Wrong-site surgeries can occur due to the absence of an appropriate surgical time-out. However, during a time-out, surgical participants are unable to review the patient’s charts due to their aseptic hands. To improve the conditions in surgical time-outs, we introduce a deep learning-based smart speaker to confirm the surgical information prior to cataract surgeries. This pilot study utilized the publicly available audio vocabulary dataset and recorded audio data published by the authors. The audio clips of the target words, such as left, right, cataract, phacoemulsification, and intraocular lens, were selected to determine and confirm surgical information in the time-out speech. A deep convolutional neural network model was trained and implemented in the smart speaker that was developed using a mini development board and commercial speakerphone. To validate our model in the consecutive speeches during time-outs, we generated 200 time-out speeches for cataract surgeries by randomly selecting the surgical statuses of the surgical participants. After the training process, the deep learning model achieved an accuracy of 96.3% for the validation dataset of short-word audio clips. Our deep learning-based smart speaker achieved an accuracy of 93.5% for the 200 time-out speeches. The surgical and procedural accuracy was 100%. Additionally, on validating the deep learning model by using web-generated time-out speeches and video clips for general surgery, the model exhibited a robust and good performance. In this pilot study, the proposed deep learning-based smart speaker was able to successfully confirm the surgical information during the time-out speech. Future studies should focus on collecting real-world time-out data and automatically connecting the device to electronic health records. Adopting smart speaker-assisted time-out phases will improve the patients’ safety during cataract surgeries, particularly in relation to wrong-site surgeries.

Lim HS, et al. Clin Nutr Res. 2019 Jan;8(1):28-35. https://doi.org/10.7762/cnr.2019.8.1.28

Minor glomerular abnormalities (MGAs) are unclassified glomerular lesions indicated by the presence of minor structural abnormalities that are insufficient for a specific pathological diagnosis. The long-term clinical outcomes and pathogenesis have not been examined. We hypothesized that MGAs would be associated with the deterioration of long-term kidney function and increased urinary mitochondrial DNA (mtDNA) copy numbers. We retrospectively enrolled patients with MGAs, age-/sex-/estimated glomerular filtration rate (eGFR)-matched patients with immunoglobulin A nephropathy (IgAN), and similarly matched healthy controls (MHCs; n = 49 each). We analyzed the time × group interaction effects of the eGFR and compared mean annual eGFR decline rates between the groups. We prospectively enrolled patients with MGAs, age- and sex-matched patients with IgAN, and MHCs (n = 15 each) and compared their urinary mtDNA copy numbers. Compared to the MHC group, the MGA and IgAN groups displayed differences in the time × group effects of eGFR, higher mean annual rates of eGFR decline, and higher urinary mtDNA copy numbers; however, these groups did not significantly differ from each other. The results indicate that MGAs are associated with deteriorating long-term kidney function, and mitochondrial injury, despite few additional pathological changes. We suggest that clinicians conduct close long-term follow-up of patients with MGAs.

Background: Kidney injury molecule-1 (KIM-1) is a biomarker useful for detecting early tubular damage and has been recently reported as a useful marker for evaluating kidney injury in IgA nephropathy (IgAN). We therefore investigated whether treatment decreases urinary KIM-1 excretion in IgAN. Methods: We prospectively enrolled 37 patients with biopsy-proven IgAN. Urinary KIM-1 was assessed before and after treatment, which included low salt diet, blood pressure control, pharmacotherapy with angiotensin receptor blockers and/or angiotensin converting enzyme inhibitors, and immunosuppressive agents as necessary. The median treatment duration was 24 months. Results: Urinary KIM-1/creatinine (Cr) was significantly decreased in patients with IgAN after treatment compared to baseline (P < 0.0001, 1.16 [0.51-1.83] vs 0.26 [0.12-0.65] ng/mg). There was a decrease in the amount of proteinuria after treatment, but it was not statistically significant (P = 0.052, 748.1 [405-1569.7] vs 569.2 [252.2-1114] g/d). Estimated glomerular filtration rate (eGFR) did not change with treatment (P = 0.599, 79.28 ± 30.56 vs 80.98 ± 32.37 ml/min/1.73 m²). Urinary KIM-1 was not correlated with proteinuria baseline or follow up (pre-: R = - 0.100, P = 0.577, post-: R = 0.001, P = 0.993). In patients with higher baseline urinary KIM-1, both urinary KIM-1 level and proteinuria were significantly decreased following treatment. Conclusions: Treatment decreases urinary KIM-1/Cr in patients with IgAN. It also reduces proteinuria in patients with higher baseline urinary KIM-1. These results suggest a potential role for urinary KIM-1 as a biomarker for predicting treatment response in IgAN, however, further study is needed to verify this.

C5b-9 plays an important role in the pathogenesis of immunoglobin A nephropathy (IgAN). We evaluated C5b-9 as a prognostic marker for IgAN. We prospectively enrolled 33 patients with biopsy-proven IgAN. We analyzed the correlation between baseline urinary C5b-9 levels, posttreatment changes in their levels, and clinical outcomes, including changes in proteinuria, estimated glomerular filtration rate (eGFR), and treatment response. Baseline urinary C5b-9 levels were positively correlated with proteinuria (r = 0.548, p = 0.001) at the time of diagnosis. Changes in urinary C5b-9 levels were positively correlated with changes in proteinuria (r = 0.644, p < 0.001) and inversely correlated with changes in eGFR (r = −0.410, p = 0.018) at 6 months after treatment. Changes in urinary C5b-9 levels were positively correlated with time-averaged proteinuria during the follow-up period (r = 0.461, p = 0.007) but were not correlated with the mean annual rate of eGFR decline (r = −0.282, p = 0.112). Baseline urinary C5b-9 levels were not a significant independent factor that could predict the treatment response in logistic regression analyses (odds ratio 0.997; 95% confidence interval, 0.993 to 1.000; p = 0.078). Currently, urinary C5b-9 is not a promising prognostic biomarker for IgAN, and further studies are needed.