Adaptive Feature Selection Guided Deep Forest for COVID-19 Classification With Chest CT.

Chest computed tomography (CT) becomes an effective tool to assist the diagnosis of coronavirus disease-19 (COVID-19). Due to the outbreak of COVID-19 worldwide, using the computed-aided diagnosis technique for COVID-19 classification based on CT images could largely alleviate the burden of clinicians. In this paper, we propose an Adaptive Feature Selection guided Deep Forest (AFS-DF) for COVID-19 classification based on chest CT images. Specifically, we first extract location-specific features from CT images. Then, in order to capture the high-level representation of these features with the relatively small-scale data, we leverage a deep forest model to learn high-level representation of the features. Moreover, we propose a feature selection method based on the trained deep forest model to reduce the redundancy of features, where the feature selection could be adaptively incorporated with the COVID-19 classification model. We evaluated our proposed AFS-DF on COVID-19 dataset with 1495 patients of COVID-19 and 1027 patients of community acquired pneumonia (CAP). The accuracy (ACC), sensitivity (SEN), specificity (SPE), AUC, precision and F1-score achieved by our method are 91.79%, 93.05%, 89.95%, 96.35%, 93.10% and 93.07%, respectively. Experimental results on the COVID-19 dataset suggest that the proposed AFS-DF achieves superior performance in COVID-19 vs. CAP classification, compared with 4 widely used machine learning methods.

Convolutional Sparse Support Estimator-Based COVID-19 Recognition From X-Ray Images.

Coronavirus disease (COVID-19) has been the main agenda of the whole world ever since it came into sight. X-ray imaging is a common and easily accessible tool that has great potential for COVID-19 diagnosis and prognosis. Deep learning techniques can generally provide state-of-the-art performance in many classification tasks when trained properly over large data sets. However, data scarcity can be a crucial obstacle when using them for COVID-19 detection. Alternative approaches such as representation-based classification [collaborative or sparse representation (SR)] might provide satisfactory performance with limited size data sets, but they generally fall short in performance or speed compared to the neural network (NN)-based methods. To address this deficiency, convolution support estimation network (CSEN) has recently been proposed as a bridge between representation-based and NN approaches by providing a noniterative real-time mapping from query sample to ideally SR coefficient support, which is critical information for class decision in representation-based techniques. The main premises of this study can be summarized as follows: 1) A benchmark X-ray data set, namely QaTa-Cov19, containing over 6200 X-ray images is created. The data set covering 462 X-ray images from COVID-19 patients along with three other classes; bacterial pneumonia, viral pneumonia, and normal. 2) The proposed CSEN-based classification scheme equipped with feature extraction from state-of-the-art deep NN solution for X-ray images, CheXNet, achieves over 98% sensitivity and over 95% specificity for COVID-19 recognition directly from raw X-ray images when the average performance of 5-fold cross validation over QaTa-Cov19 data set is calculated. 3) Having such an elegant COVID-19 assistive diagnosis performance, this study further provides evidence that COVID-19 induces a unique pattern in X-rays that can be discriminated with high accuracy.

A Call for Consistency in the Official Naming of the Disease Caused by Severe Acute Respiratory Syndrome Coronavirus 2 in Non-English Languages.

We investigated the adoption of World Health Organization (WHO) naming of COVID-19 into the respective languages among the Group of Twenty (G20) countries, and the variation of COVID-19 naming in the Chinese language across different health authorities. On May 7, 2020, we identified the websites of the national health authorities of the G20 countries to identify naming of COVID-19 in their respective languages, and the websites of the health authorities in mainland China, Hong Kong, Macau, Taiwan and Singapore and identify their Chinese name for COVID-19. Among the G20 nations, Argentina, China, Italy, Japan, Mexico, Saudi Arabia and Turkey do not use the literal translation of COVID-19 in their official language(s) to refer to COVID-19, as they retain "novel" in the naming of this disease. China is the only G20 nation that names COVID-19 a pneumonia. Among Chinese-speaking jurisdictions, Hong Kong and Singapore governments follow the WHO's recommendation and adopt the literal translation of COVID-19 in Chinese. In contrast, mainland China, Macau, and Taiwan refer to COVID-19 as a type of pneumonia in Chinese. We urge health authorities worldwide to adopt naming in their native languages that are consistent with WHO's naming of COVID-19.

Glasgow Early Treatment Arm Favirpiravir (GETAFIX) for adults with early stage COVID-19: A structured summary of a study protocol for a randomised controlled trial.

OBJECTIVES: The GETAFIX trial will test the hypothesis that favipiravir is a more effective treatment for COVID-19 infection in patients who have early stage disease, compared to current standard of care. This study will also provide an important opportunity to investigate the safety and tolerability of favipiravir, the pharmacokinetic and pharmacodynamic profile of this drug and mechanisms of resistance in the context of COVID-19 infection, as well as the effect of favipiravir on hospitalisation duration and the post COVID-19 health and psycho-social wellbeing of patients recruited to the study. TRIAL DESIGN: GETAFIX is an open label, parallel group, two arm phase II/III randomised trial with 1:1 treatment allocation ratio. Patients will be randomised to one of two arms and the primary endpoint will assess the superiority of favipiravir plus standard treatment compared to standard treatment alone. PARTICIPANTS: This trial will recruit adult patients with confirmed positive valid COVID-19 test, who are not pregnant or breastfeeding and have no prior major co-morbidities. This is a multi-centre trial, patients will be recruited from in-patients and outpatients from three Glasgow hospitals: Royal Alexandra Hospital; Queen Elizabeth University Hospital; and the Glasgow Royal Infirmary. Patients must meet all of the following criteria: 1. Age 16 or over at time of consent 2. Exhibiting symptoms associated with COVID-19 3. Positive for SARS-CoV-2 on valid COVID-19 test 4. Point 1, 2, 3, or 4 on the WHO COVID-19 ordinal severity scale at time of randomisation. (Asymptomatic with positive valid COVID-19 test, Symptomatic Independent, Symptomatic assistance needed, Hospitalized, with no oxygen therapy) 5. Have >=10% risk of death should they be admitted to hospital as defined by the ISARIC4C risk index: https://isaric4c.net/risk 6. Able to provide written informed consent 7. Negative pregnancy test (women of childbearing potential*) 8. Able to swallow oral medication Patients will be excluded from the trial if they meet any of the following criteria: 1. Renal impairment requiring, or likely to require, dialysis or haemofiltration 2. Pregnant or breastfeeding 3. Of child bearing potential (women), or with female partners of child bearing potential (men) who do not agree to use adequate contraceptive measures for the duration of the study and for 3 months after the completion of study treatment 4. History of hereditary xanthinuria 5. Other patients judged unsuitable by the Principal Investigator or sub-Investigator 6. Known hypersensitivity to favipiravir, its metabolites or any excipients 7. Severe co-morbidities including: patients with severe hepatic impairment, defined as: • greater than Child-Pugh grade A • AST or ALT > 5 x ULN • AST or ALT >3 x ULN and Total Bilirubin > 2xULN 8. More than 96 hours since first positive COVID-19 test sample was taken 9. Unable to discontinue contra-indicated concomitant medications This is a multi-centre trial, patients will be recruited from in-patients and outpatients from three Glasgow hospitals: Royal Alexandra Hospital; Queen Elizabeth University Hospital; and the Glasgow Royal Infirmary. INTERVENTION AND COMPARATOR: Patients randomised to the experimental arm of GETAFIX will receive standard treatment for COVID-19 at the discretion of the treating clinician plus favipiravir. These patients will receive a loading dose of favipiravir on day 1 of 3600mg (1800mg 12 hours apart). On days 2-10, patients in the experimental arm will receive a maintenance dose of favipiravir of 800mg 12 hours apart (total of 18 doses). Patients randomised to the control arm of the GETAFIX trial will receive standard treatment for COVID-19 at the discretion of the treating clinician. MAIN OUTCOMES: The primary outcome being assessed in the GETAFIX trial is the efficacy of favipiravir in addition to standard treatment in patients with COVID-19 in reducing the severity of disease compared to standard treatment alone. Disease severity will be assessed using WHO COVID 10 point ordinal severity scale at day 15 +/- 48 hours. All randomised participants will be followed up until death or 60 days post-randomisation (whichever is sooner). RANDOMISATION: Patients will be randomised 1:1 to the experimental versus control arm using computer generated random sequence allocation. A minimisation algorithm incorporating a random component will be used to allocate patients. The factors used in the minimisation will be: site, age (16-50/51-70/71+), history of hypertension or currently obsess (BMI>30 or obesity clinically evident; yes/no), 7 days duration of symptoms (yes/no/unknown), sex (male/female), WHO COVID-19 ordinal severity score at baseline (1/2or 3/4). BLINDING (MASKING): No blinding will be used in the GETAFIX trial. Both participants and those assessing outcomes will be aware of treatment allocation. NUMBERS TO BE RANDOMISED (SAMPLE SIZE): In total, 302 patients will be randomised to the GETAFIX trial: 151 to the control arm and 151 to the experimental arm. There will be an optional consent form for patients who may want to contribute to more frequent PK and PD sampling. The maximum number of patients who will undergo this testing will be sixteen, eight males and eight females. This option will be offered to all patients who are being treated in hospital at the time of taking informed consent, however only patients in the experimental arm of the trial will be able to undergo this testing. TRIAL STATUS: The current GETAFIX protocol is version 4.0 12th September 2020. GETAFIX opened to recruitment on 26th October 2020 and will recruit patients over a period of approximately six months. TRIAL REGISTRATION: GETAFIX was registered on the European Union Drug Regulating Authorities Clinical Trials (EudraCT) Database on 15th April 2020; Reference number 2020-001904-41 ( https://www.clinicaltrialsregister.eu/ctr-search/trial/2020-001904-41/GB ). GETAFIX was registered on ISRCTN on 7th September 2020; Reference number ISRCTN31062548 ( https://www.isrctn.com/ISRCTN31062548 ). FULL PROTOCOL: The full protocol is attached as an additional file, accessible from the Trials website (Additional file 1). In the interest in expediting dissemination of this material, the familiar formatting has been eliminated; this Letter serves as a summary of the key elements of the full protocol. The study protocol has been reported in accordance with the Standard Protocol Items: Recommendations for Clinical Interventional Trials (SPIRIT) guidelines (see Additional file 2).

Joint prediction and time estimation of COVID-19 developing severe symptoms using chest CT scan.

With the rapidly worldwide spread of Coronavirus disease (COVID-19), it is of great importance to conduct early diagnosis of COVID-19 and predict the conversion time that patients possibly convert to the severe stage, for designing effective treatment plans and reducing the clinicians' workloads. In this study, we propose a joint classification and regression method to determine whether the patient would develop severe symptoms in the later time formulated as a classification task, and if yes, the conversion time will be predicted formulated as a classification task. To do this, the proposed method takes into account 1) the weight for each sample to reduce the outliers' influence and explore the problem of imbalance classification, and 2) the weight for each feature via a sparsity regularization term to remove the redundant features of the high-dimensional data and learn the shared information across two tasks, i.e., the classification and the regression. To our knowledge, this study is the first work to jointly predict the disease progression and the conversion time, which could help clinicians to deal with the potential severe cases in time or even save the patients' lives. Experimental analysis was conducted on a real data set from two hospitals with 408 chest computed tomography (CT) scans. Results show that our method achieves the best classification (e.g., 85.91% of accuracy) and regression (e.g., 0.462 of the correlation coefficient) performance, compared to all comparison methods. Moreover, our proposed method yields 76.97% of accuracy for predicting the severe cases, 0.524 of the correlation coefficient, and 0.55 days difference for the conversion time.

Plasma Proteomics Identify Biomarkers and Pathogenesis of COVID-19.

The coronavirus disease 2019 (COVID-19) pandemic is a global public health crisis. However, little is known about the pathogenesis and biomarkers of COVID-19. Here, we profiled host responses to COVID-19 by performing plasma proteomics of a cohort of COVID-19 patients, including non-survivors and survivors recovered from mild or severe symptoms, and uncovered numerous COVID-19-associated alterations of plasma proteins. We developed a machine-learning-based pipeline to identify 11 proteins as biomarkers and a set of biomarker combinations, which were validated by an independent cohort and accurately distinguished and predicted COVID-19 outcomes. Some of the biomarkers were further validated by enzyme-linked immunosorbent assay (ELISA) using a larger cohort. These markedly altered proteins, including the biomarkers, mediate pathophysiological pathways, such as immune or inflammatory responses, platelet degranulation and coagulation, and metabolism, that likely contribute to the pathogenesis. Our findings provide valuable knowledge about COVID-19 biomarkers and shed light on the pathogenesis and potential therapeutic targets of COVID-19.

Dual-branch combination network (DCN): Towards accurate diagnosis and lesion segmentation of COVID-19 using CT images.

The recent global outbreak and spread of coronavirus disease (COVID-19) makes it an imperative to develop accurate and efficient diagnostic tools for the disease as medical resources are getting increasingly constrained. Artificial intelligence (AI)-aided tools have exhibited desirable potential; for example, chest computed tomography (CT) has been demonstrated to play a major role in the diagnosis and evaluation of COVID-19. However, developing a CT-based AI diagnostic system for the disease detection has faced considerable challenges, which is mainly due to the lack of adequate manually-delineated samples for training, as well as the requirement of sufficient sensitivity to subtle lesions in the early infection stages. In this study, we developed a dual-branch combination network (DCN) for COVID-19 diagnosis that can simultaneously achieve individual-level classification and lesion segmentation. To focus the classification branch more intensively on the lesion areas, a novel lesion attention module was developed to integrate the intermediate segmentation results. Furthermore, to manage the potential influence of different imaging parameters from individual facilities, a slice probability mapping method was proposed to learn the transformation from slice-level to individual-level classification. We conducted experiments on a large dataset of 1202 subjects from ten institutes in China. The results demonstrated that 1) the proposed DCN attained a classification accuracy of 96.74% on the internal dataset and 92.87% on the external validation dataset, thereby outperforming other models; 2) DCN obtained comparable performance with fewer samples and exhibited higher sensitivity, especially in subtle lesion detection; and 3) DCN provided good interpretability on the loci of infection compared to other deep models due to its classification guided by high-level semantic information. An online CT-based diagnostic platform for COVID-19 derived from our proposed framework is now available.

[CT imaging features of patients with different clinical types of COVID-19].

OBJECTIVE: To investigate the CT findings of patients with different clinical types of coronavirus disease 2019 (COVID-19). METHODS: A total of 67 patients diagnosed as COVID-19 by nucleic acid testing were collected and divided into 4 groups according to the clinical stages based on Diagnosis and treatment of novel coronavirus pneumonia (trial version 6). The CT imaging characteristics were analyzed among patients with different clinical types. RESULTS: Among 67 patients, 3(4.5%) were mild, 35 (52.2%) were moderate, 22 (32.8%) were severe, and 7(10.4%) were critical ill. No significant abnormality in chest CT imaging in mild patients. The 35 cases of moderate type included 3 (8.6%) single lesions, the 22 cases of severe cases included 1 (4.5%) single lesion and the rest cases were with multiple lesions. CT images of moderate patients were mainly manifested by solid plaque shadow and halo sign (18/35, 51.4%); while fibrous strip shadow with ground glass shadow was more frequent in severe cases (7/22, 31.8%). Consolidation shadow as the main lesion was observed in 7 cases, and all of them were severe or critical ill patients. CONCLUSIONS: CT images of patients with different clinical types of COVID-19 have characteristic manifestations, and solid shadow may predict severe and critical illness.

Using machine learning of clinical data to diagnose COVID-19: a systematic review and meta-analysis.

BACKGROUND: The recent Coronavirus Disease 2019 (COVID-19) pandemic has placed severe stress on healthcare systems worldwide, which is amplified by the critical shortage of COVID-19 tests. METHODS: In this study, we propose to generate a more accurate diagnosis model of COVID-19 based on patient symptoms and routine test results by applying machine learning to reanalyzing COVID-19 data from 151 published studies. We aim to investigate correlations between clinical variables, cluster COVID-19 patients into subtypes, and generate a computational classification model for discriminating between COVID-19 patients and influenza patients based on clinical variables alone. RESULTS: We discovered several novel associations between clinical variables, including correlations between being male and having higher levels of serum lymphocytes and neutrophils. We found that COVID-19 patients could be clustered into subtypes based on serum levels of immune cells, gender, and reported symptoms. Finally, we trained an XGBoost model to achieve a sensitivity of 92.5% and a specificity of 97.9% in discriminating COVID-19 patients from influenza patients. CONCLUSIONS: We demonstrated that computational methods trained on large clinical datasets could yield ever more accurate COVID-19 diagnostic models to mitigate the impact of lack of testing. We also presented previously unknown COVID-19 clinical variable correlations and clinical subgroups.

Hypercytokinemia in COVID-19: Tear cytokine profile in hospitalized COVID-19 patients.

The aim of this study is to analyze the concentrations of cytokines in tear of hospitalized COVID-19 patients compared to healthy controls. Tear samples were obtained from 41 healthy controls and 62 COVID-19 patients. Twenty-seven cytokines were assessed: interleukin (IL)-1b, IL-1RA, IL-2, IL-4, IL-5, IL-6, IL-7, IL-8, IL9, IL-10, IL-12, IL-13, IL-15, IL-17, eotaxin, fibroblast growth factor basic, granulocyte colony-stimulating factor (G-CSF), granulocyte-monocyte colony-stimulating factor (GM-CSF), interferon (IFN)-γ, interferon gamma-induced protein, monocyte chemo-attractant protein-1, macrophage inflammatory protein (MIP)-1a, MIP-1b, platelet-derived growth factor (PDGF), regulated on activation normal T cell expressed and secreted, tumor necrosis factor-α and vascular endothelial growth factor (VEGF).In tear samples of COVID-19 patients, an increase in IL-9, IL-15, G-CSF, GM-CSF, IFN-γ, PDGF and VEGF was observed, along with a decrease in eotaxin compared to the control group (p < 0.05). A poor correlation between IL-6 levels in tear and blood was found. IL-1RA and GM-CSF were significantly lower in severe patients and those who needed treatment targeting the immune system (p < 0.05). Tear cytokine levels corroborate the inflammatory nature of SARS-CoV-2.

Contrastive Cross-Site Learning With Redesigned Net for COVID-19 CT Classification.

The pandemic of coronavirus disease 2019 (COVID-19) has lead to a global public health crisis spreading hundreds of countries. With the continuous growth of new infections, developing automated tools for COVID-19 identification with CT image is highly desired to assist the clinical diagnosis and reduce the tedious workload of image interpretation. To enlarge the datasets for developing machine learning methods, it is essentially helpful to aggregate the cases from different medical systems for learning robust and generalizable models. This paper proposes a novel joint learning framework to perform accurate COVID-19 identification by effectively learning with heterogeneous datasets with distribution discrepancy. We build a powerful backbone by redesigning the recently proposed COVID-Net in aspects of network architecture and learning strategy to improve the prediction accuracy and learning efficiency. On top of our improved backbone, we further explicitly tackle the cross-site domain shift by conducting separate feature normalization in latent space. Moreover, we propose to use a contrastive training objective to enhance the domain invariance of semantic embeddings for boosting the classification performance on each dataset. We develop and evaluate our method with two public large-scale COVID-19 diagnosis datasets made up of CT images. Extensive experiments show that our approach consistently improves the performanceson both datasets, outperforming the original COVID-Net trained on each dataset by 12.16% and 14.23% in AUC respectively, also exceeding existing state-of-the-art multi-site learning methods.

Efficient and Effective Training of COVID-19 Classification Networks With Self-Supervised Dual-Track Learning to Rank.

Coronavirus Disease 2019 (COVID-19) has rapidly spread worldwide since first reported. Timely diagnosis of COVID-19 is crucial both for disease control and patient care. Non-contrast thoracic computed tomography (CT) has been identified as an effective tool for the diagnosis, yet the disease outbreak has placed tremendous pressure on radiologists for reading the exams and may potentially lead to fatigue-related mis-diagnosis. Reliable automatic classification algorithms can be really helpful; however, they usually require a considerable number of COVID-19 cases for training, which is difficult to acquire in a timely manner. Meanwhile, how to effectively utilize the existing archive of non-COVID-19 data (the negative samples) in the presence of severe class imbalance is another challenge. In addition, the sudden disease outbreak necessitates fast algorithm development. In this work, we propose a novel approach for effective and efficient training of COVID-19 classification networks using a small number of COVID-19 CT exams and an archive of negative samples. Concretely, a novel self-supervised learning method is proposed to extract features from the COVID-19 and negative samples. Then, two kinds of soft-labels ('difficulty' and 'diversity') are generated for the negative samples by computing the earth mover's distances between the features of the negative and COVID-19 samples, from which data 'values' of the negative samples can be assessed. A pre-set number of negative samples are selected accordingly and fed to the neural network for training. Experimental results show that our approach can achieve superior performance using about half of the negative samples, substantially reducing model training time.

COVID-19 pathways for brain and heart injury in comorbidity patients: A role of medical imaging and artificial intelligence-based COVID severity classification: A review.

Artificial intelligence (AI) has penetrated the field of medicine, particularly the field of radiology. Since its emergence, the highly virulent coronavirus disease 2019 (COVID-19) has infected over 10 million people, leading to over 500,000 deaths as of July 1st, 2020. Since the outbreak began, almost 28,000 articles about COVID-19 have been published (https://pubmed.ncbi.nlm.nih.gov); however, few have explored the role of imaging and artificial intelligence in COVID-19 patients-specifically, those with comorbidities. This paper begins by presenting the four pathways that can lead to heart and brain injuries following a COVID-19 infection. Our survey also offers insights into the role that imaging can play in the treatment of comorbid patients, based on probabilities derived from COVID-19 symptom statistics. Such symptoms include myocardial injury, hypoxia, plaque rupture, arrhythmias, venous thromboembolism, coronary thrombosis, encephalitis, ischemia, inflammation, and lung injury. At its core, this study considers the role of image-based AI, which can be used to characterize the tissues of a COVID-19 patient and classify the severity of their infection. Image-based AI is more important than ever as the pandemic surges and countries worldwide grapple with limited medical resources for detection and diagnosis.

Analysis of clinical features and imaging signs of COVID-19 with the assistance of artificial intelligence.

OBJECTIVE: To explore the CT imaging features/signs of patients with different clinical types of Coronavirus Disease 2019 (COVID-19) via the application of artificial intelligence (AI), thus improving the understanding of COVID-19. PANTIENTS AND METHODS: Clinical data and chest CT imaging features of 58 patients confirmed with COVID-19 in the Fifth Medical Center of PLA General Hospital were retrospectively analyzed. According to the Guidelines on Novel Coronavirus-Infected Pneumonia Diagnosis and Treatment (Provisional 6th Edition), COVID-19 patients were divided into mild type (7), common type (34), severe type (7) and critical type (10 patients). The CT imaging features of the patients with different clinical types of COVID-19 types were analyzed, and the volume percentage of pneumonia lesions with respect to the lung lobes (where the lesion was located) and to the whole lung was calculated with the use of AI software. SPSS 21.0 software was used for statistical analysis. RESULTS: Common clinical manifestations of COVID-19 patients: fever was found in 47 patients (81.0%), cough in 31 (53.4%) and weakness in 10 (17.2%). Laboratory examinations: normal or decreased white blood cell (WBC) counts were observed in 52 patients (89.7%), decreased lymphocyte counts (LCs) in 14 (24.1%) and increased C-reactive protein (CRP) levels in 18 (31.0%). CT imaging features: there were 48 patients (94.1%) with lesions distributed in both lungs and 46 patients (90.2%) had lesions most visible in the lower lungs; the primary manifestations in patients with common type COVID-19 were ground-glass opacities (GGOs) (23/34, 67.6%) or mixed type (17/34, 50.0%), with lesions mainly distributed in the periphery of the lungs (28/34, 82.4%); the primary manifestations of patients with severe/critical type COVID-19 were consolidations (13/17, 76.5%) or mixed type (14/17, 82.4%), with lesions distributed in both the peripheral and central areas of lungs (14/17,82.4%); other common signs, including pleural parallel signs, halo signs, vascular thickening signs, crazy-paving signs and air bronchogram signs, were visible in patients with different clinical types, and pleural effusion was found in 5 patients with severe/critical COVID-19. AI software was used to calculate the volume percentages of pneumonia lesions with respect to the lung lobes (where the lesion was located) and to the whole lung. There were significant differences in the volume percentages of pneumonia lesions for the superior lobe of the left lung, the inferior lobe of the left lung, the superior lobe of the right lung, the inferior lobe of the right lung and the whole lung among patients with different clinical types (p<0.05). The area under the ROC curve (AUC) of the volume percentage of pneumonia lesions for the whole lung for the diagnosis of severe/critical type COVID-19 was 0.740, with sensitivity and specificity of 91.2% and 58.8%, respectively. CONCLUSIONS: The clinical and CT imaging features of COVID-19 patients were characteristic to a certain degree; thus, the clinical course and severity of COVID-19 could be evaluated with a combination of an analysis of clinical features and CT imaging features and assistant diagnosis by AI software.

Haematological characteristics and risk factors in the classification and prognosis evaluation of COVID-19: a retrospective cohort study.

BACKGROUND: COVID-19 is an ongoing global pandemic. Changes in haematological characteristics in patients with COVID-19 are emerging as important features of the disease. We aimed to explore the haematological characteristics and related risk factors in patients with COVID-19. METHODS: This retrospective cohort study included patients with COVID-19 admitted to three designated sites of Wuhan Union Hospital (Wuhan, China). Demographic, clinical, laboratory, treatment, and outcome data were extracted from electronic medical records and compared between patients with moderate, severe, and critical disease (defined according to the diagnosis and treatment protocol for novel coronavirus pneumonia, trial version 7, published by the National Health Commission of China). We assessed the risk factors associated with critical illness and poor prognosis. Dynamic haematological and coagulation parameters were investigated with a linear mixed model, and coagulopathy screening with sepsis-induced coagulopathy and International Society of Thrombosis and Hemostasis overt disseminated intravascular coagulation scoring systems was applied. FINDINGS: Of 466 patients admitted to hospital from Jan 23 to Feb 23, 2020, 380 patients with COVID-19 were included in our study. The incidence of thrombocytopenia (platelet count <100 × 109 cells per L) in patients with critical disease (42 [49%] of 86) was significantly higher than in those with severe (20 [14%] of 145) or moderate (nine [6%] of 149) disease (p<0·0001). The numbers of lymphocytes and eosinophils were significantly lower in patients with critical disease than those with severe or moderate disease (p<0·0001), and prothrombin time, D-dimer, and fibrin degradation products significantly increased with increasing disease severity (p<0·0001). In multivariate analyses, death was associated with increased neutrophil to lymphocyte ratio (≥9·13; odds ratio [OR] 5·39 [95% CI 1·70-17·13], p=0·0042), thrombocytopenia (platelet count <100 × 109 per L; OR 8·33 [2·56-27·15], p=0·00045), prolonged prothrombin time (>16 s; OR 4·94 [1·50-16·25], p=0·0094), and increased D-dimer (>2 mg/L; OR 4·41 [1·06-18·30], p=0·041). Thrombotic and haemorrhagic events were common complications in patients who died (19 [35%] of 55). Sepsis-induced coagulopathy and International Society of Thrombosis and Hemostasis overt disseminated intravascular coagulation scores (assessed in 12 patients who survived and eight patients who died) increased over time in patients who died. The onset of sepsis-induced coagulopathy was typically before overt disseminated intravascular coagulation. INTERPRETATION: Rapid blood tests, including platelet count, prothrombin time, D-dimer, and neutrophil to lymphocyte ratio can help clinicians to assess severity and prognosis of patients with COVID-19. The sepsis-induced coagulopathy scoring system can be used for early assessment and management of patients with critical disease. FUNDING: National Key Research and Development Program of China.