Severity assessment of COVID-19 using CT image features and laboratory indices.

The coronavirus disease 2019 (COVID-19) is now a global pandemic. Tens of millions of people have been confirmed with infection, and also more people are suspected. Chest computed tomography (CT) is recognized as an important tool for COVID-19 severity assessment. As the number of chest CT images increases rapidly, manual severity assessment becomes a labor-intensive task, delaying appropriate isolation and treatment. In this paper, a study of automatic severity assessment for COVID-19 is presented. Specifically, chest CT images of 118 patients (age 46.5 ± 16.5 years, 64 male and 54 female) with confirmed COVID-19 infection are used, from which 63 quantitative features and 110 radiomics features are derived. Besides the chest CT image features, 36 laboratory indices of each patient are also used, which can provide complementary information from a different view. A random forest (RF) model is trained to assess the severity (non-severe or severe) according to the chest CT image features and laboratory indices. Importance of each chest CT image feature and laboratory index, which reflects the correlation to the severity of COVID-19, is also calculated from the RF model. Using three-fold cross-validation, the RF model shows promising results: 0.910 (true positive ratio), 0.858 (true negative ratio) and 0.890 (accuracy), along with AUC of 0.98. Moreover, several chest CT image features and laboratory indices are found to be highly related to COVID-19 severity, which could be valuable for the clinical diagnosis of COVID-19.

Immunodominant regions prediction of nucleocapsid protein for SARS-CoV-2 early diagnosis: a bioinformatics and immunoinformatics study.

COVID-19 caused by SARS-CoV-2 is sweeping the world and posing serious health problems. Rapid and accurate detection along with timely isolation is the key to control the epidemic. Nucleic acid test and antibody-detection have been applied in the diagnosis of COVID-19, while both have their limitations. Comparatively, direct detection of viral antigens in clinical specimens is highly valuable for the early diagnosis of SARS-CoV-2. The nucleocapsid (N) protein is one of the predominantly expressed proteins with high immunogenicity during the early stages of infection. Here, we applied multiple bioinformatics servers to forecast the potential immunodominant regions derived from the N protein of SARS-CoV-2. Since the high homology of N protein between SARS-CoV-2 and SARS-CoV, we attempted to leverage existing SARS-CoV immunological studies to develop SARS-CoV-2 diagnostic antibodies. Finally, N229-269, N349-399, and N405-419 were predicted to be the potential immunodominant regions, which contain both predicted linear B-cell epitopes and murine MHC class II binding epitopes. These three regions exhibited good surface accessibility and hydrophilicity. All were forecasted to be non-allergen and non-toxic. The final construct was built based on the bioinformatics analysis, which could help to develop an antigen-capture system for the early diagnosis of SARS-CoV-2.

Integrating regression formulas and kernel functions into locally adaptive knowledge-based neural networks: a case study on renal function evaluation.

OBJECTIVE: In many medical areas, there exist different regression formulas to predict/evaluate a medical outcome on the same problem, each of them being efficient only in a particular sub-space of the problem space. The paper aims at the development of a generic, incremental learning model that includes all available regression formulas for a particular prediction problem to define local areas of the problem space with their best performing formula along with useful explanation rules. Another objective of the paper is to develop a specific model for renal function evaluation using nine existing formulas. METHODS AND MATERIALS: We have used a connectionist neuro-fuzzy approach and have developed a knowledge-based neural network model (KBNN) which incorporates and adapts incrementally several existing regression formulas and kernel functions. The model incorporates different non-linear regression functions as neurons in its hidden layer and adapts these functions through incremental learning from data in particular local areas of the space. More specifically, each hidden neural node has a pair of functions associated with it--one regression formula, that represents existing knowledge and one Gaussian kernel function, that defines the sub-space of the whole problem space, in which the formula is locally adapted to new data. All these functions are aggregated and changed through incremental learning. The proposed KBNN model is illustrated using a medical dataset of observed patient glomerular filtration rate (GFR) measurements for renal function evaluation. In this case study, the regression function for each cluster is selected by the model from nine formulas commonly used by medical practitioners to predict GFR. 441 GFR data vectors from 141 patients taken from 12 sites in Australia and New Zealand have been used as a case study experimental data set. RESULTS: The proposed GFR prediction model, based on the proposed generic KBNN model, outperforms at least by 10% accuracy any of the individual regression formulas or a standard neural network model. Furthermore, we have derived locally adapted regression formulas to perform best on local clusters of data along with useful explanatory rules. CONCLUSION: The proposed KBNN model manifests better accuracy then existing regression formulas or neural network models for renal function evaluation and extracts modified formulas that perform well in local areas of the problem space.

Sustained low-efficiency daily diafiltration (SLEDD-f) for critically ill patients requiring renal replacement therapy: towards an adequate therapy.

BACKGROUND: Sustained low-efficiency daily dialysis (SLEDD) is an increasingly popular renal replacement therapy for intensive care unit (ICU) patients. SLEDD has been previously reported to provide good solute control and haemodynamic stability. However, continuous renal replacement therapy (CRRT) is considered superior by many ICU practitioners, due first to the large amounts of convective clearance achieved and second to the ability to deliver treatment independently of nephrology services. We report on a program of sustained low-efficiency daily diafiltration (SLEDD-f) delivered autonomously by ICU nursing personnel, and benchmark solute clearance data with recently published reports that have provided dose-outcome relationships for renal replacement therapy in this population. METHODS: SLEDD-f treatments were delivered using countercurrent dialysate flow at 200 ml/min and on-line haemofiltration at 100 ml/min for 8 h on a daily or at least alternate day basis. All aspects of SLEDD-f were managed by ICU nursing personnel. Clinical parameters, patient outcomes and solute levels were monitored. Kt/V, corrected equivalent renal urea clearance (EKRc) and theoretical Kt/V(B12) were calculated. RESULTS: Fifty-six SLEDD-f treatments in 24 critically ill acute renal failure patients were studied. There were no episodes of intradialytic hypotension or other complications. Observed hospital mortality was 46%, not significantly different from the expected mortality as determined from the APACHE II illness severity scoring system. Electrolyte control was excellent. Kt/V per completed treatment was 1.43+/-0.28 (0.96-2.0). Kt/V(B12) per completed treatment was 1.02+/-0.21 (0.6-1.38). EKRc for patients was 35.7+/-6.4 ml/min (25.0-48.2). CONCLUSION: SLEDD-f provides stable renal replacement therapy and good clinical outcomes. Logistic elements of SLEDD-f delivery by ICU nursing personnel are satisfactory. Small solute clearance is adequate by available standards for CRRT and intermittent haemodialysis, and larger solute clearance considerable. SLEDD-f is a viable alternative to CRRT in this setting.