RESUMO
Given the pronounced impact COVID-19 continues to have on society-infecting 700 million reported individuals and causing 6.96 million deaths-many deep learning works have recently focused on the virus's diagnosis. However, assessing severity has remained an open and challenging problem due to a lack of large datasets, the large dimensionality of images for which to find weights, and the compute limitations of modern graphics processing units (GPUs). In this paper, a new, iterative application of transfer learning is demonstrated on the understudied field of 3D CT scans for COVID-19 severity analysis. This methodology allows for enhanced performance on the MosMed Dataset, which is a small and challenging dataset containing 1130 images of patients for five levels of COVID-19 severity (Zero, Mild, Moderate, Severe, and Critical). Specifically, given the large dimensionality of the input images, we create several custom shallow convolutional neural network (CNN) architectures and iteratively refine and optimize them, paying attention to learning rates, layer types, normalization types, filter sizes, dropout values, and more. After a preliminary architecture design, the models are systematically trained on a simplified version of the dataset-building models for two-class, then three-class, then four-class, and finally five-class classification. The simplified problem structure allows the model to start learning preliminary features, which can then be further modified for more difficult classification tasks. Our final model CoSev boosts classification accuracies from below 60% at first to 81.57% with the optimizations, reaching similar performance to the state-of-the-art on the dataset, with much simpler setup procedures. In addition to COVID-19 severity diagnosis, the explored methodology can be applied to general image-based disease detection. Overall, this work highlights innovative methodologies that advance current computer vision practices for high-dimension, low-sample data as well as the practicality of data-driven machine learning and the importance of feature design for training, which can then be implemented for improvements in clinical practices.
RESUMO
With the novel COVID-19 pandemic disrupting and threatening the lives of millions, researchers and clinicians have been recently conducting clinical trials at an unprecedented rate to learn more about the virus and potential drugs/treatments/vaccines to treat its infection. As a result of the influx of clinical trials, researchers, clinicians, and the lay public, now more than ever, face a significant challenge in keeping up-to-date with the rapid rate of discoveries and advances. To remedy this problem, this research mined the ClinicalTrials.gov corpus to extract COVID-19 related clinical trials, produce unique reports to summarize findings and make the meta-data available via Application Programming Interfaces (APIs). Unique reports were created for each drug/intervention, Medical Subject Heading (MeSH) term, and Human Phenotype Ontology (HPO) term. These reports, which have been run over multiple time points, along with APIs to access meta-data, are freely available at http://covidresearchtrials.com. The pipeline, reports, association of COVID-19 clinical trials with MeSH and HPO terms, insights, public repository, APIs, and correlations produced are all novel in this work. The freely available, novel resources present up-to-date relevant biological information and insights in a robust, accessible manner, illustrating their invaluable potential to aid researchers overcome COVID-19 and save hundreds of thousands of lives.
Assuntos
Ontologias Biológicas , Ensaios Clínicos como Assunto , Infecções por Coronavirus/terapia , Processamento de Linguagem Natural , Pneumonia Viral/terapia , Betacoronavirus , COVID-19 , Biologia Computacional , Humanos , Internet , Medical Subject Headings , Pandemias , Fenótipo , SARS-CoV-2 , SoftwareRESUMO
Researchers and clinicians face a significant challenge in keeping up-to-date with the rapid rate of new associations between genetic mutations and diseases. To remedy this problem, this research mined the ClinicalTrials.gov corpus to extract relevant biological insights, produce unique reports to summarize findings, and make the meta-data available via APIs. An automated text-analysis pipeline performed the following features: parsing the ClinicalTrials.gov files, extracting and analyzing mutations from the corpus, mapping clinical trials to Human Phenotype Ontology (HPO), and finding associations between clinical trials and HPO nodes. Unique reports were created for each mutation (SNPs and protein mutations) mentioned in the corpus, as well as for each clinical trial that references a mutation. These reports, which have been run over multiple time points, along with APIs to access meta-data, are freely available at http://snpminertrials.com. Additionally, HPO was used to normalize disease terms and associate clinical trials with relevant genes. The creation of the pipeline and reports, the association of clinical trials with HPO terms, and the insights, public repository, and APIs produced are all novel in this work. The freely-available resources present relevant biological information and novel insights between biomedical entities in a robust and accessible manner, mitigating the challenge of being informed about new associations between mutations, genes, and diseases.