Dataset Information

Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence

ABSTRACT: Artificial intelligence (AI) provides a promising substitution for streamlining COVID-19 diagnoses. However, concerns surrounding security and trustworthiness impede the collection of large-scale representative medical data, posing a considerable challenge for training a well-generalised model in clinical practices. To address this, we launch the Unified CT-COVID AI Diagnostic Initiative (UCADI), where the AI model can be distributedly trained and independently executed at each host institution under a federated learning framework (FL) without data sharing. Here we show that our FL model outperformed all the local models by a large yield (test sensitivity/specificity in China: 0.973/0.951, in the UK: 0.730/0.942), achieving comparable performance with a panel of professional radiologists. We further evaluated the model on the hold-out (collected from another two hospitals leaving out the FL) and heterogeneous (acquired with contrast materials) data, provided visual explanations for decisions made by the model, and analysed the trade-offs between the model performance and the communication costs in the federated training process. Our study is based on 9,573 chest computed tomography scans (CTs) from 3,336 patients collected from 23 hospitals located in China and the UK. Collectively, our work advanced the prospects of utilising federated learning for privacy-preserving AI in digital health. One sentence summary: An efficient and effective privacy-preserving AI framework is proposed for CT-based COVID-19 diagnosis, based on 9,573 CT scans of 3,336 patients, from 23 hospitals in China and the UK.

SUBMITTER: Bai X

PROVIDER: S-EPMC8609899 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:PurposeDeveloping robust artificial intelligence (AI) models for medical image analysis requires large quantities of diverse, well-chosen data that can prove challenging to collect because of privacy concerns, disease rarity, or diagnostic label quality. Collecting image-based datasets for retinopathy of prematurity (ROP), a potentially blinding disease, suffers from these challenges. Progressively growing generative adversarial networks (PGANs) may help, because they can synthesize highly realistic images that may increase both the size and diversity of medical datasets.DesignDiagnostic validation study of convolutional neural networks (CNNs) for plus disease detection, a component of severe ROP, using synthetic data.ParticipantsFive thousand eight hundred forty-two retinal fundus images (RFIs) collected from 963 preterm infants.MethodsRetinal vessel maps (RVMs) were segmented from RFIs. PGANs were trained to synthesize RVMs with normal, pre-plus, or plus disease vasculature. Convolutional neural networks were trained, using real or synthetic RVMs, to detect plus disease from 2 real RVM test datasets.Main outcome measuresFeatures of real and synthetic RVMs were evaluated using uniform manifold approximation and projection (UMAP). Similarities were evaluated at the dataset and feature level using Fréchet inception distance and Euclidean distance, respectively. CNN performance was assessed via area under the receiver operating characteristic curve (AUC); AUCs were compared via bootstrapping and Delong's test for correlated receiver operating characteristic curves. Confusion matrices were compared using McNemar's chi-square test and Cohen's κ value.ResultsThe CNN trained on synthetic RVMs showed a significantly higher AUC (0.971; P = 0.006 and P = 0.004) and classified plus disease more similarly to a set of 8 international experts (κ = 0.922) than the CNN trained on real RVMs (AUC = 0.934; κ = 0.701). Real and synthetic RVMs overlapped, by plus disease diagnosis, on the UMAP manifold, showing that synthetic images spanned the disease severity spectrum. Fréchet inception distance and Euclidean distances suggested that real and synthetic RVMs were more dissimilar to one another than real RVMs were to one another, further suggesting that synthetic RVMs were distinct from the training data with respect to privacy considerations.ConclusionsSynthetic datasets may be useful for training robust medical AI models. Furthermore, PGANs may be able to synthesize realistic data for use without protected health information concerns.

Project description:BackgroundMain challenges for COVID-19 include the lack of a rapid diagnostic test, a suitable tool to monitor and predict a patient's clinical course and an efficient way for data sharing among multicenters. We thus developed a novel artificial intelligence system based on deep learning (DL) and federated learning (FL) for the diagnosis, monitoring, and prediction of a patient's clinical course.MethodsCT imaging derived from 6 different multicenter cohorts were used for stepwise diagnostic algorithm to diagnose COVID-19, with or without clinical data. Patients with more than 3 consecutive CT images were trained for the monitoring algorithm. FL has been applied for decentralized refinement of independently built DL models.ResultsA total of 1,552,988 CT slices from 4804 patients were used. The model can diagnose COVID-19 based on CT alone with the AUC being 0.98 (95% CI 0.97-0.99), and outperforms the radiologist's assessment. We have also successfully tested the incorporation of the DL diagnostic model with the FL framework. Its auto-segmentation analyses co-related well with those by radiologists and achieved a high Dice's coefficient of 0.77. It can produce a predictive curve of a patient's clinical course if serial CT assessments are available.InterpretationThe system has high consistency in diagnosing COVID-19 based on CT, with or without clinical data. Alternatively, it can be implemented on a FL platform, which would potentially encourage the data sharing in the future. It also can produce an objective predictive curve of a patient's clinical course for visualization.Key points• CoviDet could diagnose COVID-19 based on chest CT with high consistency; this outperformed the radiologist's assessment. Its auto-segmentation analyses co-related well with those by radiologists and could potentially monitor and predict a patient's clinical course if serial CT assessments are available. It can be integrated into the federated learning framework. • CoviDet can be used as an adjunct to aid clinicians with the CT diagnosis of COVID-19 and can potentially be used for disease monitoring; federated learning can potentially open opportunities for global collaboration.

Project description:Background: Recently, Coronavirus Disease 2019 (COVID-19), caused by severe acute respiratory syndrome virus 2 (SARS-CoV-2), has affected more than 200 countries and lead to enormous losses. This study systematically reviews the application of Artificial Intelligence (AI) techniques in COVID-19, especially for diagnosis, estimation of epidemic trends, prognosis, and exploration of effective and safe drugs and vaccines; and discusses the potential limitations. Methods: We report this systematic review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We searched PubMed, Embase and the Cochrane Library from inception to 19 September 2020 for published studies of AI applications in COVID-19. We used PROBAST (prediction model risk of bias assessment tool) to assess the quality of literature related to the diagnosis and prognosis of COVID-19. We registered the protocol (PROSPERO CRD42020211555). Results: We included 78 studies: 46 articles discussed AI-assisted diagnosis for COVID-19 with total accuracy of 70.00 to 99.92%, sensitivity of 73.00 to 100.00%, specificity of 25 to 100.00%, and area under the curve of 0.732 to 1.000. Fourteen articles evaluated prognosis based on clinical characteristics at hospital admission, such as clinical, laboratory and radiological characteristics, reaching accuracy of 74.4 to 95.20%, sensitivity of 72.8 to 98.00%, specificity of 55 to 96.87% and AUC of 0.66 to 0.997 in predicting critical COVID-19. Nine articles used AI models to predict the epidemic of the COVID-19, such as epidemic peak, infection rate, number of infected cases, transmission laws, and development trend. Eight articles used AI to explore potential effective drugs, primarily through drug repurposing and drug development. Finally, 1 article predicted vaccine targets that have the potential to develop COVID-19 vaccines. Conclusions: In this review, we have shown that AI achieved high performance in diagnosis, prognosis evaluation, epidemic prediction and drug discovery for COVID-19. AI has the potential to enhance significantly existing medical and healthcare system efficiency during the COVID-19 pandemic.

Project description:BackgroundA considerable amount of various types of data have been collected during the COVID-19 pandemic, the analysis and understanding of which have been indispensable for curbing the spread of the disease. As the pandemic moves to an endemic state, the data collected during the pandemic will continue to be rich sources for further studying and understanding the impacts of the pandemic on various aspects of our society. On the other hand, naïve release and sharing of the information can be associated with serious privacy concerns.MethodsWe use three common but distinct data types collected during the pandemic (case surveillance tabular data, case location data, and contact tracing networks) to illustrate the publication and sharing of granular information and individual-level pandemic data in a privacy-preserving manner. We leverage and build upon the concept of differential privacy to generate and release privacy-preserving data for each data type. We investigate the inferential utility of privacy-preserving information through simulation studies at different levels of privacy guarantees and demonstrate the approaches in real-life data. All the approaches employed in the study are straightforward to apply.ResultsThe empirical studies in all three data cases suggest that privacy-preserving results based on the differentially privately sanitized data can be similar to the original results at a reasonably small privacy loss ([Formula: see text]). Statistical inferences based on sanitized data using the multiple synthesis technique also appear valid, with nominal coverage of 95% confidence intervals when there is no noticeable bias in point estimation. When [Formula: see text] and the sample size is not large enough, some privacy-preserving results are subject to bias, partially due to the bounding applied to sanitized data as a post-processing step to satisfy practical data constraints.ConclusionsOur study generates statistical evidence on the practical feasibility of sharing pandemic data with privacy guarantees and on how to balance the statistical utility of released information during this process.

Dataset Information

Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets