scholarly journals A Predictive Clinical-Radiomics Nomogram for Survival Prediction of Glioblastoma Using MRI

Diagnostics ◽  
2021 ◽  
Vol 11 (11) ◽  
pp. 2043
Author(s):  
Samy Ammari ◽  
Raoul Sallé de Chou ◽  
Corinne Balleyguier ◽  
Emilie Chouzenoux ◽  
Mehdi Touat ◽  
...  
Keyword(s):  
Primary Brain Tumor ◽  
Survival Prediction ◽  
Clinical Tool ◽  
Training Set ◽  
Kaplan Meier ◽  
Prediction Of Survival ◽  
Test Sets ◽  
One Year ◽  
Independent Cohort ◽  
Treatment Personalization

Glioblastoma (GBM) is the most common and aggressive primary brain tumor in adult patients with a median survival of around one year. Prediction of survival outcomes in GBM patients could represent a huge step in treatment personalization. The objective of this study was to develop machine learning (ML) algorithms for survival prediction of GBM patient. We identified a radiomic signature on a training-set composed of data from the 2019 BraTS challenge (210 patients) from MRI retrieved at diagnosis. Then, using this signature along with the age of the patients for training classification models, we obtained on test-sets AUCs of 0.85, 0.74 and 0.58 (0.92, 0.88 and 0.75 on the training-sets) for survival at 9-, 12- and 15-months, respectively. This signature was then validated on an independent cohort of 116 GBM patients with confirmed disease relapse for the prediction of patients surviving less or more than the median OS of 22 months. Our model insured an AUC of 0.71 (0.65 on train). The Kaplan–Meier method showed significant OS difference between groups (log-rank p = 0.05). These results suggest that radiomic signatures may improve survival outcome predictions in GBM thus creating a solid clinical tool for tailoring therapy in this population.

scholarly journals A Comprehensive Prognostic and Immunological Analysis of a Six-Gene Signature Associated With Glycolysis and Immune Response in Uveal Melanoma

2021 ◽  
Vol 12 ◽  
Author(s):  
Jun Liu ◽  
Jianjun Lu ◽  
Wenli Li
Keyword(s):  
Immune Response ◽  
Risk Stratification ◽  
Cox Regression ◽  
Predictive Ability ◽  
Gene Signature ◽  
Risk Scores ◽  
Survival Prediction ◽  
Regression Analyses ◽  
Training Set ◽  
Kaplan Meier

Uveal melanoma (UM) is a subtype of melanoma with poor prognosis. This study aimed to construct a new prognostic gene signature that can be used for survival prediction and risk stratification of UM patients. In this work, transcriptome data from the Molecular Signatures Database were used to identify the cancer hallmarks most relevant to the prognosis of UM patients. Weighted gene co-expression network, univariate least absolute contraction and selection operator (LASSO), and multivariate Cox regression analyses were used to construct the prognostic gene characteristics. Kaplan–Meier and receiver operating characteristic (ROC) curves were used to evaluate the survival predictive ability of the gene signature. The results showed that glycolysis and immune response were the main risk factors for overall survival (OS) in UM patients. Using univariate Cox regression analysis, 238 candidates related to the prognosis of UM patients were identified (p < 0.05). Using LASSO and multivariate Cox regression analyses, a six-gene signature including ARPC1B, BTBD6, GUSB, KRTCAP2, RHBDD3, and SLC39A4 was constructed. Kaplan–Meier analysis of the UM cohort in the training set showed that patients with higher risk scores had worse OS (HR = 2.61, p < 0.001). The time-dependent ROC (t-ROC) curve showed that the risk score had good predictive efficiency for UM patients in the training set (AUC > 0.9). Besides, t-ROC analysis showed that the predictive ability of risk scores was significantly higher than that of other clinicopathological characteristics. Univariate and multivariate Cox regression analyses showed that risk score was an independent risk factor for OS in UM patients. The prognostic value of risk scores was further verified in two external UM cohorts (GSE22138 and GSE84976). Two-factor survival analysis showed that UM patients with high hypoxia or immune response scores and high risk scores had the worst prognosis. Moreover, a nomogram based on the six-gene signature was established for clinical practice. In addition, risk scores were related to the immune infiltration profiles. Taken together, this study identified a new prognostic six-gene signature related to glycolysis and immune response. This six-gene signature can not only be used for survival prediction and risk stratification but also may be a potential therapeutic target for UM patients.

scholarly journals A Deep-Learning Model With the Attention Mechanism Could Rigorously Predict Survivals in Neuroblastoma

2021 ◽  
Vol 11 ◽  
Author(s):  
Chenzhao Feng ◽  
Tianyu Xiang ◽  
Zixuan Yi ◽  
Xinyao Meng ◽  
Xufeng Chu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Molecular Mechanisms ◽  
Operating Characteristic ◽  
Roc Curves ◽  
Attention Mechanism ◽  
Survival Prediction ◽  
Training Set ◽  
Kaplan Meier ◽  
Applied Artificial Intelligence ◽  
Deep Learning Model

BackgroundNeuroblastoma is one of the most devastating forms of childhood cancer. Despite large amounts of attempts in precise survival prediction in neuroblastoma, the prediction efficacy remains to be improved.MethodsHere, we applied a deep-learning (DL) model with the attention mechanism to predict survivals in neuroblastoma. We utilized 2 groups of features separated from 172 genes, to train 2 deep neural networks and combined them by the attention mechanism.ResultsThis classifier could accurately predict survivals, with areas under the curve of receiver operating characteristic (ROC) curves and time-dependent ROC reaching 0.968 and 0.974 in the training set respectively. The accuracy of the model was further confirmed in a validation cohort. Importantly, the two feature groups were mapped to two groups of patients, which were prognostic in Kaplan-Meier curves. Biological analyses showed that they exhibited diverse molecular backgrounds which could be linked to the prognosis of the patients.ConclusionsIn this study, we applied artificial intelligence methods to improve the accuracy of neuroblastoma survival prediction based on gene expression and provide explanations for better understanding of the molecular mechanisms underlying neuroblastoma.

scholarly journals A novel tp53-associated nomogram to predict the overall survival in patients with pancreatic cancer

BMC Cancer ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Xun Liu ◽  
Bobo Chen ◽  
Jiahui Chen ◽  
Shaolong Sun
Keyword(s):  
Pancreatic Cancer ◽  
Overall Survival ◽  
Regression Analysis ◽  
Risk Score ◽  
Roc Curves ◽  
Gene Signature ◽  
Survival Prediction ◽  
Training Set ◽  
Kaplan Meier ◽  
Validation Set

Abstract Background Gene mutations play critical roles in tumorigenesis and cancer development. Our study aimed to screen survival-related mutations and explore a novel gene signature to predict the overall survival in pancreatic cancer. Methods Somatic mutation data from three cohorts were used to identify the common survival-related gene mutation with Kaplan-Meier curves. RNA-sequencing data were used to explore the signature for survival prediction. First, Weighted Gene Co-expression Network Analysis was conducted to identify candidate genes. Then, the ICGC-PACA-CA cohort was applied as the training set and the TCGA-PAAD cohort was used as the external validation set. A TP53-associated signature calculating the risk score of every patient was developed with univariate Cox, least absolute shrinkage and selection operator, and stepwise regression analysis. Kaplan-Meier and receiver operating characteristic curves were plotted to verify the accuracy. The independence of the signature was confirmed by the multivariate Cox regression analysis. Finally, a prognostic nomogram including 359 patients was constructed based on the combined expression data and the risk scores. Results TP53 mutation was screened to be the robust and survival-related mutation type, and was associated with immune cell infiltration. Two thousand, four hundred fifty-five genes included in the six modules generated in the WGCNA were screened as candidate survival related TP53-associated genes. A seven-gene signature was constructed: Risk score = (0.1254 × ERRFI1) - (0.1365 × IL6R) - (0.4400 × PPP1R10) - (0.3397 × PTOV1-AS2) + (0.1544 × SCEL) - (0.4412 × SSX2IP) – (0.2231 × TXNL4A). Area Under Curves of 1-, 3-, and 5-year ROC curves were 0.731, 0.808, and 0.873 in the training set and 0.703, 0.677, and 0.737 in the validation set. A prognostic nomogram including 359 patients was constructed and well-calibrated, with the Area Under Curves of 1-, 3-, and 5-year ROC curves as 0.713, 0.753, and 0.823. Conclusions The TP53-associated signature exhibited good prognostic efficacy in predicting the overall survival of PC patients.

scholarly journals Screening the genome for HCC-specific CpG methylation signatures as biomarkers for diagnosis and prognosis evaluation

2021 ◽  
Vol 14 (1) ◽  
Author(s):  
Rui-kun Zhang ◽  
Jia-lin Liu
Keyword(s):  
Cox Regression ◽  
Malignant Tumors ◽  
Gene Expression Omnibus ◽  
The Cancer Genome Atlas ◽  
Survival Prediction ◽  
Training Set ◽  
Cpg Sites ◽  
Diagnosis And Prognosis ◽  
Patient Prognosis ◽  
Prognosis Evaluation

Abstract Background Hepatocellular carcinoma (HCC) is one of the most common and invasive malignant tumors in the world. The change in DNA methylation is a key event in HCC. Methods Methylation datasets for HCC and 17 other types of cancer were downloaded from The Cancer Genome Atlas (TCGA). The CpG sites with large differences in methylation between tumor tissues and paracancerous tissues were identified. We used the HCC methylation dataset downloaded from the TCGA as the training set and removed the overlapping sites among all cancer datasets to ensure that only CpG sites specific to HCC remained. Logistic regression analysis was performed to select specific biomarkers that can be used to diagnose HCC, and two datasets—GSE157341 and GSE54503—downloaded from GEO as validation sets were used to validate our model. We also used a Cox regression model to select CpG sites related to patient prognosis. Results We identified 6 HCC-specific methylated CpG sites as biomarkers for HCC diagnosis. In the training set, the area under the receiver operating characteristic (ROC) curve (AUC) for the model containing all these sites was 0.971. The AUCs were 0.8802 and 0.9711 for the two validation sets from the GEO database. In addition, 3 other CpG sites were analyzed and used to create a risk scoring model for patient prognosis and survival prediction. Conclusions Through the analysis of HCC methylation datasets from the TCGA and Gene Expression Omnibus (GEO) databases, potential biomarkers for HCC diagnosis and prognosis evaluation were ascertained.

Malnutrition and biological frailty are independent and complementary predictors of one-year mortality in women after primary angioplasty for ST-segment elevation myocardial infarction

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
R Arroyo-Espliguero ◽  
M.C Viana-Llamas ◽  
A Silva-Obregon ◽  
A Estrella-Alonso ◽  
C Marian-Crespo ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Mortality Rate ◽  
Primary Angioplasty ◽  
Prognostic Impact ◽  
St Segment Elevation ◽  
Segment Elevation Myocardial Infarction ◽  
Kaplan Meier ◽  
St Segment ◽  
One Year ◽  
The Impact

Abstract Background Malnutrition and sarcopenia are common features of frailty. Prevalence of frailty among ST-segment elevation myocardial infarction (STEMI) patients is higher in women than men. Purpose Assess gender-based differences in the impact of nutritional risk index (NRI) and frailty in one-year mortality rate among STEMI patients following primary angioplasty (PA). Methods Cohort of 321 consecutive patients (64 years [54–75]; 22.4% women) admitted to a general ICU after PA for STEMI. NRI was calculated as 1.519 × serum albumin (g/L) + 41.7 × (actual body weight [kg]/ideal weight [kg]). Vulnerable and moderate to severe NRI patients were those with Clinical Frailty Scale (CFS)≥4 and NRI<97.5, respectively. We used Kaplan-Meier survival model. Results Baseline and mortality variables of 4 groups (NRI-/CFS-; NRI+/CFS-; NRI+/CFS- and NRI+/CFS+) are depicted in the Table. Prevalence of malnutrition, frailty or both were significantly greater in women (34.3%, 10% y 21.4%, respectively) than in men (28.9%, 2.8% y 6.0%, respectively; P<0.001). Women had greater mortality rate (20.8% vs. 5.2%: OR 4.78, 95% CI, 2.15–10.60, P<0.001), mainly from cardiogenic shock (P=0.003). Combination of malnutrition and frailty significantly decreased cumulative one-year survival in women (46.7% vs. 73.3% in men, P<0.001) Conclusion Among STEMI patients undergoing PA, the prevalence of malnutrition and frailty are significantly higher in women than in men. NRI and frailty had an independent and complementary prognostic impact in women with STEMI. Kaplan-Meier and Cox survival curves Funding Acknowledgement Type of funding source: None

scholarly journals Feature-Weighted Sampling for Proper Evaluation of Classification Models

2021 ◽  
Vol 11 (5) ◽  
pp. 2039
Author(s):  
Hyunseok Shin ◽  
Sejong Oh
Keyword(s):  
Random Sampling ◽  
Sampling Method ◽  
Classification Model ◽  
Training Set ◽  
Test Set ◽  
Feature Importance ◽  
Proper Training ◽  
Machine Learning Applications ◽  
Test Sets ◽  
The Given

In machine learning applications, classification schemes have been widely used for prediction tasks. Typically, to develop a prediction model, the given dataset is divided into training and test sets; the training set is used to build the model and the test set is used to evaluate the model. Furthermore, random sampling is traditionally used to divide datasets. The problem, however, is that the performance of the model is evaluated differently depending on how we divide the training and test sets. Therefore, in this study, we proposed an improved sampling method for the accurate evaluation of a classification model. We first generated numerous candidate cases of train/test sets using the R-value-based sampling method. We evaluated the similarity of distributions of the candidate cases with the whole dataset, and the case with the smallest distribution–difference was selected as the final train/test set. Histograms and feature importance were used to evaluate the similarity of distributions. The proposed method produces more proper training and test sets than previous sampling methods, including random and non-random sampling.

scholarly journals POS0859 DEEP PHENOTYPING OF DERMATOMYOSITIS BASED ON LIPID FERROPTOSIS-RELATED GENES BY MACHINE LEARNING

2021 ◽  
Vol 80 (Suppl 1) ◽  
pp. 684.1-684
Author(s):  
J. Q. Zhang ◽  
S. X. Zhang ◽  
R. Zhao ◽  
J. Qiao ◽  
M. T. Qiu ◽  
...  
Keyword(s):  
Gene Expression ◽  
T Cells ◽  
Expression Profiles ◽  
Inflammatory Myopathy ◽  
Shanxi Province ◽  
Survival Prediction ◽  
Training Set ◽  
Redox Biology ◽  
Score Model ◽  
Validation Set

Background:Dermatomyositis (DM) is an idiopathic inflammatory myopathy with heterogeneous clinical manifestation that raise challenges regarding diagnosis and therapy1. Ferroptosis is a newly discovered form of regulated cell death that is the nexus between metabolism, redox biology, and rheumatic immune diseases2. However, how ferroptosis maintains the balance of lymphocyte T cells and affect disease activity in DM is unclear.Objectives:To investigate an ferroptosis-related multiple gene expression signature for classification by assessing the global gene expression profile, and calculate the lymphocyte T cells status in the different subsets.Methods:Gene expression profiles of skeletal muscle from DM samples were acquired from GEO database. GSE143323 (30 patients and 20 HCs) was selected as the training set. The GSE3307 contained 21 DM patients and was selected as the validation set. The 60 ferroptosis genes were obtained from previous literature3. The intersection of the global gene and ferroptosis genes was considered the set of significant G-Ferroptosis genes for further analysis. The “NMF” (R-package) was applied as an unsupervised clustering method for sample classification by using G-Ferroptosis genes expression microarray data from the training datasets. An ferroptosis score model was constructed. The performance of the ferroptosis genes-based risk score model constructed by the DM training set was validated in the batch-1 and batch-2 DM sets. Normalized ferroptosis genes training data was used to compare the ssGSEA scores of gene sets between the high risk and low risk group. The statistical software package R (version 4.0.3) was used for all analyses. P value < 0.05 were considered statistically significant.Results:We selected 54 significant G-Ferroptosis genes for further analysis in training set. There were 2 distinct subtypes (high-ferroptosis-score groups and low-ferroptosis-score groups) identified in G-Ferroptosis genes cohort which were also identified in validation datasets (Fig.1A, C, D). Metallothionein 1G (MT1G) was a characteristic gene of low-ferroptosis-score group. The characteristic genes of high-ferroptosis-score group were acyl-CoA synthetase family member 2(ACSF2) and aconitase 1(ACO1) (Fig.1B). Patients in high-ferroptosis-score group had a lower level of Tregs compared with that of low-ferroptosis-score patients in both training and validation set (P <0.05, Fig.1E).Conclusion:The biological process of ferroptosis is associated with the lever of Tregs, suggesting the process of ferroptosis may be involved in the disease progression of DM. Identificating ferroptosis-related features for DM might provide a new idea for clinical treatment.References:[1]DeWane ME, Waldman R, Lu J. Dermatomyositis: Clinical features and pathogenesis. Journal of the American Academy of Dermatology 2020;82(2):267-81. doi: 10.1016/j.jaad.2019.06.1309 [published Online First: 2019/07/08].[2]Liang C, Zhang X, Yang M, et al. Recent Progress in Ferroptosis Inducers for Cancer Therapy. Advanced materials (Deerfield Beach, Fla) 2019;31(51):e1904197. doi: 10.1002/adma.201904197 [published Online First: 2019/10/09].[3]Liang JY, Wang DS, Lin HC, et al. A Novel Ferroptosis-related Gene Signature for Overall Survival Prediction in Patients with Hepatocellular Carcinoma. International journal of biological sciences 2020;16(13):2430-41. doi: 10.7150/ijbs.45050 [published Online First: 2020/08/08].Acknowledgements:This project was supported by National Science Foundation of China (82001740).Open Fund from the Key Laboratory of Cellular Physiology (Shanxi Medical University) (KLCP2019) and Innovation Plan for Postgraduate Education in Shanxi Province (2020BY078).Disclosure of Interests:None declared

scholarly journals 18F-FDG PET/CT and Urothelial Carcinoma: Impact on Management and Prognosis—A Multicenter Retrospective Study

Cancers ◽  
2019 ◽  
Vol 11 (5) ◽  
pp. 700 ◽  
Author(s):  
Fabio Zattoni ◽  
Elena Incerti ◽  
Fabrizio Dal Moro ◽  
Marco Moschini ◽  
Paolo Castellucci ◽  
...  
Keyword(s):  
Overall Survival ◽  
Urothelial Carcinoma ◽  
Fdg Pet ◽  
Patient Management ◽  
Survival Prediction ◽  
Primary Tumor Site ◽  
Kaplan Meier ◽  
Pet Ct ◽  
18F Fdg ◽  
Fdg Pet Ct

Objectives: To evaluate the ability of 18F-labeled fluoro-2-deoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) to predict survivorship of patients with bladder cancer (BC) and/or upper urinary tract carcinoma (UUTC). Materials: Data from patients who underwent FDG PET/CT for suspicion of recurrent urothelial carcinoma (UC) between 2007 and 2015 were retrospectively collected in a multicenter study. Disease management after the introduction of FDG PET/CT in the diagnostic algorithm was assessed in all patients. Kaplan-Meier and log-rank analysis were computed for survival assessment. A Cox regression analysis was used to identify predictors of recurrence and death, for BC, UUTC, and concomitant BC and UUTC. Results: Data from 286 patients were collected. Of these, 212 had a history of BC, 38 of UUTC and 36 of concomitant BC and UUTC. Patient management was changed in 114/286 (40%) UC patients with the inclusion of FDG PET/CT, particularly in those with BC, reaching 74% (n = 90/122). After a mean follow-up period of 21 months (Interquartile range: 4–28 mo.), 136 patients (47.4%) had recurrence/progression of disease. Moreover, 131 subjects (45.6%) died. At Kaplan-Meier analyses, patients with BC and positive PET/CT had a worse overall survival than those with a negative scan (log-rank < 0.001). Furthermore, a negative PET/CT scan was associated with a lower recurrence rate than a positive examination, independently from the primary tumor site. At multivariate analysis, in patients with BC and UUTC, a positive FDG PET/CT resulted an independent predictor of disease-free and overall survival (p < 0,01). Conclusions: FDG PET/CT has the potential to change patient management, particularly for patients with BC. Furthermore, it can be considered a valid survival prediction tool after primary treatment in patients with recurrent UC. However, a firm recommendation cannot be made yet. Further prospective studies are necessary to confirm our findings.

scholarly journals One-year outcomes of microhook trabeculotomy versus suture trabeculotomy ab interno

2021 ◽  
Author(s):  
Hiroshi Yokoyama ◽  
Masashi Takata ◽  
Fumi Gomi
Keyword(s):  
Survival Analysis ◽  
Clinical Success ◽  
Treatment Success ◽  
Medication Use ◽  
Glaucoma Surgery ◽  
Success Rates ◽  
Kaplan Meier ◽  
One Year ◽  
Ab Interno

Abstract Purpose To compare clinical success rates and reductions in intraocular pressure (IOP) and IOP-lowering medication use following suture trabeculotomy ab interno (S group) or microhook trabeculotomy (μ group). Methods This retrospective review collected data from S (n = 104, 122 eyes) and μ (n = 42, 47 eyes) groups who underwent treatment between June 1, 2016, and October 31, 2019, and had 12-month follow-up data including IOP, glaucoma medications, complications, and additional IOP-lowering procedures. The Kaplan–Meier survival analysis was used to evaluate treatment success rates defined as normal IOP (> 5 to ≤ 18 mm Hg), ≥ 20% reduction of IOP from baseline at two consecutive visits, and no further glaucoma surgery. Results Schlemm’s canal opening was longer in the S group than in the μ group (P < 0.0001). The Kaplan–Meier survival analysis of all eyes showed cumulative clinical success rates in S and µ groups were 71.1% and 61.7% (P = 0.230). The Kaplan–Meier survival analysis of eyes with preoperative IOP ≥ 21 mmHg showed cumulative clinical success rates in S and μ groups were 80.4% and 60.0% (P = 0.0192). There were no significant differences in postoperative IOP at 1, 3, and 6 months (S group, 14.9 ± 5.6, 14.6 ± 4.5, 14.6 ± 3.9 mmHg; μ group, 15.8 ± 5.9, 15.2 ± 4.4, 14.7 ± 3.7 mmHg; P = 0.364, 0.443, 0.823), but postoperative IOP was significantly lower in the S group at 12 months (S group, 14.1 ± 3.1 mmHg; μ group, 15.6 ± 4.1 mmHg; P = 0.0361). There were no significant differences in postoperative numbers of glaucoma medications at 1, 3, 6, and 12 months (S group, 1.8 ± 1.6, 1.8 ± 1.5, 2.0 ± 1.6, 1.8 ± 1.5; μ group, 2.0 ± 1.6, 2.0 ± 1.6, 2.1 ± 1.6, 2.2 ± 1.7; P = 0.699, 0.420, 0.737, 0.198). Conclusion S and µ group eyes achieved IOP reduction, but μ group eyes had lower clinical success rates among patients with high preoperative IOP at 12 months.

scholarly journals U-survival for prognostic prediction of disease progression and mortality of patients with COVID-19

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Janne J. Näppi ◽  
Tomoki Uemura ◽  
Chinatsu Watari ◽  
Toru Hironaka ◽  
Tohru Kamiya ◽  
...  
Keyword(s):  
Risk Groups ◽  
Healthcare Services ◽  
Chest Ct ◽  
Prediction Performance ◽  
Survival Prediction ◽  
Concordance Index ◽  
Survival Curves ◽  
Analysis Methodology ◽  
Kaplan Meier ◽  
Prognostic Prediction

AbstractThe rapid increase of patients with coronavirus disease 2019 (COVID-19) has introduced major challenges to healthcare services worldwide. Therefore, fast and accurate clinical assessment of COVID-19 progression and mortality is vital for the management of COVID-19 patients. We developed an automated image-based survival prediction model, called U-survival, which combines deep learning of chest CT images with the established survival analysis methodology of an elastic-net Cox survival model. In an evaluation of 383 COVID-19 positive patients from two hospitals, the prognostic bootstrap prediction performance of U-survival was significantly higher (P < 0.0001) than those of existing laboratory and image-based reference predictors both for COVID-19 progression (maximum concordance index: 91.6% [95% confidence interval 91.5, 91.7]) and for mortality (88.7% [88.6, 88.9]), and the separation between the Kaplan–Meier survival curves of patients stratified into low- and high-risk groups was largest for U-survival (P < 3 × 10–14). The results indicate that U-survival can be used to provide automated and objective prognostic predictions for the management of COVID-19 patients.

Sign in / Sign up

Export Citation Format

Share Document