Comparison of characteristics and laboratory tests of COVID-19 hematological patients from France and Brazil during the pre-vaccination period: identification of prognostic profiles for survival

ABSTRACT Introduction: COVID-19 disease presentation is heterogeneous, from asymptomatic up to severe life-threatening forms. Getting further insights into patients with specific diseases is of particular interest. We aimed to identify profiles of hematology patients hospitalized with COVID-19 that would be associated with survival and to assess the differences between cohorts Methods: A binational cohort of 263 patients with COVID-19 and hematological disease was studied in Paris, France and São Paulo, Brazil. Patient profiles were based on age, comorbidities, biological measurements, COVID-19 symptoms and hematological disease characteristics. A semi-supervised learning method with a survival endpoint was first used, following which, a classifier was identified to allow the classification of patients using only baseline information Main results: Two profiles of patients were identified, one being young patients with few comorbidities and low C-reactive protein (CRP), D-dimers, lactate dehydrogenase (LDH) and creatinine levels, and the other, older patients, with several comorbidities and high levels of the 4 biology markers. The profiles were strongly associated with survival (p < 0.0001), even after adjusting for age (p = 0.0002). The 30-day survival rate was 77.1% in the first profiles, versus 46.7% in the second. The Brazilian analysis emphasized the importance of age, while the French focused on the comorbidities Conclusion: This analysis showed the importance of CRP, LHD and creatinine in the COVID-19 presentation and prognosis, whatever the geographic origin of the patients.

A semi-supervised material quantitative intelligent imaging algorithm for spectral CT based on prior information perception learning / 南方医科大学学报

OBJECTIVE@#To propose a semi-supervised material quantitative intelligent imaging algorithm based on prior information perception learning (SLMD-Net) to improve the quality and precision of spectral CT imaging.@*METHODS@#The algorithm includes a supervised and a self- supervised submodule. In the supervised submodule, the mapping relationship between low and high signal-to-noise ratio (SNR) data was constructed through mean square error loss function learning based on a small labeled dataset. In the self- supervised sub-module, an image recovery model was utilized to construct the loss function incorporating the prior information from a large unlabeled low SNR basic material image dataset, and the total variation (TV) model was used to to characterize the prior information of the images. The two submodules were combined to form the SLMD-Net method, and pre-clinical simulation data were used to validate the feasibility and effectiveness of the algorithm.@*RESULTS@#Compared with the traditional model-driven quantitative imaging methods (FBP-DI, PWLS-PCG, and E3DTV), data-driven supervised-learning-based quantitative imaging methods (SUMD-Net and BFCNN), a material quantitative imaging method based on unsupervised learning (UNTV-Net) and semi-supervised learning-based cycle consistent generative adversarial network (Semi-CycleGAN), the proposed SLMD-Net method had better performance in both visual and quantitative assessments. For quantitative imaging of water and bone materials, the SLMD-Net method had the highest PSNR index (31.82 and 29.06), the highest FSIM index (0.95 and 0.90), and the lowest RMSE index (0.03 and 0.02), respectively) and achieved significantly higher image quality scores than the other 7 material decomposition methods (P < 0.05). The material quantitative imaging performance of SLMD-Net was close to that of the supervised network SUMD-Net trained with labeled data with a doubled size.@*CONCLUSIONS@#A small labeled dataset and a large unlabeled low SNR material image dataset can be fully used to suppress noise amplification and artifacts in basic material decomposition in spectral CT and reduce the dependence on labeled data-driven network, which considers more realistic scenario in clinics.

Semi-supervised prediction of gene regulatory networks using machine learning algorithms.

Use of computational methods to predict gene regulatory networks (GRNs) from gene expression data is a challenging task. Many studies have been conducted using unsupervised methods to fulfill the task; however, such methods usually yield low prediction accuracies due to the lack of training data. In this article, we propose semi-supervised methods for GRN prediction by utilizing two machine learning algorithms, namely, support vector machines (SVM) and random forests (RF). The semi-supervised methods make use of unlabelled data for training. We investigated inductive and transductive learning approaches, both of which adopt an iterative procedure to obtain reliable negative training data from the unlabelled data. We then applied our semi-supervised methods to gene expression data of Escherichia coli and Saccharomyces cerevisiae, and evaluated the performance of our methods using the expression data. Our analysis indicated that the transductive learning approach outperformed the inductive learning approach for both organisms. However, there was no conclusive difference identified in the performance of SVM and RF. Experimental results also showed that the proposed semi-supervised methods performed better than existing supervised methods for both organisms.