Automated detection of enteric tubes misplaced in the respiratory tract on chest radiographs using deep learning with two centre validation.

AIM: To develop and test a model based on a convolutional neural network that can identify enteric tube position accurately on chest radiography. MATERIALS AND METHODS: The chest radiographs of adult patients were classified by radiologists based on enteric tube position as either critically misplaced (within the respiratory tract) or not critically misplaced (misplaced within the oesophagus or safely positioned below the diaphragm). A deep-learning model based on the 121-layer DenseNet architecture was developed using a training and validation set of 4,693 chest radiographs. The model was evaluated on an external test data set from a separate institution that consisted of 1,514 consecutive radiographs with a real-world incidence of critically misplaced enteric tubes. RESULTS: The receiver operator characteristic area under the curve was 0.90 and 0.92 for the internal validation and external test data sets, respectively. For the external data set with a prevalence of 4.4% of critically misplaced enteric tubes, the model achieved high accuracy (92%), sensitivity (80%), and specificity (92%) for identifying a critically misplaced enteric tube. The negative predictive value (99%) was higher than the positive predictive value (32%). CONCLUSION: The present study describes the development and external testing of a model that accurately identifies an enteric tube misplaced within the respiratory tract. This model could help reduce the risk of the catastrophic consequences of feeding through a misplaced enteric tube.

Alloantibody Responses After Renal Transplant Failure Can Be Better Predicted by Donor-Recipient HLA Amino Acid Sequence and Physicochemical Disparities Than Conventional HLA Matching.

We have assessed whether HLA immunogenicity as defined by differences in donor-recipient HLA amino-acid sequence (amino-acid mismatch score, AMS; and eplet mismatch score, EpMS) and physicochemical properties (electrostatic mismatch score, EMS) enables prediction of allosensitization to HLA, and also prediction of the risk of an individual donor-recipient HLA mismatch to induce donor-specific antibody (DSA). HLA antibody screening was undertaken using single-antigen beads in 131 kidney transplant recipients returning to the transplant waiting list following first graft failure. The effect of AMS, EpMS, and EMS on the development of allosensitization (calculated reaction frequency [cRF]) and DSA was determined. Multivariate analyses, adjusting for time on the waiting list, maintenance on immunosuppression after transplant failure, and graft nephrectomy, showed that AMS (odds ratio [OR]: 1.44 per 10 units, 95% CI: 1.02-2.10, p = 0.04) and EMS (OR: 1.27 per 10 units, 95% CI: 1.02-1.62, p = 0.04) were independently associated with the risk of developing sensitization to HLA (cRF > 15%). AMS, EpMS, and EMS were independently associated with the development of HLA-DR and HLA-DQ DSA, but only EMS correlated with the risk of HLA-A and -B DSA development. Differences in donor-recipient HLA amino-acid sequence and physicochemical properties enable better assessment of the risk of HLA-specific sensitization than conventional HLA matching.

Successful transplantation of kidneys from elderly circulatory death donors by using microscopic and macroscopic characteristics to guide single or dual implantation.

Most kidneys from potential elderly circulatory death (DCD) donors are declined. We report single center outcomes for kidneys transplanted from DCD donors over 70 years old, using preimplantation biopsy Remuzzi grading to inform implantation as single or dual transplants. Between 2009 and 2012, 43 single transplants and 12 dual transplants were performed from elderly DCD donors. Remuzzi scores were higher for dual than single implants (4.4 vs. 3.4, p < 0.001), indicating more severe baseline injury. Donor and recipient characteristics for both groups were otherwise similar. Early graft loss from renal vein thrombosis occurred in two singly implanted kidneys, and in one dual-implanted kidney; its pair continued to function satisfactorily. Death-censored graft survival at 3 years was comparable for the two groups (single 94%; dual 100%), as was 1 year eGFR. Delayed graft function occurred less frequently in the dual-implant group (25% vs. 65%, p = 0.010). Using this approach, we performed proportionally more kidney transplants from elderly DCD donors (23.4%) than the rest of the United Kingdom (7.3%, p < 0.001), with graft outcomes comparable to those achieved nationally for all deceased-donor kidney transplants. Preimplantation biopsy analysis is associated with acceptable transplant outcomes for elderly DCD kidneys and may increase transplant numbers from an underutilized donor pool.

Use of Ex Vivo Normothermic Perfusion for Quality Assessment of Discarded Human Donor Pancreases.

A significant number of pancreases procured for transplantation are deemed unsuitable due to concerns about graft quality and the associated risk of complications. However, this decision is subjective and some declined grafts may be suitable for transplantation. Ex vivo normothermic perfusion (EVNP) prior to transplantation may allow a more objective assessment of graft quality and reduce discard rates. We report ex vivo normothermic perfusion of human pancreases procured but declined for transplantation, with ABO-compatible warm oxygenated packed red blood cells for 1-2 h. Five declined human pancreases were assessed using this technique after a median cold ischemia time of 13 h 19 min. One pancreas, with cold ischemia over 30 h, did not appear viable and was excluded. In the remaining pancreases, blood flow and pH were maintained throughout perfusion. Insulin secretion was observed in all four pancreases, but was lowest in an older donation after cardiac death pancreas. Amylase levels were highest in a gland with significant fat infiltration. This is the first study to assess the perfusion, injury, as measured by amylase, and exocrine function of human pancreases using EVNP and demonstrates the feasibility of the approach, although further refinements are required.

Physiochemical disparity of mismatched HLA class I alloantigens and risk of acute GVHD following HSCT.

We determined whether assessment of the immunogenicity of individual donor-recipient HLA mismatches based on differences in their amino-acid sequence and physiochemical properties predicts clinical outcome following haematopoietic SCT (HSCT). We examined patients transplanted with 9/10 single HLA class I-mismatched grafts (n=171) and 10/10 HLA-A-, -B-, -C-, -DRB1- and -DQB1-matched grafts (n=168). A computer algorithm was used to determine the physiochemical disparity (electrostatic mismatch score (EMS) and hydrophobic mismatch score (HMS)) of mismatched HLA class I specificities in the graft-versus-host direction. Patients transplanted with HLA-mismatched grafts with high EMS/HMS had increased incidence of ⩾grade II acute GVHD (aGVHD) compared with patients transplanted with low EMS/HMS grafts; patients transplanted with low and medium EMS/HMS grafts had similar incidence of aGVHD to patients transplanted with 10/10 HLA-matched grafts. Mortality was higher following single HLA-mismatched HSCT but was not correlated with HLA physiochemical disparity. Assessment of donor-recipient HLA incompatibility based on physiochemical HLA disparity may enable better selection of HLA-mismatched donors in HSCT.

The diagnostic value of fine needle aspiration in parotid lumps.

INTRODUCTION: Fine needle aspiration (FNA) is a safe and quick method of diagnosing superficial lumps, which aids preoperative planning. However, FNA of the parotid gland has not gained the widespread acceptance noted in other head and neck lumps. The aim of this study was to determine the ability of FNA of the parotid gland to differentiate benign and malignant disease, and to determine the impact on surgical outcome. METHODS: A retrospective analysis of 201 consecutive parotid operations with preoperative FNA in a large district hospital in the UK was performed. The diagnostic characteristics were calculated for benign and malignant disease, and the impact on surgical procedure was determined. RESULTS: In identifying benign disease, FNA has a sensitivity of 85% and a specificity of 76%. In detecting malignant disease, FNA has a sensitivity and specificity of 52% and 92% respectively. A false positive on FNA was associated with a higher incidence of neck dissection. CONCLUSIONS: FNA is a useful diagnostic test. However, owing to low sensitivity, it is necessary to interpret it in the context of all other clinical information.