Background Anaemia is an important health-care burden globally, and screening for anaemia is crucial to prevent multi-organ injury, irreversible complications, and life-threatening adverse events. We aimed to establish whether a deep learning algorithm (DLA) that enables non-invasive anaemia screening from electrocardiograms (ECGs) might improve the detection of anaemia.Methods We did a retrospective, multicentre, diagnostic study in which a DLA was developed using ECGs and then internally and externally validated. We used data from two hospitals, Sejong General Hospital (hospital A) and Mediplex Sejong Hospital (hospital B), in South Korea. Data from hospital A was for DLA development and internal validation, and data from hospital B was for external validation. We included individuals who had at least one ECG with a haemoglobin measurement within 1 h of the index ECG and excluded individuals with missing demographic, electrocardiographic, or haemoglobin information. Three types of DLA were developed with 12-lead, 6-lead (limb lead), and single-lead (lead I) ECGs to detect haemoglobin concentrations of 10 g/dL or less. The DLA was built by a convolutional neural network and used 500-Hz raw ECG, age, and sex as input data.

BackgroundNew-onset diabetes mellitus after transplantation (NODAT) is a serious complication following renal transplantation. The aim of this study was to identify the risk factors for the development of NODAT in Korean transplant patients.MethodsRecipients who underwent living donor kidney transplantation between January 2009 and April 2012 at Asan Medical Center were reviewed. Diagnosis of NODAT was defined according to the American Diabetes Association criteria.ResultsA total of 418 patients were enrolled. NODAT was diagnosed in 85 (20.4 %) patients within 1 year. By multivariate analysis, old age (odds ratio [OR], 1.05; 95 % Confidence interval [CI]: 1.01–1.08), family history of diabetes mellitus (OR, 2.48; 95 % CI: 1.04–5.94), pre-transplant high serum glucose level (OR, 1.04; 95 % CI: 1.01–1.08), and obesity (OR, 3.46; 95 % CI: 1.55–7.73) were independent risk factors for NODAT.ConclusionOld age, family history of diabetes, pre-transplant high plasma glucose level, and obesity are independent factors associated with the development of diabetes after renal transplantation. In contrast, serum magnesium levels and the use of tacrolimus are not associated with the development of NODAT.Electronic supplementary materialThe online version of this article (doi:10.1186/s12882-016-0321-8) contains supplementary material, which is available to authorized users.

Background: Latent tuberculosis infection (LTBI) is prevalent in end-stage renal disease (ESRD) patients. The risk of tuberculosis activation is also high. The appropriate LTBI screening and treatment is required in this population. Meanwhile, whether hemodialysis adequacy is associated with LTBI in the ESRD population is unclear. In this study, we aimed to investigate the association between hemodialysis adequacy and LTBI in ESRD patients. Methods: In the present cross-sectional study, we reviewed all outpatient-based ESRD patients in our artificial kidney room. Interferon gamma release assay (IGRA) was used for the diagnosis of LTBI. Clinical variables including nutritional adequacy (i.e., normalized protein catabolic rate, nPCR) and dialysis adequacy (i.e., Kt/V) were compared between IGRA-positive and IGRA-negative patients. Results: A total of 90 patients were enrolled, of which 20 (22.2%) had positive IGRA results using the QuantiFERON-TB method. Old fibrotic changes and nPCR (g/kg/day) were significantly different between IGRA-positive and IGRA-negative patients (both p < 0.005), while serum albumin and Kt/V were comparable (p = 0.429 and p = 0.590, respectively). Normalized PCR remained to be significant in a multivariate logistic regression analysis (adjusted hazard ratio, 0.911 (0.861–0.963); p = 0.001). The cutoff nPCR value less than 0.87 g/kg/day had an adjusted hazard ratio of 7.74 (1.77–33.74) for predicting LTBI. Patients with nPCR value less than 0.87 g/kg/day were older and had lower serum hemoglobin, albumin, calcium concentration, and Kt/V levels than those with nPCR value greater than 0.87 g/kg/day. Conclusions: Nutritional adequacy, especially when assessing nPCR value, was associated with LTBI, while dialysis adequacy was not associated with LTBI.