Clinical, laboratory and imaging predictors for critical illness and mortality in patients with COVID-19: protocol for a systematic review and meta-analysis

Lai, Xinxing; Liu, Jian; Zhang, Tianyi; Feng, Luda; Jiang, Ping; Kang, Ligaoge; Liu, Qiang; Gao, Ying

doi:10.1136/bmjopen-2020-039813

Cited by 8 publications

(8 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is an urgent need to identify patients at higher risk of intubation and death, since de novo ARF plays a central role in Covid-19, being responsible for morbidity and mortality [4,42,43]. In addition, defining the best setting where to allocate patients affected by SARS-CoV-2 pneumonia could play a central role in this emergency era for health care resources worldwide.…”

Section: Discussionmentioning

confidence: 99%

Standardizing PaO2 for PaCO2 in P/F ratio predicts in-hospital mortality in acute respiratory failure due to Covid-19: A pilot prospective study

Prediletto

D’Antoni

Carbonara

et al. 2021

European Journal of Internal Medicine

View full text Add to dashboard Cite

Up to fifteen percent of patients with novel pandemic coronavirus disease have acute respiratory failure (ARF). Ratio between arterial partial pressure of oxygen (PaO2) and fraction of inspired oxygen (FiO2), P/F, is currently used as a marker of ARF severity in Covid-19. P/F does not reflect the respiratory efforts made by patients to maintain arterial blood oxygenation, such as tachypnea and hyperpnea, leading to hypocapnia. Standard PaO2, the value of PaO2 adjusted for arterial partial pressure of carbon dioxide (PaCO2) of the subject, better reflects the pathophysiology of hypoxemic ARF. We hypothesized that the ratio between standard PaO2 over FiO2 (STP/F) better predicts Covid-19 ARF severity compared to P/F. Methods: Aim of this pilot prospectic observational study was to observe differences between STP/F and P/F in predicting outcome failure, defined as need of invasive mechanical ventilation and/or deaths in Covid-19 ARF. Accuracy was calculated using Receiver Operating Characteristics (ROC) analysis and areas under the ROC curve (AUROC) were compared. Results: 349 consecutive subjects admitted to our respiratory wards due to Covid-19 ARF were enrolled. STP/F was accurate to predict mortality and superior to P/F with, respectively, AUROC 0.710 versus 0.688, p = 0.012. Both STP/F and PF were accurate to predict outcome failure (AUROC respectively of 0.747 and 0.742, p = 0.590).

show abstract

Section: Discussionmentioning

confidence: 99%

Standardizing PaO2 for PaCO2 in P/F ratio predicts in-hospital mortality in acute respiratory failure due to Covid-19: A pilot prospective study

Prediletto

D’Antoni

Carbonara

et al. 2021

European Journal of Internal Medicine

View full text Add to dashboard Cite

show abstract

“…On the other hand, many studies have been conducted to select the most significant variables for predicting COVID-19 mortality from a clinical perspective. In these studies, the top 10 predictors or effective factors for the mortality of COVID-19 patients are advanced age (older age) [2-6, 55, 63, 65, 67], longer LOS [1-3, 6, 65], mechanical ventilation [4,7,55,[61][62][63], fever [1,2,6,55,61,62,65], decreased SPO 2 (low oxygen saturation) [35,49,51,60], elevated interlukin-6 [4,5,55,[61][62][63][64][65], high blood pressure [2, 4-6, 8, 55, 63, 64], leukocytosis [1,4,7,8,61,63,64], increased BUN [4,5,55,[61][62][63][64][65], cardiovascular [1, 2, 4-6, 8, 55, 61-65], and COPD [4,6,…”

Section: Discussionmentioning

confidence: 99%

“…(1) Assigning weights to all the linkages to start the algorithm (2) Using the inputs and linkages for the activation rate of hidden nodes (3) Using the activation rate of hidden nodes and linkages to output, obtaining the activation rate of output nodes (4) Obtaining the error rate at the output node and cascading down the error to hidden nodes (5) Recalibrating the weights between the hidden nodes and the input nodes (6) Repeating the process till the convergence (7) Scoring the activation rate of the output nodes by the final linkage weights SVM: The SVM classifier, based on the strategy of the maximal margin classifier, looks for the hyperplane that maximizes the border between those two classes with linear separation of two classes. For example, in Figure 2, the SVM classifier finds the best hyperplane (the red line) to maximize the distance between the nearest data samples of class A and class B [48].…”

Section: Ga Implementationmentioning

confidence: 99%

“…Due to fast transmission, COV-ID-19 was known as a pandemic in a few months worldwide, affecting public health, economic, and social conditions [3,4] with a wide range of clinical presentation and prognosis, such as the common cold, respiratory infections, multiple organ failure, and death [5,6]. Also, fast exponential transmission and incremental mortality rate led to a tremendous panic in the world [7,8]. Without fully licensed treatment or whole safe vaccination, some mitigation efforts were implemented to control the epidemic [9,10].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Predicting Risk of Mortality in COVID-19 Hospitalized Patients using Hybrid Machine Learning Algorithms

2022

J Biomed Phys Eng

View full text Add to dashboard Cite

Background: Since hospitalized patients with COVID-19 are considered at high risk of death, the patients with the sever clinical condition should be identified. Despite the potential of machine learning (ML) techniques to predict the mortality of COVID-19 patients, high-dimensional data is considered a challenge, which can be addressed by metaheuristic and nature-inspired algorithms, such as genetic algorithm (GA).Objective: This paper aimed to compare the efficiency of the GA with several ML techniques to predict COVID-19 in-hospital mortality. Material and Methods:In this retrospective study, 1353 COVID-19 in-hospital patients were examined from February 9 to December 20, 2020. The GA technique was applied to select the important features, then using selected features several ML algorithms such as K-nearest-neighbor (K-NN), Decision Tree (DT), Support Vector Machines (SVM), and Artificial Neural Network (ANN) were trained to design predictive models. Finally, some evaluation metrics were used for the comparison of developed models.Results: A total of 10 features out of 56 were selected, including length of stay (LOS), age, cough, respiratory intubation, dyspnea, cardiovascular diseases, leukocytosis, blood urea nitrogen (BUN), C-reactive protein, and pleural effusion by 10-independent execution of GA. The GA-SVM had the best performance with the accuracy and specificity of 9.5147e+01 and 9.5112e+01, respectively. Conclusion:The hybrid ML models, especially the GA-SVM, can improve the treatment of COVID-19 patients, predict severe disease and mortality, and optimize the utilization of health resources based on the improvement of input features and the adaption of the structure of the models.

show abstract

“…The studies that are most closely related to our work focus on the development and assessment of prognostic models of mortality among COVID-19 infected patients [17] , [18] and the identification of prognostic factors for severity and mortality in patients infected with COVID-19. [19] , [20] , [21] , [22] , [23] …”

Section: The 24h Models Were Found To Perform Significantly Better Than the 0h Models (Improved Auroc Of 0·02) But Since It Is Only A Smamentioning

confidence: 99%

Can we reliably automate clinical prognostic modelling? A retrospective cohort study for ICU triage prediction of in-hospital mortality of COVID-19 patients in the Netherlands

Vagliano

Brinkman

Abu‐Hanna

et al. 2022

International Journal of Medical Informatics

View full text Add to dashboard Cite

Background Building Machine Learning (ML) models in healthcare may suffer from time-consuming and potentially biased pre-selection of predictors by hand that can result in limited or trivial selection of suitable models. We aimed to assess the predictive performance of automating the process of building ML models (AutoML) in-hospital mortality prediction modelling of triage COVID-19 patients at ICU admission versus expert-based predictor pre-selection followed by logistic regression. Methods We conducted an observational study of all COVID-19 patients admitted to Dutch ICUs between February and July 2020. We included 2,690 COVID-19 patients from 70 ICUs participating in the Dutch National Intensive Care Evaluation (NICE) registry. The main outcome measure was in-hospital mortality. We asessed model performance (at admission and after 24 hours, respectively) of AutoML compared to the more traditional approach of predictor pre-selection and logistic regression. Findings : Predictive performance of the autoML models with variables available at admission shows fair discrimination (average AUROC = 0·75-0·76 (sdev = 0·03), PPV = 0·70-0·76 (sdev = 0·1) at cut-off = 0·3 (the observed mortality rate), and good calibration. This performance is on par with a logistic regression model with selection of patient variables by three experts (average AUROC = 0·78 (sdev = 0·03) and PPV = 0·79 (sdev = 0·2)). Extending the models with variables that are available at 24 hours after admission resulted in models with higher predictive performance (average AUROC = 0·77-0·79 (sdev = 0·03) and PPV = 0·79-0·80 (sdev = 0·10-0·17)). Conclusions AutoML delivers prediction models with fair discriminatory performance, and good calibration and accuracy, which is as good as regression models with expert-based predictor pre-selection. In the context of the restricted availability of data in an ICU quality registry, extending the models with variables that are available at 24 hours after admission showed small (but significantly) performance increase.

show abstract

Clinical, laboratory and imaging predictors for critical illness and mortality in patients with COVID-19: protocol for a systematic review and meta-analysis

Cited by 8 publications

References 30 publications

Standardizing PaO2 for PaCO2 in P/F ratio predicts in-hospital mortality in acute respiratory failure due to Covid-19: A pilot prospective study

Standardizing PaO2 for PaCO2 in P/F ratio predicts in-hospital mortality in acute respiratory failure due to Covid-19: A pilot prospective study

Predicting Risk of Mortality in COVID-19 Hospitalized Patients using Hybrid Machine Learning Algorithms

Can we reliably automate clinical prognostic modelling? A retrospective cohort study for ICU triage prediction of in-hospital mortality of COVID-19 patients in the Netherlands

Contact Info

Product

Resources

About