Prognostic factors for COVID-19 pneumonia progression to severe symptom based on the earlier clinical features: a retrospective analysis

Huang, Huang; Cai, Shuijiang; Liu, Yueping; Li, Youxia; Fan, Yan; Li, Linghua; Lei, Chunliang; Tang, Xiaoping; Hu, Fengyu; Li, Feng; Deng, Xilong

doi:10.1101/2020.03.28.20045989

Cited by 35 publications

(27 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There are a variety of haematological and radiological predictors which have been associated with SARS-CoV-2 outcomes which are not included in our models. 29,30 Whilst our current models can produce point-of-admission outcome predictions due to the relative ease of collecting demographic, comorbidity and symptom data, additional clinical parameters could be introduced in future to improve the predictive accuracy of the models. We could not account for patients who were admitted for, and diagnosed with SARS-CoV-2, but may have died due to another comorbidity.…”

Section: Discussionmentioning

confidence: 99%

Comparison of deep learning with regression analysis in creating predictive models for SARS-CoV-2 outcomes

Abdulaal

Patel

Charani

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Accurately predicting patient outcomes in SARS-CoV-2 could aid patient management and allocation of healthcare resources. There are a variety of methods which can be used to develop prognostic models, ranging from logistic regression and survival analysis to more complex machine learning algorithms and deep learning. Despite several models having been created for SARS-CoV-2, most of these have been found to be highly susceptible to bias. We aimed to develop and compare two separate predictive models for death during admission with SARS-CoV-2. Method: Between March 1 - April 24, 2020, 398 patients were identified with laboratory confirmed SARS-CoV-2 in a London teaching hospital. Data from electronic health records were extracted and used to create two predictive models using: 1) a Cox regression model and 2) an artificial neural network (ANN). Model performance profiles were assessed by validation, discrimination, and calibration. Results: Both the Cox regression and ANN models achieved high accuracy (83.8%, 95% confidence interval (CI): 73.8 - 91.1 and 90.0%, 95% CI: 81.2 - 95.6, respectively). The area under the receiver operator curve (AUROC) for the ANN (92.6%, 95% CI: 91.1 - 94.1) was significantly greater than that of the Cox regression model (86.9%, 95% CI: 85.7 - 88.2), p=0.0136. Both models achieved acceptable calibration with Brier scores of 0.13 and 0.11 for the Cox model and ANN, respectively. Conclusion: We demonstrate an ANN which is non-inferior to a Cox regression model but with potential for further development such that it can learn as new data becomes available. Deep learning techniques are particularly suited to complex datasets with non-linear solutions, which make them appropriate for use in conditions with a paucity of prior knowledge. Accurate prognostic models for SARS-CoV-2 can provide benefits at the patient, departmental and organisational level.

show abstract

Section: Discussionmentioning

confidence: 99%

Comparison of deep learning with regression analysis in creating predictive models for SARS-CoV-2 outcomes

Abdulaal

Patel

Charani

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The authors would like to thank all nurses in the treatment team for taking care of the patients and doctors in the expert panel for their treatment guidance. This manuscript has been released as a preprint at medRxiv ( 18 ).…”

mentioning

confidence: 99%

Prognostic Factors for COVID-19 Pneumonia Progression to Severe Symptoms Based on Earlier Clinical Features: A Retrospective Analysis

et al. 2020

Self Cite

View full text Add to dashboard Cite

Approximately 15–20% of COVID-19 patients will develop severe pneumonia, and about 10% of these will die if not properly managed. Earlier discrimination of potentially severe patients basing on routine clinical and laboratory changes and commencement of prophylactical management will not only save lives but also mitigate the otherwise overwhelming healthcare burden. In this retrospective investigation, the clinical and laboratory features were collected from 125 COVID-19 patients who were classified into mild (93 cases) or severe (32 cases) groups according to their clinical outcomes after 3–7 days post-admission. The subsequent analysis with single-factor and multivariate logistic regression methods indicated that 17 factors on admission differed significantly between mild and severe groups but that only comorbidity with underlying diseases, increased respiratory rate (>24/min), elevated C-reactive protein (CRP >10 mg/L), and lactate dehydrogenase (LDH >250 U/L) were independently associated with the later disease development. Finally, we evaluated their prognostic values with receiver operating characteristic curve (ROC) analysis and found that the above four factors could not confidently predict the occurrence of severe pneumonia individually, though a combination of fast respiratory rate and elevated LDH significantly increased the predictive confidence (AUC = 0.944, sensitivity = 0.941, and specificity = 0.902). A combination consisting of three or four factors could further increase the prognostic value. Additionally, measurable serum viral RNA post-admission independently predicted the severe illness occurrence. In conclusion, a combination of general clinical characteristics and laboratory tests could provide a highly confident prognostic value for identifying potentially severe COVID-19 pneumonia patients.

show abstract

“…Table 1 summarizes the most relevant characteristics of the selected studies. Sixteen studies were peer-reviewed [5,6,[12][13][14][15][16][17][18][19][20][21][22][23][24][25] , nineteen were non-peer-reviewed [26][27][28][29][30][31][32][33][34][35][36][37][38][39][40][41][42][43][44] . Not surprisingly, quality assessment revealed a non-high study quality (Supplemental Table 1).…”

Section: Resultsmentioning

confidence: 99%

Prognostic Impact of Coagulopathy in Patients with COVID-19: a Meta-analysis of 35 Studies and 6427 Patients

Polimeni¹,

Leo²,

Spaccarotella³

et al. 2020

Preprint

View full text Add to dashboard Cite

Coronavirus Disease 2019 (COVID-19) is a highly contagious disease that appeared in China in December 2019. Several patients with severe COVID-19 infection can develop a coagulopathy according to the ISTH-criteria for disseminated intravascular coagulopathy (DIC). We conducted a meta-analysis of all available studies on COVID-19 to explore the impact of coagulopathy on severe illness and mortality. An electronic search was performed within PubMed, Google Scholar and Scopus electronic databases. The primary endpoint was the difference of D-dimer values between Non-Severe vs Severe disease and Survivors vs Non-Survivors. The primary analysis showed that mean d-dimer is significantly higher in COVID-19 patients with severe disease than in those without (SMD -2.15 [-2.73 to -1.56], I2 98%, P <0.0001). Additional analysis of platelet count showed lower levels of mean PLT in Severe patients than those observed in the Non-Severe patients (SMD 0.77 [0.32 to 1.22], I2 96%, P <0.001). Interestingly, longer mean PT was found in Severe group (SMD -1.34 [-2.06 to -0.62], I2 98%, P <0.0002) compared to Non-Severe group. In conclusion, the results of the present meta-analysis, the largest and most comprehensive to date, demonstrate that Severe COVID-19 infection is associated with higher D-dimer values, lower platelet count and prolonged PT.

show abstract

Prognostic factors for COVID-19 pneumonia progression to severe symptom based on the earlier clinical features: a retrospective analysis

Cited by 35 publications

References 14 publications

Comparison of deep learning with regression analysis in creating predictive models for SARS-CoV-2 outcomes

Comparison of deep learning with regression analysis in creating predictive models for SARS-CoV-2 outcomes

Prognostic Factors for COVID-19 Pneumonia Progression to Severe Symptoms Based on Earlier Clinical Features: A Retrospective Analysis

Prognostic Impact of Coagulopathy in Patients with COVID-19: a Meta-analysis of 35 Studies and 6427 Patients

Contact Info

Product

Resources

About