architecture was used for prediction. We compared DL predictions to those from baseline linear models. We carried out 10-fold stratified cross-validation to optimize generalizability. The performance of the DL and baseline models was compared based on correlations between ground truth and predicted VF measures and mean absolute error (MAE; ground truth - predicted values). Results: Average (SD) MD was -9.3 (7.7) dB. Average (SD) correlations between predicted and ground truth MD and MD MAE were 0.74 (0.09) and 3.5 (0.4) dB, respectively. Estimation accuracy deteriorated with worsening MD. Average (SD) Pearson correlations between predicted and ground truth TS and MAEs for DL and baseline model were 0.71 (0.05) and 0.52 (0.05) (P < 0.001) and 6.5 (0.6) and 7.5 (0.5) dB (P < 0.001), respectively. For TD, correlation (SD) and MAE (SD) for DL and baseline models were 0.69 (0.02) and 0.48 (0.05) (P < 0.001) and 6.1 (0.5) and 7.8 (0.5) dB (P < 0.001), respectively. Conclusions: Macular OCT volume scans can be used to predict global central VF parameters with clinically relevant accuracy. Translational Relevance: Macular OCT imaging may be used to confirm and supplement central VF findings using deep learning.
