Search

Although high-dimensional clinical data (HDCD) are increasingly available in biobank-scale datasets, their use for genetic discovery remains challenging. Here we introduce an unsupervised deep learning model, Representation Learning for Genetic Discovery on Low-Dimensional Embeddings (REGLE), for discovering associations between genetic variants and HDCD. REGLE leverages variational autoencoders to compute nonlinear disentangled embeddings of HDCD, which become the inputs to genome-wide association studies (GWAS). REGLE can uncover features not captured by existing expert-defined features and enables the creation of accurate disease-specific polygenic risk scores (PRSs) in datasets with very few labeled data. We apply REGLE to perform GWAS on respiratory and circulatory HDCD-spirograms measuring lung function and photoplethysmograms measuring blood volume changes. REGLE replicates known loci while identifying others not previously detected. REGLE are predictive of overall survival, and PRSs constructed from REGLE loci improve disease prediction across multiple biobanks. Overall, REGLE contain clinically relevant information beyond that captured by existing expert-defined features, leading to improved genetic discovery and disease prediction., (© 2024. The Author(s).)

Chronic obstructive pulmonary disease (COPD), the third leading cause of death worldwide, is highly heritable. While COPD is clinically defined by applying thresholds to summary measures of lung function, a quantitative liability score has more power to identify genetic signals. Here we train a deep convolutional neural network on noisy self-reported and International Classification of Diseases labels to predict COPD case-control status from high-dimensional raw spirograms and use the model's predictions as a liability score. The machine-learning-based (ML-based) liability score accurately discriminates COPD cases and controls, and predicts COPD-related hospitalization without any domain-specific knowledge. Moreover, the ML-based liability score is associated with overall survival and exacerbation events. A genome-wide association study on the ML-based liability score replicates existing COPD and lung function loci and also identifies 67 new loci. Lastly, our method provides a general framework to use ML methods and medical-record-based labels that does not require domain knowledge or expert curation to improve disease prediction and genomic discovery for drug design., (© 2023. The Author(s), under exclusive licence to Springer Nature America, Inc.)

Genome-wide association studies (GWASs) require accurate cohort phenotyping, but expert labeling can be costly, time intensive, and variable. Here, we develop a machine learning (ML) model to predict glaucomatous optic nerve head features from color fundus photographs. We used the model to predict vertical cup-to-disc ratio (VCDR), a diagnostic parameter and cardinal endophenotype for glaucoma, in 65,680 Europeans in the UK Biobank (UKB). A GWAS of ML-based VCDR identified 299 independent genome-wide significant (GWS; p ≤ 5 × 10 -8 ) hits in 156 loci. The ML-based GWAS replicated 62 of 65 GWS loci from a recent VCDR GWAS in the UKB for which two ophthalmologists manually labeled images for 67,040 Europeans. The ML-based GWAS also identified 93 novel loci, significantly expanding our understanding of the genetic etiologies of glaucoma and VCDR. Pathway analyses support the biological significance of the novel hits to VCDR: select loci near genes involved in neuronal and synaptic biology or harboring variants are known to cause severe Mendelian ophthalmic disease. Finally, the ML-based GWAS results significantly improve polygenic prediction of VCDR and primary open-angle glaucoma in the independent EPIC-Norfolk cohort., (Copyright © 2021 The Author(s). Published by Elsevier Inc. All rights reserved.)

Background: Locally recurrent rectal cancer (LRRC) is a complex problem requiring multidisciplinary consultation and specialized surgical care. Given the paucity of published longer-term survival data, skepticism persists regarding the benefit of major extirpative surgery. We investigated ultra-long-term (~15 years) outcomes following radical resection of LRRC and sought relevant clinicopathologic prognostic variables., Methods: A cohort of 52 consecutive patients who underwent resection of LRRC at our institution between 1997 and 2005 were followed with serial exams and imaging up to the point of death, or 30/06/2019., Results: Median follow-up time was 16.5 years (9.9-18.3) for patients who were alive at last follow-up; only one patient was lost to follow-up, at 9.9 years. For the entire cohort of 52 patients, disease-specific survival (DSS) at 5, 10, and 15 years following salvage surgery was 41%, 33%, and 31%, respectively. All patients who had distant metastatic disease at the time of LRRC resection (n = 6) subsequently died of cancer, at a median of 21 months (4-46). In those without distant metastases at time of salvage surgery (n = 46), DSS at 5, 10, and 15 years was 47%, 38%, and 35%, respectively, median 60 months. Negative resection margin (R0) was independently predictive of superior outcomes. In patients with M0 disease who had R0 resection (n = 37), DSS at 5, 10 and 15 years was 58%, 47%, and 44%, respectively, median 73 months. No patient developed re-recurrence after 5.5 years., Conclusions: This study demonstrates exceptionally durable long-term cancer-free survival following salvage surgery for LRRC, indicating that cure is possible., Competing Interests: Declaration of competing interest The authors have no conflicts of interest or funding source to declare., (Copyright © 2020 Elsevier Ltd, BASO ~ The Association for Cancer Surgery, and the European Society of Surgical Oncology. All rights reserved.)

Ruptured abdominal aortic aneurysms (AAAs) are associated with a 90% overall mortality and $150 000 cost of care per patient. Despite improvements in intensive care and surgical technology, morbidity and mortality remain unchanged over the past 20 years. The most significant predictor of survival is time from the door of the hospital to the operating room. To streamline operational efficiency, a team utilized Lean Six Sigma methodologies, team training, and intentional clinical process design to institute changes in our clinical processes, enhance care coordination, and improve communication. Changes led to a $1.8 million profit on operations, 10-day reduction in length of stay, and 89% survival rate among patients with ruptured AAA.

Background: While transradial approach to conduct percutaneous coronary interventions offers multiple advantages, the procedure can cause radial artery damage and occlusion. Because radial artery is the preferred site for the creation of an arteriovenous fistula to provide dialysis, patients with chronic kidney disease are particularly dependent on radial artery for their long-term survival., Methods: In this retrospective study, we investigated the prevalence of chronic kidney disease in patients undergoing coronary interventions via radial artery. Stage of chronic kidney disease was based on estimated glomerular filtration rate and National Kidney Foundation - Kidney Disease Outcomes Quality Initiative guidelines., Results: A total of 497 patients undergoing transradial percutaneous coronary interventions were included. Over 70.4% (350/497) of the patients had chronic kidney disease. Stage II chronic kidney disease was observed in 243 (69%) patients (estimated glomerular filtration rate = 76.0 ± 8.4 mL/min). Stage III was observed in 93 (27%) patients (estimated glomerular filtration rate = 49 ± 7.5 mL/min). Stage IV chronic kidney disease was observed in 5 (1%) patients (estimated glomerular filtration rate = 25.6 ± 4.3 mL/min) and Stage V chronic kidney disease was observed in 9 (3%) patients (estimated glomerular filtration rate = 9.3 ± 3.5 mL/min). Overall, 107 of 350 patients (30%) had advanced chronic kidney disease, that is, stage III-V chronic kidney disease. Importantly, 14 of the 107 (13%) patients had either stage IV or V chronic kidney disease., Conclusion: This study finds that nearly one-third of the patients undergoing transradial percutaneous coronary interventions have advanced chronic kidney disease. Because many of these patients may require dialysis, the use of radial artery to conduct percutaneous coronary interventions must be carefully considered in chronic kidney disease population.

Atypical hemolytic uremic syndrome (aHUS) is characterized by microangiopathic hemolytic anemia, consumptive thrombocytopenia, and widespread damage to multiple organs including the kidney. The syndrome has a high mortality necessitating the need for an early diagnosis to limit target organ damage. Because thrombotic microangiopathies present with similar clinical picture, accurate diagnosis of aHUS continues to pose a diagnostic challenge. This article focuses on the role of four distinct aspects of aHUS that assist clinicians in making an accurate diagnosis of aHUS. First, because of the lack of a single specific laboratory test for aHUS, other forms of thrombotic microangiopathies such as thrombotic thrombocytopenic purpura and Shiga toxin-associated HUS must be excluded to successfully establish the diagnosis of aHUS. Second, application of the knowledge of complement-amplifying conditions is critically important in making an accurate diagnosis. Third, when available, a renal biopsy can reveal changes consistent with thrombotic microangiopathy. Fourth, genetic mutations are increasingly clarifying the underlying complement dysfunction and gaining importance in the diagnosis and management of patients with aHUS. This review concentrates on the four aspects of aHUS and calls for heightened awareness in making an accurate diagnosis of aHUS., Competing Interests: None declared

Contrast-induced acute kidney injury is a common iatrogenic complication associated with increased health resource utilization and adverse outcomes, including short- and long-term mortality and accelerated progression of preexisting renal insufficiency. The incidence of contrast-induced nephropathy (CIN) has been reported to range from 0% to 24%. This wide range reported by the studies is due to differences in definition, background risk factors, type and dose of contrast medium used, and the frequency of other coexisting potential causes of acute renal failure. CIN is usually transient, with serum creatinine levels peaking at 2-3 days after administration of contrast medium and returning to baseline within 7-10 days after administration. Multiple studies have been conducted using variety of therapeutic interventions in an attempt to prevent CIN. Of these, careful selection of patients, using newer radiocontrast agents, maintenance of hydration status, and avoiding nephrotoxic agents pre- and post-procedure are the most effective interventions to protect against CIN. This review focuses on the basic concepts of CIN and summarizes our recent understanding of its pathophysiology. In addition, this article provides practical recommendations with respect to CIN prevention and management., Competing Interests: None declared.

Rationale: Despite the increasing recognition of asthma-chronic obstructive pulmonary disease overlap syndrome (ACOS) as a clinical entity, it remains poorly characterized due to a lack of agreement on its definition and diagnostic criteria., Objectives: The aim of this study was to use spirometry and computed tomography (CT) to help better define ACOS as well as to classify subjects with ACOS based on Global Initiative for Chronic Obstructive Lung Disease (GOLD) letter grade., Methods: We analyzed 10,192 subjects enrolled in the COPDGene Study. Subjects were non-Hispanic white or African American current or former smokers aged 45-80 years with at least a 10-pack-year smoking history. Subjects were categorized as having either ACOS with a bronchodilator response or chronic obstructive pulmonary disease with emphysema on the basis of spirometry, high-resolution CT, and a history of asthma or hay fever., Measurements and Main Results: Subjects with ACOS were younger (60.6 vs. 65.9 years old; P < 0.0001), more likely to be African American (26.8% vs. 14.4%; P < 0.0001), had a higher body mass index (29.6 vs. 25.1 kg/m(2); P < 0.0001), and were more likely to be current smokers (50.9% vs. 20.7%; P < 0.0001). The majority of subjects with ACOS were categorized as GOLD grade B. Despite less severe spirometry and CT findings in subjects with ACOS, there was no significant difference in severe or frequent exacerbations., Conclusions: Bronchodilator responsiveness and degree of emphysema can help define ACOS. When defined on the basis of bronchodilator responsiveness and degree of emphysema, patients with ACOS represent a unique and high-risk group with distinct clinical features.