The volume and complexity of diagnostic imaging is increasing at a pace faster than the availability of human expertise to interpret it. Artificial intelligence has shown great promise in classifying two-dimensional photographs of some common diseases and typically relies on databases of millions of annotated images. Until now, the challenge of reaching the performance of expert clinicians in a real-world clinical pathway with three-dimensional diagnostic scans has remained unsolved. Here, we apply a novel deep learning architecture to a clinically heterogeneous set of three-dimensional optical coherence tomography scans from patients referred to a major eye hospital. We demonstrate performance in making a referral recommendation that reaches or exceeds that of experts on a range of sight-threatening retinal diseases after training on only 14,884 scans. Moreover, we demonstrate that the tissue segmentations produced by our architecture act as a device-independent representation; referral accuracy is maintained when using tissue segmentations from a different type of device. Our work removes previous barriers to wider clinical use without prohibitive training data requirements across multiple pathologies in a real-world setting.
Abstract-Excess weight is established as a major risk factor for cardiovascular diseases, particularly in young individuals.To get a better understanding of the pathophysiology underlying increased cardiovascular disease risk, we evaluated early signs of organ damage and their possible relationship to sympathetic nervous activity. Eighteen lean (body mass index Ͻ25 kg/m 2 ) and 25 overweight or obese (body mass index Ͼ25 kg/m 2 ) healthy university students were included in the study. We comprehensively assessed subclinical target organ damage, including the following: (1) assessment of renal function; (2) left ventricular structure and systolic and diastolic function; and (3) O besity is an established risk factor for cardiovascular disease (CVD) development. 1 Although excess adiposity is frequently linked with metabolic abnormalities such as elevated triglycerides, low levels of high-density lipoprotein (HDL), elevated glucose, elevated blood pressure (BP), insulin resistance, and a proinflammatory state, most likely contributing to excess CVD, 2 large scale epidemiological studies have shown that the CVD risk associated with obesity remains appreciable even after correction for these factors. 1,3 Perhaps surprising is the finding that the obesity-related relative risk of death from stroke and all of the CVDs combined is higher in younger than in older subjects, 4,5 indicating that excess adiposity is likely to have deleterious effects on the cardiovascular system already at an early age, well before clinical manifestations of CVD become apparent. In agreement with this view, recent studies have demonstrated that the presence of obesity since childhood was the only consistent and significant determinant of adverse cardiac remodeling 6 and that being overweight at age 20 years or obese at any time in life was linked with a 3-fold increased risk of developing chronic renal failure. 7 Moreover, functional and structural abnormalities of the endothelium are already evident in obese children aged 9 to 12 years. 8 Given that the sympathetic nervous system (SNS) is an important regulatory mechanism of both metabolic and cardiovascular functions, altered SNS may likely play a role in the etiology and complications of obesity. 9 It is now well established that obesity is associated with elevated SNS Continuing medical education (CME) credit is available for this article. Go to http://cme.ahajournals.org to take the quiz.
Background Deep learning has the potential to transform health care; however, substantial expertise is required to train such models. We sought to evaluate the utility of automated deep learning software to develop medical image diagnostic classifiers by health-care professionals with no coding-and no deep learning-expertise. MethodsWe used five publicly available open-source datasets: retinal fundus images (MESSIDOR); optical coherence tomography (OCT) images (Guangzhou Medical University and Shiley Eye Institute, version 3); images of skin lesions (Human Against Machine [HAM] 10000), and both paediatric and adult chest x-ray (CXR) images (Guangzhou Medical University and Shiley Eye Institute, version 3 and the National Institute of Health [NIH] dataset, respectively)to separately feed into a neural architecture search framework, hosted through Google Cloud AutoML, that automatically developed a deep learning architecture to classify common diseases. Sensitivity (recall), specificity, and positive predictive value (precision) were used to evaluate the diagnostic properties of the models. The discriminative performance was assessed using the area under the precision recall curve (AUPRC). In the case of the deep learning model developed on a subset of the HAM10000 dataset, we did external validation using the Edinburgh Dermofit Library dataset.Findings Diagnostic properties and discriminative performance from internal validations were high in the binary classification tasks (sensitivity 73•3-97•0%; specificity 67-100%; AUPRC 0•87-1•00). In the multiple classification tasks, the diagnostic properties ranged from 38% to 100% for sensitivity and from 67% to 100% for specificity. The discriminative performance in terms of AUPRC ranged from 0•57 to 1•00 in the five automated deep learning models. In an external validation using the Edinburgh Dermofit Library dataset, the automated deep learning model showed an AUPRC of 0•47, with a sensitivity of 49% and a positive predictive value of 52%.Interpretation All models, except the automated deep learning model trained on the multilabel classification task of the NIH CXR14 dataset, showed comparable discriminative performance and diagnostic properties to state-of-the-art performing deep learning algorithms. The performance in the external validation study was low. The quality of the open-access datasets (including insufficient information about patient flow and demographics) and the absence of measurement for precision, such as confidence intervals, constituted the major limitations of this study. The availability of automated deep learning platforms provide an opportunity for the medical community to enhance their understanding in model development and evaluation. Although the derivation of classification models without requiring a deep understanding of the mathematical, statistical, and programming principles is attractive, comparable performance to expertly designed models is limited to more elementary classification tasks. Furthermore, care should be placed in adhering t...
Progression to exudative 'wet' age-related macular degeneration (exAMD) is a major cause of visual deterioration. In patients diagnosed with exAMD in one eye, we introduce an artificial intelligence (AI) system to predict progression to exAMD in the second eye. By combining models based on 3D optical coherence tomography images and corresponding automatic tissue maps, our system predicts conversion to exAMD within a clinically-actionable 6-month time window, achieving a per-volumetric-scan sensitivity of 80% at 55% specificity, and 34% sensitivity at 90% specificity. This level of performance corresponds to true positives in 78% and 41% individual eyes, and false positives in 56% and 17% individual eyes, at the high sensitivity and high specificity points respectively. Moreover, we show that automatic tissue segmentation can identify anatomical changes prior to conversion and high-risk subgroups. This AI system overcomes substantial interobserver variability in expert predictions, performing better than five out of six experts, and demonstrates the potential of using AI to predict disease progression.
OBJECTIVESympathetic nervous system (SNS) overactivity contributes to the pathogenesis and target organ complications of obesity. This study was conducted to examine the effects of lifestyle interventions (weight loss alone or together with exercise) on SNS function.RESEARCH DESIGN AND METHODSUntreated men and women (mean age 55 ± 1 year; BMI 32.3 ± 0.5 kg/m2) who fulfilled Adult Treatment Panel III metabolic syndrome criteria were randomly allocated to either dietary weight loss (WL, n = 20), dietary weight loss and moderate-intensity aerobic exercise (WL+EX, n = 20), or no treatment (control, n = 19). Whole-body norepinephrine kinetics, muscle sympathetic nerve activity by microneurography, baroreflex sensitivity, fitness (maximal oxygen consumption), metabolic, and anthropometric measurements were made at baseline and 12 weeks.RESULTSBody weight decreased by −7.1 ± 0.6 and −8.4 ± 1.0 kg in the WL and WL+EX groups, respectively (both P < 0.001). Fitness increased by 19 ± 4% (P < 0.001) in the WL+EX group only. Resting SNS activity decreased similarly in the WL and WL+EX groups: norepinephrine spillover by −96 ± 30 and −101 ± 34 ng/min (both P < 0.01) and muscle sympathetic nerve activity by −12 ± 6 and −19 ± 4 bursts/100 heart beats, respectively (both P < 0.01), but remained unchanged in control subjects. Blood pressure, baroreflex sensitivity, and metabolic parameters improved significantly and similarly in the two lifestyle intervention groups.CONCLUSIONSThe addition of moderate-intensity aerobic exercise training to a weight loss program does not confer additional benefits on resting SNS activity. This suggests that weight loss is the prime mover in sympathetic neural adaptation to a hypocaloric diet.
Moderate weight loss in obese MetS patients is associated with a reduction in albuminuria and an improvement in eGFR which is augmented by exercise co-intervention.
IR subjects with the metabolic syndrome have a blunted SNS response to oral glucose compared with IS subjects with the metabolic syndrome, which is related to central adiposity and the insulin response but not to differences in skeletal muscle vasodilation or BRS.
PURPOSE. We evaluate how deep learning can be applied to extract novel information such as refractive error from retinal fundus imaging. METHODS.Retinal fundus images used in this study were 45-and 30-degree field of view images from the UK Biobank and Age-Related Eye Disease Study (AREDS) clinical trials, respectively. Refractive error was measured by autorefraction in UK Biobank and subjective refraction in AREDS. We trained a deep learning algorithm to predict refractive error from a total of 226,870 images and validated it on 24,007 UK Biobank and 15,750 AREDS images. Our model used the ''attention'' method to identify features that are correlated with refractive error. RESULTS.The resulting algorithm had a mean absolute error (MAE) of 0.56 diopters (95% confidence interval [CI]: 0.55-0.56) for estimating spherical equivalent on the UK Biobank data set and 0.91 diopters (95% CI: 0.89-0.93) for the AREDS data set. The baseline expected MAE (obtained by simply predicting the mean of this population) was 1.81 diopters (95% CI: 1.79-1.84) for UK Biobank and 1.63 (95% CI: 1.60-1.67) for AREDS. Attention maps suggested that the foveal region was one of the most important areas used by the algorithm to make this prediction, though other regions also contribute to the prediction.CONCLUSIONS. To our knowledge, the ability to estimate refractive error with high accuracy from retinal fundus photos has not been previously known and demonstrates that deep learning can be applied to make novel predictions from medical images.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.