Diabetes is a metabolic disorder that results from defects in autoimmune beta-cell destruction in Type 1, peripheral resistance to insulin action in Type 2 or, most commonly, both. Patients with long-standing diabetes often fall prey to Diabetic Retinopathy (DR) resulting in changes in the retina of the human eye, which may lead to loss of vision in extreme cases. The aim of this study is two-fold: (a) create deep learning models that were trained to grade degraded retinal fundus images and (b) to create a browser-based application that will aid in diagnostic procedures by highlighting the key features of the fundus image. Deep learning has proven to be a success for computer-aided DR diagnosis resulting in early-detection and prevention of blindness. In this research work, we have emulated the images plagued by distortions by degrading the images based on multiple different combinations of Light Transmission Disturbance, Image Blurring and insertion of Retinal Artifacts. These degraded images were used for the training of multiple Deep Learning based Convolutional Neural Networks. We have trained InceptionV3, ResNet-50 and InceptionResNetV2 on multiple datasets. The models were used to classify retinal fundus images based on their severity level and then further used in the creation of a browser-based application, which demonstrates the model's prediction and the probability associated with each class. It will also show the Integration Gradient (IG) Attribution Mask superimposed onto the input image. The creation of the browser-based application would aid in the diagnostic procedures performed by ophthalmologists by highlighting the key features of the fundus image based on an educated prediction made by the model.
Objective. Shock Index (SI) is widely used for prognosticating outcomes in ICU and emergency settings. We aimed to create a multi-modal early warning system (EWS) for development of abnormal shock index using routinely available vitals and clinical notes. Material and Methods. 17,294 ICU-stays in MIMIC-III data were scored for SI. A new episode of abnormal SI was defined as SI > 0.7 for >30 minutes AND preceded by >=24 hours of normal SI. ICU stays with <24 hours admission, or SI >0.7 within the first 24 hours of admission, or missing SI in >50% in the 24 hour early warning window were excluded, leaving a final cohort of 337 normal and 84 abnormal SI instances. 3117 features from vitals time-series combined with BERT-based features from clinical notes were used to train a battery of machine learning models. The best multimodal pipeline (ShockModes) was assessed for interpretability using SHAP features. Results. Vitals-based, notes-based and multi-modal classifiers achieved the best sensitivity of 0.81, 0.81, and 0.83 with corresponding specificity of 0.92, 0.99, and 0.94 respectively, thus demonstrating the potential of ShockModes for early detection, while preventing false alarms. Global SHAP values revealed Fourier-features of heart rate and heparin sodium prophylaxis as top features. Sensitivity of early detection was highest in acute respiratory failure and chronic kidney disease patients. Conclusion. The multimodal, interpretable early warning system ShockModes can be used for prognosticating SI based outcomes in ICU and emergency settings.Objective. Shock Index (SI) is widely used for prognosticating outcomes in ICU and emergency settings. We aimed to create a multi-modal early warning system (EWS) for development of abnormal shock index using routinely available vitals and clinical notes. Material and Methods. 17,294 ICU-stays in MIMIC-III data were scored for SI. A new episode of abnormal SI was defined as SI > 0.7 for >30 minutes AND preceded by >=24 hours of normal SI. ICU stays with <24 hours admission, or SI >0.7 within the first 24 hours of admission, or missing SI in >50% in the 24 hour early warning window were excluded, leaving a final cohort of 337 normal and 84 abnormal SI instances. 3117 features from vitals time-series combined with BERT-based features from clinical notes were used to train a battery of machine learning models. The best multimodal pipeline (ShockModes) was assessed for interpretability using SHAP features. Results. Vitals-based, notes-based and multi-modal classifiers achieved the best sensitivity of 0.81, 0.81, and 0.83 with corresponding specificity of 0.92, 0.99, and 0.94 respectively, thus demonstrating the potential of ShockModes for early detection, while preventing false alarms. Global SHAP values revealed Fourier-features of heart rate and heparin sodium prophylaxis as top features. Sensitivity of early detection was highest in acute respiratory failure and chronic kidney disease patients. Conclusion. The multimodal, interpretable early warning system ShockModes can be used for prognosticating SI based outcomes in ICU and emergency settings.
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.