Search

While deep neural networks (DNNs) and other machine learning models often have higher accuracy than simpler models like logistic regression (LR), they are often considered to be "black box" models and this lack of interpretability and transparency is considered a challenge for clinical adoption. In healthcare, intelligible models not only help clinicians to understand the problem and create more targeted action plans, but also help to gain the clinicians' trust. One method of overcoming the limited interpretability of more complex models is to use Generalized Additive Models (GAMs). Standard GAMs simply model the target response as a sum of univariate models. Inspired by GAMs, the same idea can be applied to neural networks through an architecture referred to as Generalized Additive Models with Neural Networks (GAM-NNs). In this manuscript, we present the development and validation of a model applying the concept of GAM-NNs to allow for interpretability by visualizing the learned feature patterns related to risk of in-hospital mortality for patients undergoing surgery under general anesthesia. The data consists of 59,985 patients with a feature set of 46 features extracted at the end of surgery to which we added previously not included features: total anesthesia case time (1 feature); the time in minutes spent with mean arterial pressure (MAP) below 40, 45, 50, 55, 60, and 65 mmHg during surgery (6 features); and Healthcare Cost and Utilization Project (HCUP) Code Descriptions of the Primary current procedure terminology (CPT) codes (33 features) for a total of 86 features. All data were randomly split into 80% for training (n = 47,988) and 20% for testing (n = 11,997) prior to model development. Model performance was compared to a standard LR model using the same features as the GAM-NN. The data consisted of 59,985 surgical records, and the occurrence of in-hospital mortality was 0.81% in the training set and 0.72% in the testing set. The GAM-NN model with HCUP features had the highest area under the curve (AUC) 0.921 (0.895-0.95). Overall, both GAM-NN models had higher AUCs than LR models, however, had lower average precisions. The LR model without HCUP features had the highest average precision 0.217 (0.136-0.31). To assess the interpretability of the GAM-NNs, we then visualized the learned contributions of the GAM-NNs and compared against the learned contributions of the LRs for the models with HCUP features. Overall, we were able to demonstrate that our proposed generalized additive neural network (GAM-NN) architecture is able to (1) leverage a neural network's ability to learn nonlinear patterns in the data, which is more clinically intuitive, (2) be interpreted easily, making it more clinically useful, and (3) maintain model performance as compared to previously published DNNs.

Prediction models of post-liver transplant mortality are crucial so that donor organs are not allocated to recipients with unreasonably high probabilities of mortality. Machine learning algorithms, particularly deep neural networks (DNNs), can often achieve higher predictive performance than conventional models. In this study, we trained a DNN to predict 90-day post-transplant mortality using preoperative variables and compared the performance to that of the Survival Outcomes Following Liver Transplantation (SOFT) and Balance of Risk (BAR) scores, using United Network of Organ Sharing data on adult patients who received a deceased donor liver transplant between 2005 and 2015 (n = 57,544). The DNN was trained using 202 features, and the best DNN's architecture consisted of 5 hidden layers with 110 neurons each. The area under the receiver operating characteristics curve (AUC) of the best DNN model was 0.703 (95% CI: 0.682-0.726) as compared to 0.655 (95% CI: 0.633-0.678) and 0.688 (95% CI: 0.667-0.711) for the BAR score and SOFT score, respectively. In conclusion, despite the complexity of DNN, it did not achieve a significantly higher discriminative performance than the SOFT score. Future risk models will likely benefit from the inclusion of other data sources, including high-resolution clinical features for which DNNs are particularly apt to outperform conventional statistical methods.

Objective The endoscopic endonasal approach has emerged as an excellent option for the treatment of lesions involving the petroclival fissure (PCF). Here, we investigate the surgical anatomy of the ventral PCF and its application in endoscopic endonasal surgery. Methods Sixteen head specimens were used to investigate the anatomical features of PCF and relevant technical nuances in translacerum, extreme medial, and contralateral transmaxillary (CTM) approaches. Two representative endoscopic endonasal surgeries involving the PCF were selected to illustrate the clinical application. Results From the endoscopic endonasal view, the ventral PCF is presented as a lazy L sign, which is divided into two distinct segments: (1) upper (or petrosphenoidal) segment, which extends vertically from the foramen lacerum inferiorly to the junction of the petrosal process of sphenoid bone and petrous apex superiorly, and (2) lower (or petroclival) segment, which extends inferolaterally from the foramen lacerum to the ventral jugular foramen. Approaching both segments of the ventral PCF first requires full exposure of the foramen lacerum, followed either by exposure of the anterior wall of cavernous sinus and paraclival internal carotid artery for upper segment access, or transection of pterygosphenoidal fissure and Eustachian tube mobilization for lower segment access. Combined with a CTM approach, the lateral extension of the surgical access can be improved for both upper and lower segment PCF approaches. Conclusion This study provides a detailed investigation of the microsurgical anatomy of the ventral part of PCF, relevant surgical approaches, and technical nuances that may facilitate its safe exposure intraoperatively. [ABSTRACT FROM AUTHOR]

Introduction: Allograft dysfunction within the first week posttransplant is an uncommon but known complication following liver transplantation. Seventh‐Day Syndrome (7DS) is a rare complication of allograft dysfunction following liver transplantation characterized by the rapid clinical deterioration of a formerly well‐functioning allograft within the first week posttransplant. The etiology of 7DS is unknown, and treatment options remain limited. While cases of graft survival have been reported, the risk of mortality remains exceedingly high without urgent retransplantation. Methods: Patient data was retrospectively analyzed and a literature review performed. Results: We present a unique case of split liver transplantation into two pediatric recipients in which one recipient developed rapidly progressive graft failure approximately 1 week postoperatively requiring urgent retransplantation while the other recipient had an unremarkable postoperative course. Upon clinical manifestation of progressive graft failure, the patient was treated with thymoglobulin, rituximab, intravenous immunoglobulin, and plasmapheresis. Despite this, the patient's clinical status continued to decline and she underwent retransplantation 11 days following her initial liver transplant. Conclusion: Seventh‐Day Syndrome is a rare complication following liver transplantation that is associated with a high risk of morbidity and mortality. Our case adds to the limited literature on 7DS in children and is the first to report a comparative posttransplant clinical course in two recipients who received split grafts from the same donor. [ABSTRACT FROM AUTHOR]

What we already know about this topicWHAT THIS ARTICLE TELLS US THAT IS NEW: BACKGROUND:: The authors tested the hypothesis that deep neural networks trained on intraoperative features can predict postoperative in-hospital mortality.MethodsThe data used to train and validate the algorithm consists of 59,985 patients with 87 features extracted at the end of surgery. Feed-forward networks with a logistic output were trained using stochastic gradient descent with momentum. The deep neural networks were trained on 80% of the data, with 20% reserved for testing. The authors assessed improvement of the deep neural network by adding American Society of Anesthesiologists (ASA) Physical Status Classification and robustness of the deep neural network to a reduced feature set. The networks were then compared to ASA Physical Status, logistic regression, and other published clinical scores including the Surgical Apgar, Preoperative Score to Predict Postoperative Mortality, Risk Quantification Index, and the Risk Stratification Index.ResultsIn-hospital mortality in the training and test sets were 0.81% and 0.73%. The deep neural network with a reduced feature set and ASA Physical Status classification had the highest area under the receiver operating characteristics curve, 0.91 (95% CI, 0.88 to 0.93). The highest logistic regression area under the curve was found with a reduced feature set and ASA Physical Status (0.90, 95% CI, 0.87 to 0.93). The Risk Stratification Index had the highest area under the receiver operating characteristics curve, at 0.97 (95% CI, 0.94 to 0.99).ConclusionsDeep neural networks can predict in-hospital mortality based on automatically extractable intraoperative data, but are not (yet) superior to existing methods.

Perianeurysmal cysts are a rare and poorly understood finding in patients both with treated and untreated aneurysms. While the prior literature suggests that a minority of perianeurysmal cysts develop 1-4 years following endovascular aneurysm treatment, this updated review demonstrates that nearly half of perianeurysmal cysts were diagnosed following aneurysm coiling, with the other half diagnosed concurrently with an associated aneurysm prior to treatment. 64% of perianeurysmal cysts were surgically decompressed, with a 39% rate of recurrence requiring re-operation. We report a case of a 71-year-old woman who presented with vertigo and nausea and was found to have a 3.4 cm perianeurysmal cyst 20 years after initial endovascular coiling of a ruptured giant ophthalmic aneurysm. The cyst was treated with endoscopic fenestration followed by open fenestration upon recurrence. The case represents the longest latency from initial aneurysm treatment to cyst diagnosis reported in the literature and indicates that the diagnosis of perianeurysmal cyst should remain on the differential even decades after treatment. Based on a case discussion and updated literature review, this report highlights proposed etiologies of development and management strategies for a challenging lesion. [ABSTRACT FROM AUTHOR]

Summary: Background: Data on oral vancomycin for primary sclerosing cholangitis (PSC)‐associated inflammatory bowel disease (IBD) are limited. Aims: Using data from the Paediatric PSC Consortium, to examine the effect of vancomycin on IBD activity. Methods: In this retrospective multi‐centre cohort study, we matched vancomycin‐treated and untreated patients (1:3) based on IBD duration at the time of primary outcome assessment. The primary outcome was Physician Global Assessment (PGA) of IBD clinical activity after 1 year (±6 months) of vancomycin. We used generalised estimating equations (GEE) to examine the association between vancomycin and PGA remission, adjusting for IBD type, severity and medication exposures. Secondary outcomes included serum labs and endoscopic remission (global rating of no activity) among those with available data and also analysed with GEE. Results: 113 PSC‐IBD patients received vancomycin (median age 12.7 years, 63% male). The matched cohort included 70 vancomycin‐treated and 210 untreated patients. Vancomycin was associated with greater odds of IBD clinical remission (odds ratio [OR] 3.52, 95% CI 1.97–6.31; adjusted OR [aOR] 5.24, 95% CI 2.68–10.22). Benefit was maintained in sensitivity analyses restricted to non‐transplanted patients and those with baseline moderate–severe PGA. Vancomycin was associated with increased odds of endoscopic remission (aOR 2.76, 95% CI 1.002–7.62; N = 101 with data), and with lower CRP (p = 0.03) and higher haemoglobin and albumin (both p < 0.01). Conclusion: Vancomycin was associated with greater odds of IBD clinical and endoscopic remission. Additional, preferably randomised, controlled studies are needed to characterise efficacy using objective markers of mucosal inflammation, and to examine safety and define optimal dosing. [ABSTRACT FROM AUTHOR]

This article, titled "Cavernous Sinus Exenteration for Invasive Mucormycosis," discusses a case study of a 61-year-old woman with HIV and diabetes mellitus who experienced vision loss due to invasive rhino-orbito-cerebral mucormycosis. Despite initial surgery and antifungal therapy, the disease progressed into the cavernous sinus and trigeminal nerve branches. The authors performed a STA-to-MCA bypass and a middle fossa approach for cavernous sinus exenteration, which successfully controlled the disease. The article highlights the technical aspects of cavernous sinus exenteration. [Extracted from the article]

This article, published in the Journal of Neurological Surgery, explores the pterygoid-sphenoidal fissure (PSF) as a key landmark for accessing the foramen lacerum in pediatric endoscopic endonasal surgery. The study evaluates the morphometry and developmental variations of the PSF in a general pediatric population using computed tomography scans. The results show that the length, width, and morphology of the PSF vary significantly across different age groups. Understanding these radiological findings is important for preoperative planning and intraoperative guidance in pediatric endoscopic endonasal surgery. [Extracted from the article]

This article, published in the Journal of Neurological Surgery, discusses a case presentation of a 2-year-old boy with a tubero-infundibular craniopharyngioma. The boy had a history of previous surgeries and developed visual abnormalities due to the growth of the tumor. The authors used an endoscopic endonasal transplanum approach to completely remove the tumor, resulting in improvement of visual symptoms. However, the patient did develop diabetes insipidus postoperatively. The article provides valuable insights into the treatment of pediatric patients with craniopharyngioma. [Extracted from the article]

This article discusses the surgical anatomy of the transmastoid transcervical intradural approach to the jugular foramen, which is a challenging area for skull base surgeons due to the presence of critical structures. The approach is versatile and allows for modifications to tailor it to specific tumors. The article provides a detailed description of the surgical steps and relevant anatomy, including variations such as vertebral artery transposition and facial nerve rerouting. The transmastoid transcervical intradural approach provides excellent exposure to the jugular foramen and surrounding areas, but precise knowledge of the anatomy is crucial due to the complex relationships of vital structures in this region. [Extracted from the article]

This article discusses seven different techniques for pituitary transposition in endoscopic endonasal surgery. The techniques are categorized based on their relationship with the dura mater and include extradural, hybrid extradural/intradural, interdural transcavernous, extended interdural transcavernous, intradural hemitransposition, intradural, and pituitary sacrifice. The article evaluates the clinical application and selection of these techniques in different anatomical regions and types of pathology. The authors emphasize the importance of selecting the most appropriate technique based on the specific case and preoperative pituitary function for successful surgical outcomes. [Extracted from the article]

This article, published in the Journal of Neurological Surgery, examines the impact of the transcavernous extension of the endonasal endoscopic approach on posterior pituitary function for the resection of pituitary adenomas. The study retrospectively reviewed 290 patients who underwent endoscopic endonasal resection of pituitary adenomas and compared the incidence of postoperative diabetes insipidus (DI) between groups based on the occurrence of transcavernous extension. The results showed that the transcavernous approach with medial wall of the cavernous sinus (MWCS) resection did not increase the risk of postoperative DI. [Extracted from the article]