While the pace of development of AI has rapidly progressed in recent years, the implementation of safe and effective regulatory frameworks has lagged behind. In particular, the adaptive nature of AI models presents unique challenges to regulators as updating a model can improve its performance but also introduce safety risks. In the US, the Food and Drug Administration (FDA) has been a forerunner in regulating and approving hundreds of AI medical devices. To better understand how AI is updated and its regulatory considerations, we systematically analyze the frequency and nature of updates in FDA-approved AI medical devices. We find that less than 2% of all devices report having been updated by being re-trained on new data. Meanwhile, nearly a quarter of devices report updates in the form of new functionality and marketing claims. As an illustrative case study, we analyze pneumothorax detection models and find that while model performance can degrade by as much as 0.18 AUC when evaluated on new sites, re-training on site-specific data can mitigate this performance drop, recovering up to 0.23 AUC. However, we also observed significant degradation on the original site after re-training using data from new sites, providing insight from one example that challenges the current one-model-fits-all approach to regulatory approvals. Our analysis provides an in-depth look at the current state of FDA-approved AI device updates and insights for future regulatory policies toward model updating and adaptive AI.
Point-of-Care Ultrasound (POCUS) refers to clinician-performed and interpreted ultrasonography at the patient's bedside. Interpreting these images requires a high level of expertise, which may not be available during emergencies. In this paper, we support POCUS by developing classifiers that can aid medical professionals by diagnosing whether or not a patient has pneumothorax. We decomposed the task into multiple steps, using YOLOv4 to extract relevant regions of the video and a 3D sparse coding model to represent video features. Given the difficulty in acquiring positive training videos, we trained a small-data classifier with a maximum of 15 positive and 32 negative examples. To counteract this limitation, we leveraged subject matter expert (SME) knowledge to limit the hypothesis space, thus reducing the cost of data collection. We present results using two lung ultrasound datasets and demonstrate that our model is capable of achieving performance on par with SMEs in pneumothorax identification. We then developed an iOS application that runs our full system in less than 4 seconds on an iPad Pro, and less than 8 seconds on an iPhone 13 Pro, labeling key regions in the lung sonogram to provide interpretable diagnoses.
Chest X-ray (CXR) datasets hosted on Kaggle, though useful from a data science competition standpoint, have limited utility in clinical use because of their narrow focus on diagnosing one specific disease. In real-world clinical use, multiple diseases need to be considered since they can co-exist in the same patient. In this work, we demonstrate how federated learning (FL) can be used to make these toy CXR datasets from Kaggle clinically useful. Specifically, we train a single FL classification model (`global`) using two separate CXR datasets -- one annotated for presence of pneumonia and the other for presence of pneumothorax (two common and life-threatening conditions) -- capable of diagnosing both. We compare the performance of the global FL model with models trained separately on both datasets (`baseline`) for two different model architectures. On a standard, naive 3-layer CNN architecture, the global FL model achieved AUROC of 0.84 and 0.81 for pneumonia and pneumothorax, respectively, compared to 0.85 and 0.82, respectively, for both baseline models (p>0.05). Similarly, on a pretrained DenseNet121 architecture, the global FL model achieved AUROC of 0.88 and 0.91 for pneumonia and pneumothorax, respectively, compared to 0.89 and 0.91, respectively, for both baseline models (p>0.05). Our results suggest that FL can be used to create global `meta` models to make toy datasets from Kaggle clinically useful, a step forward towards bridging the gap from bench to bedside.
Among various medical imaging tools, chest radiographs are the most important and widely used diagnostic tool for detection of thoracic pathologies. Research is being carried out in order to propose robust automatic diagnostic tool for detection of pathologies from chest radiographs. Artificial Intelligence techniques especially deep learning methodologies have found to be giving promising results in automating the field of medicine. Lot of research has been done for automatic and fast detection of pneumothorax from chest radiographs while proposing several frameworks based on artificial intelligence and machine learning techniques. This study summarizes the existing literature for the automatic detection of pneumothorax from chest x-rays along with describing the available chest radiographs datasets. The comparative analysis of the literature is also provided in terms of goodness. Limitations of the existing literature along with the research gaps is also given for further investigation. The paper provides a brief overview of the present work for pneumothorax detection for helping the researchers in selection of optimal approach for future research.
Pneumothorax is a critical condition that requires timely communication and immediate action. In order to prevent significant morbidity or patient death, early detection is crucial. For the task of pneumothorax detection, we study the characteristics of three different deep learning techniques: (i) convolutional neural networks, (ii) multiple-instance learning, and (iii) fully convolutional networks. We perform a five-fold cross-validation on a dataset consisting of 1003 chest X-ray images. ROC analysis yields AUCs of 0.96, 0.93, and 0.92 for the three methods, respectively. We review the classification and localization performance of these approaches as well as an ensemble of the three aforementioned techniques.
Pneumothorax is a relatively common disease, but in some cases, it may be difficult to find with chest radiography. In this paper, we propose a novel method of detecting pneumothorax in chest radiography. We propose an ensemble model of identical convolutional neural networks (CNN) with three different sizes of radiography images. Conventional methods may not properly characterize lost features while resizing large size images into 256 x 256 or 224 x 224 sizes. Our model is evaluated with ChestX-ray dataset which contains over 100,000 chest radiography images. As a result of the experiment, the proposed model showed AUC 0.911, which is the state of the art result in pneumothorax detection. Our method is expected to be effective when applying CNN to large size medical images.