Development and validation of prognostic model for predicting mortality of COVID-19 patients in Wuhan, China.
Ontology highlight
ABSTRACT:
SUBMITTER: Mei Q
PROVIDER: S-EPMC7775455 | biostudies-literature | 2020 Dec
REPOSITORIES: biostudies-literature
Publications
Development and validation of prognostic model for predicting mortality of COVID-19 patients in Wuhan, China.
Mei Qi Q Wang Amanda Y AY Bryant Amy A Yang Yang Y Li Ming M Wang Fei F Zhao Jia Wei JW Ma Ke K Wu Liang L Chen Huawen H Luo Jinlong J Du Shangming S Halfter Kathrin K Li Yong Y Kurts Christian C Hu Guangyuan G Yuan Xianglin X Li Jian J
Scientific reports 20201231 1
Novel coronavirus 2019 (COVID-19) infection is a global public health issue, that has now affected more than 200 countries worldwide and caused a second wave of pandemic. Severe adult respiratory syndrome-CoV-2 (SARS-CoV-2) pneumonia is associated with a high risk of mortality. However, prognostic factors predicting poor clinical outcomes of individual patients with SARS-CoV-2 pneumonia remain under intensive investigation. We conducted a retrospective, multicenter study of patients with SARS-Co ...[more]
Similar Datasets
Project description:BackgroundPrevious published prognostic models for COVID-19 patients have been suggested to be prone to bias due to unrepresentativeness of patient population, lack of external validation, inappropriate statistical analyses, or poor reporting. A high-quality and easy-to-use prognostic model to predict in-hospital mortality for COVID-19 patients could support physicians to make better clinical decisions.MethodsFine-Gray models were used to derive a prognostic model to predict in-hospital mortality (treating discharged alive from hospital as the competing event) in COVID-19 patients using two retrospective cohorts (n = 1008) in Wuhan, China from January 1 to February 10, 2020. The proposed model was internally evaluated by bootstrap approach and externally evaluated in an external cohort (n = 1031).ResultsThe derivation cohort was a case-mix of mild-to-severe hospitalized COVID-19 patients (43.6% females, median age 55). The final model (PLANS), including five predictor variables of platelet count, lymphocyte count, age, neutrophil count, and sex, had an excellent predictive performance (optimism-adjusted C-index: 0.85, 95% CI: 0.83 to 0.87; averaged calibration slope: 0.95, 95% CI: 0.82 to 1.08). Internal validation showed little overfitting. External validation using an independent cohort (47.8% female, median age 63) demonstrated excellent predictive performance (C-index: 0.87, 95% CI: 0.85 to 0.89; calibration slope: 1.02, 95% CI: 0.92 to 1.12). The averaged predicted cumulative incidence curves were close to the observed cumulative incidence curves in patients with different risk profiles.ConclusionsThe PLANS model based on five routinely collected predictors would assist clinicians in better triaging patients and allocating healthcare resources to reduce COVID-19 fatality.
| S-EPMC7744735 | biostudies-literature
Project description:INTRODUCTION:COVID-19 has become a serious global pandemic. This study investigates the clinical characteristics and the risk factors for COVID-19 mortality and establishes a novel scoring system to predict mortality risk in patients with COVID-19. METHODS:A cohort of 1,663 hospitalized patients with COVID-19 in Wuhan, China, of whom 212 died and 1,252 recovered, were included in this study. Demographic, clinical, and laboratory data on admission were collected from electronic medical records between January 14, 2020 and February 28, 2020. Clinical outcomes were collected until March 26, 2020. Multivariable logistic regression was used to explore the association between potential risk factors and COVID-19 mortality. The receiver operating characteristic curve was used to predict COVID-19 mortality risk. All analyses were conducted in April 2020. RESULTS:Multivariable regression showed that increased odds of COVID-19 mortality was associated with older age (OR=2.15, 95% CI=1.35, 3.43), male sex (OR=1.97, 95% CI=1.29, 2.99), history of diabetes (OR=2.34, 95% CI=1.45, 3.76), lymphopenia (OR=1.59, 95% CI=1.03, 2.46), and increased procalcitonin (OR=3.91, 95% CI=2.22, 6.91, per SD increase) on admission. Spline regression analysis indicated that the correlation between procalcitonin levels and COVID-19 mortality was nonlinear (p=0.0004 for nonlinearity). The area under the receiver operating curve of the COVID-19 mortality risk was 0.765 (95% CI=0.725, 0.805). CONCLUSIONS:The independent risk factors for COVID-19 mortality included older age, male sex, history of diabetes, lymphopenia, and increased procalcitonin, which could help clinicians to identify patients with poor prognosis at an earlier stage. The COVID-19 mortality risk score model may assist clinicians in reducing COVID-19-related mortality by implementing better strategies for more effective use of limited medical resources.
| S-EPMC7250782 | biostudies-literature
Project description:To establish an effective nomogram for predicting in-hospital mortality of COVID-19, a retrospective cohort study was conducted in two hospitals in Wuhan, China, with a total of 4,086 hospitalized COVID-19 cases. All patients have reached therapeutic endpoint (death or discharge). First, a total of 3,022 COVID-19 cases in Wuhan Huoshenshan hospital were divided chronologically into two sets, one (1,780 cases, including 47 died) for nomogram modeling and the other (1,242 cases, including 22 died) for internal validation. We then enrolled 1,064 COVID-19 cases (29 died) in Wuhan Taikang-Tongji hospital for external validation. Independent factors included age (HR for per year increment: 1.05), severity at admission (HR for per rank increment: 2.91), dyspnea (HR: 2.18), cardiovascular disease (HR: 3.25), and levels of lactate dehydrogenase (HR: 4.53), total bilirubin (HR: 2.56), blood glucose (HR: 2.56), and urea (HR: 2.14), which were finally selected into the nomogram. The C-index for the internal resampling (0.97, 95% CI: 0.95-0.98), the internal validation (0.96, 95% CI: 0.94-0.98), and the external validation (0.92, 95% CI: 0.86-0.98) demonstrated the fair discrimination ability. The calibration plots showed optimal agreement between nomogram prediction and actual observation. We established and validated a novel prognostic nomogram that could predict in-hospital mortality of COVID-19 patients.
| S-EPMC7906167 | biostudies-literature
Project description:ObjectivesThe development of a prognostic mortality risk model for hospitalized COVID-19 patients may facilitate patient treatment planning, comparisons of therapeutic strategies, and public health preparations.MethodsWe retrospectively reviewed the electronic health records of patients hospitalized within a 13-hospital New Jersey USA network between March 1, 2020 and April 22, 2020 with positive polymerase chain reaction results for SARS-CoV-2, with follow-up through May 29, 2020. With death or hospital discharge by day 40 as the primary endpoint, we used univariate followed by stepwise multivariate proportional hazard models to develop a risk score on one-half the data set, validated on the remainder, and converted the risk score into a patient-level predictive probability of 40-day mortality based on the combined dataset.ResultsThe study population consisted of 3123 hospitalized COVID-19 patients; median age 63 years; 60% were men; 42% had >3 coexisting conditions. 713 (23%) patients died within 40 days of hospitalization for COVID-19. From 22 potential candidate factors 6 were found to be independent predictors of mortality and were included in the risk score model: age, respiratory rate ≥25/minute upon hospital presentation, oxygenation <94% on hospital presentation, and pre-hospital comorbidities of hypertension, coronary artery disease, or chronic renal disease. The risk score was highly prognostic of mortality in a training set and confirmatory set yielding in the combined dataset a hazard ratio of 1.80 (95% CI, 1.72, 1.87) for one unit increases. Using observed mortality within 20 equally sized bins of risk scores, a predictive model for an individual's 40-day risk of mortality was generated as -14.258 + 13.460*RS + 1.585*(RS-2.524)^2-0.403*(RS-2.524)^3. An online calculator of this 40-day COVID-19 mortality risk score is available at www.HackensackMeridianHealth.org/CovidRS.ConclusionsA risk score using six variables is able to prognosticate mortality within 40-days of hospitalization for COVID-19.Trial registrationClinicaltrials.gov Identifier: NCT04347993.
| S-EPMC8323891 | biostudies-literature
Project description:ObjectiveTo develop and validate a prognostic model for in-hospital mortality after four days based on age, fever at admission and five haematological parameters routinely measured in hospitalized Covid-19 patients during the first four days after admission.MethodsHaematological parameters measured during the first 4 days after admission were subjected to a linear mixed model to obtain patient-specific intercepts and slopes for each parameter. A prediction model was built using logistic regression with variable selection and shrinkage factor estimation supported by bootstrapping. Model development was based on 481 survivors and 97 non-survivors, hospitalized before the occurrence of mutations. Internal validation was done by 10-fold cross-validation. The model was temporally-externally validated in 299 survivors and 42 non-survivors hospitalized when the Alpha variant (B.1.1.7) was prevalent.ResultsThe final model included age, fever on admission as well as the slope or intercept of lactate dehydrogenase, platelet count, C-reactive protein, and creatinine. Tenfold cross validation resulted in a mean area under the receiver operating characteristic curve (AUROC) of 0.92, a mean calibration slope of 1.0023 and a Brier score of 0.076. At temporal-external validation, application of the previously developed model showed an AUROC of 0.88, a calibration slope of 0.95 and a Brier score of 0.073. Regarding the relative importance of the variables, the (apparent) variation in mortality explained by the six variables deduced from the haematological parameters measured during the first four days is higher (explained variation 0.295) than that of age (0.210).ConclusionsThe presented model requires only variables routinely acquired in hospitals, which allows immediate and wide-spread use as a decision support for earlier discharge of low-risk patients to reduce the burden on the health care system.Clinical trial registrationAustrian Coronavirus Adaptive Clinical Trial (ACOVACT); ClinicalTrials.gov, identifier NCT04351724.
| S-EPMC8819729 | biostudies-literature
Project description:BackgroundThe recent pandemic of CoVID-19 has emerged as a threat to global health security. There are very few prognostic models on CoVID-19 using machine learning.ObjectivesTo predict mortality among confirmed CoVID-19 patients in South Korea using machine learning and deploy the best performing algorithm as an open-source online prediction tool for decision-making.Materials and methodsMortality for confirmed CoVID-19 patients (n = 3,524) between January 20, 2020 and May 30, 2020 was predicted using five machine learning algorithms (logistic regression, support vector machine, K nearest neighbor, random forest and gradient boosting). The performance of the algorithms was compared, and the best performing algorithm was deployed as an online prediction tool.ResultsThe logistic regression algorithm was the best performer in terms of discrimination (area under ROC curve = 0.830), calibration (Matthews Correlation Coefficient = 0.433; Brier Score = 0.036) and. The best performing algorithm (logistic regression) was deployed as the online CoVID-19 Community Mortality Risk Prediction tool named CoCoMoRP (https://ashis-das.shinyapps.io/CoCoMoRP/).ConclusionsWe describe the development and deployment of an open-source machine learning tool to predict mortality risk among CoVID-19 confirmed patients using publicly available surveillance data. This tool can be utilized by potential stakeholders such as health providers and policymakers to triage patients at the community level in addition to other approaches.
| S-EPMC7528809 | biostudies-literature
Project description:BackgroundThe COVID-19 pandemic has affected millions of individuals and caused hundreds of thousands of deaths worldwide. Predicting mortality among patients with COVID-19 who present with a spectrum of complications is very difficult, hindering the prognostication and management of the disease. We aimed to develop an accurate prediction model of COVID-19 mortality using unbiased computational methods, and identify the clinical features most predictive of this outcome.MethodsIn this prediction model development and validation study, we applied machine learning techniques to clinical data from a large cohort of patients with COVID-19 treated at the Mount Sinai Health System in New York City, NY, USA, to predict mortality. We analysed patient-level data captured in the Mount Sinai Data Warehouse database for individuals with a confirmed diagnosis of COVID-19 who had a health system encounter between March 9 and April 6, 2020. For initial analyses, we used patient data from March 9 to April 5, and randomly assigned (80:20) the patients to the development dataset or test dataset 1 (retrospective). Patient data for those with encounters on April 6, 2020, were used in test dataset 2 (prospective). We designed prediction models based on clinical features and patient characteristics during health system encounters to predict mortality using the development dataset. We assessed the resultant models in terms of the area under the receiver operating characteristic curve (AUC) score in the test datasets.FindingsUsing the development dataset (n=3841) and a systematic machine learning framework, we developed a COVID-19 mortality prediction model that showed high accuracy (AUC=0·91) when applied to test datasets of retrospective (n=961) and prospective (n=249) patients. This model was based on three clinical features: patient's age, minimum oxygen saturation over the course of their medical encounter, and type of patient encounter (inpatient vs outpatient and telehealth visits).InterpretationAn accurate and parsimonious COVID-19 mortality prediction model based on three features might have utility in clinical settings to guide the management and prognostication of patients affected by this disease. External validation of this prediction model in other populations is needed.FundingNational Institutes of Health.
| S-EPMC7508513 | biostudies-literature
Project description:This study aimed to identify clinical features for prognosing mortality risk using machine-learning methods in patients with coronavirus disease 2019 (COVID-19). A retrospective study of the inpatients with COVID-19 admitted from 15 January to 15 March 2020 in Wuhan is reported. The data of symptoms, comorbidity, demographic, vital sign, CT scans results and laboratory test results on admission were collected. Machine-learning methods (Random Forest and XGboost) were used to rank clinical features for mortality risk. Multivariate logistic regression models were applied to identify clinical features with statistical significance. The predictors of mortality were lactate dehydrogenase (LDH), C-reactive protein (CRP) and age based on 500 bootstrapped samples. A multivariate logistic regression model was formed to predict mortality 292 in-sample patients with area under the receiver operating characteristics (AUROC) of 0.9521, which was better than CURB-65 (AUROC of 0.8501) and the machine-learning-based model (AUROC of 0.4530). An out-sample data set of 13 patients was further tested to show our model (AUROC of 0.6061) was also better than CURB-65 (AUROC of 0.4608) and the machine-learning-based model (AUROC of 0.2292). LDH, CRP and age can be used to identify severe patients with COVID-19 on hospital admission.
| S-EPMC7426607 | biostudies-literature
Project description:Coronavirus disease 2019 (COVID-19) is a novel disease resulting from infection with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), which has quickly risen since the beginning of 2020 to become a global pandemic. As a result of the rapid growth of COVID-19, hospitals are tasked with managing an increasing volume of these cases with neither a known effective therapy, an existing vaccine, nor well-established guidelines for clinical management. The need for actionable knowledge amidst the COVID-19 pandemic is dire and yet, given the urgency of this illness and the speed with which the healthcare workforce must devise useful policies for its management, there is insufficient time to await the conclusions of detailed, controlled, prospective clinical research. Thus, we present a retrospective study evaluating laboratory data and mortality from patients with positive RT-PCR assay results for SARS-CoV-2. The objective of this study is to identify prognostic serum biomarkers in patients at greatest risk of mortality. To this end, we develop a machine learning model using five serum chemistry laboratory parameters (c-reactive protein, blood urea nitrogen, serum calcium, serum albumin, and lactic acid) from 398 patients (43 expired and 355 non-expired) for the prediction of death up to 48?h prior to patient expiration. The resulting support vector machine model achieved 91% sensitivity and 91% specificity (AUC 0.93) for predicting patient expiration status on held-out testing data. Finally, we examine the impact of each feature and feature combination in light of different model predictions, highlighting important patterns of laboratory values that impact outcomes in SARS-CoV-2 infection.
| S-EPMC7567420 | biostudies-literature
Project description:ImportanceCoronavirus disease 2019 (COVID-19) has resulted in considerable morbidity and mortality worldwide since December 2019. However, information on cardiac injury in patients affected by COVID-19 is limited.ObjectiveTo explore the association between cardiac injury and mortality in patients with COVID-19.Design, setting, and participantsThis cohort study was conducted from January 20, 2020, to February 10, 2020, in a single center at Renmin Hospital of Wuhan University, Wuhan, China; the final date of follow-up was February 15, 2020. All consecutive inpatients with laboratory-confirmed COVID-19 were included in this study.Main outcomes and measuresClinical laboratory, radiological, and treatment data were collected and analyzed. Outcomes of patients with and without cardiac injury were compared. The association between cardiac injury and mortality was analyzed.ResultsA total of 416 hospitalized patients with COVID-19 were included in the final analysis; the median age was 64 years (range, 21-95 years), and 211 (50.7%) were female. Common symptoms included fever (334 patients [80.3%]), cough (144 [34.6%]), and shortness of breath (117 [28.1%]). A total of 82 patients (19.7%) had cardiac injury, and compared with patients without cardiac injury, these patients were older (median [range] age, 74 [34-95] vs 60 [21-90] years; P < .001); had more comorbidities (eg, hypertension in 49 of 82 [59.8%] vs 78 of 334 [23.4%]; P < .001); had higher leukocyte counts (median [interquartile range (IQR)], 9400 [6900-13 800] vs 5500 [4200-7400] cells/μL) and levels of C-reactive protein (median [IQR], 10.2 [6.4-17.0] vs 3.7 [1.0-7.3] mg/dL), procalcitonin (median [IQR], 0.27 [0.10-1.22] vs 0.06 [0.03-0.10] ng/mL), creatinine kinase-myocardial band (median [IQR], 3.2 [1.8-6.2] vs 0.9 [0.6-1.3] ng/mL), myohemoglobin (median [IQR], 128 [68-305] vs 39 [27-65] μg/L), high-sensitivity troponin I (median [IQR], 0.19 [0.08-1.12] vs <0.006 [<0.006-0.009] μg/L), N-terminal pro-B-type natriuretic peptide (median [IQR], 1689 [698-3327] vs 139 [51-335] pg/mL), aspartate aminotransferase (median [IQR], 40 [27-60] vs 29 [21-40] U/L), and creatinine (median [IQR], 1.15 [0.72-1.92] vs 0.64 [0.54-0.78] mg/dL); and had a higher proportion of multiple mottling and ground-glass opacity in radiographic findings (53 of 82 patients [64.6%] vs 15 of 334 patients [4.5%]). Greater proportions of patients with cardiac injury required noninvasive mechanical ventilation (38 of 82 [46.3%] vs 13 of 334 [3.9%]; P < .001) or invasive mechanical ventilation (18 of 82 [22.0%] vs 14 of 334 [4.2%]; P < .001) than those without cardiac injury. Complications were more common in patients with cardiac injury than those without cardiac injury and included acute respiratory distress syndrome (48 of 82 [58.5%] vs 49 of 334 [14.7%]; P < .001), acute kidney injury (7 of 82 [8.5%] vs 1 of 334 [0.3%]; P < .001), electrolyte disturbances (13 of 82 [15.9%] vs 17 of 334 [5.1%]; P = .003), hypoproteinemia (11 of 82 [13.4%] vs 16 of 334 [4.8%]; P = .01), and coagulation disorders (6 of 82 [7.3%] vs 6 of 334 [1.8%]; P = .02). Patients with cardiac injury had higher mortality than those without cardiac injury (42 of 82 [51.2%] vs 15 of 334 [4.5%]; P < .001). In a Cox regression model, patients with vs those without cardiac injury were at a higher risk of death, both during the time from symptom onset (hazard ratio, 4.26 [95% CI, 1.92-9.49]) and from admission to end point (hazard ratio, 3.41 [95% CI, 1.62-7.16]).Conclusions and relevanceCardiac injury is a common condition among hospitalized patients with COVID-19 in Wuhan, China, and it is associated with higher risk of in-hospital mortality.
| S-EPMC7097841 | biostudies-literature