External validation of a prediction model for CPAP failure in COVID-19 patients with severe pneumonitis.
Ontology highlight
ABSTRACT:
SUBMITTER: Stokes V
PROVIDER: S-EPMC9513984 | biostudies-literature | 2022 Sep
REPOSITORIES: biostudies-literature
Publications
External validation of a prediction model for CPAP failure in COVID-19 patients with severe pneumonitis.
Stokes Victoria V Goh Kwee Yen KY Whiting Graham G Bates Sebastian S Greenlee Hannah H Wilson Anthony A Parker Alexander J AJ
Critical care (London, England) 20220927 1
Similar Datasets
Project description:BackgroundIonized hypocalcemia is common in critically ill patients with COVID-19 and is associated with adverse outcomes. We previously developed a linear model that estimates ionized calcium (ICa) by adjusting total calcium (TCa) for the three components of the anion gap and albumin. On internal validation, it outperformed the popular method that corrects TCa for albumin alone (cTCa) in diagnosing low ICa. In this study, we sought to externally validate our ICa model in hospitalized COVID-19 positive patients.MethodsWe retrospectively studied all 200 patients with COVID-19 who were admitted to the State University of New York Downstate Medical Center between March 11th and April 30th 2020 and referred to the nephrology service for renal failure, and who had ICa measured on a venous blood gas within 25 min of a comprehensive metabolic panel. We compared the performance of the ICa model and cTCa in diagnosing low ICa by ROC analysis, and also examined the accuracy of the absolute values predicted by the two methods relative to measured ICa.ResultsOn ROC analysis, the ICa model was better than cTCa (area under ROC curve: 0.872 [0.025] vs. 0.835 [0.028]; p = 0.045). The ICa model estimated ICa accurately, but the cTCa method seemed to overcorrect TCa, as a substantial number of patients with clearly normal cTCa values had low ICa.ConclusionsIn an external validation cohort, the ICa model estimated ICa accurately and was better than cTCa in the diagnosis of low ICa. This finding can be useful in guiding direct ICa testing.
| S-EPMC8864233 | biostudies-literature
Project description: Not available
| S-EPMC7668008 | biostudies-literature
Project description:ObjectivesCOVID-19 pandemic seems to be under control. However, despite the vaccines, 5 to 10% of the patients with mild disease develop moderate to critical forms with potential lethal evolution. In addition to assess lung infection spread, chest CT helps to detect complications. Developing a prediction model to identify at-risk patients of worsening from mild COVID-19 combining simple clinical and biological parameters with qualitative or quantitative data using CT would be relevant to organizing optimal patient management.MethodsFour French hospitals were used for model training and internal validation. External validation was conducted in two independent hospitals. We used easy-to-obtain clinical (age, gender, smoking, symptoms' onset, cardiovascular comorbidities, diabetes, chronic respiratory diseases, immunosuppression) and biological parameters (lymphocytes, CRP) with qualitative or quantitative data (including radiomics) from the initial CT in mild COVID-19 patients.ResultsQualitative CT scan with clinical and biological parameters can predict which patients with an initial mild presentation would develop a moderate to critical form of COVID-19, with a c-index of 0.70 (95% CI 0.63; 0.77). CT scan quantification improved the performance of the prediction up to 0.73 (95% CI 0.67; 0.79) and radiomics up to 0.77 (95% CI 0.71; 0.83). Results were similar in both validation cohorts, considering CT scans with or without injection.ConclusionAdding CT scan quantification or radiomics to simple clinical and biological parameters can better predict which patients with an initial mild COVID-19 would worsen than qualitative analyses alone. This tool could help to the fair use of healthcare resources and to screen patients for potential new drugs to prevent a pejorative evolution of COVID-19.Clinical trial registrationNCT04481620.Clinical relevance statementCT scan quantification or radiomics analysis is superior to qualitative analysis, when used with simple clinical and biological parameters, to determine which patients with an initial mild presentation of COVID-19 would worsen to a moderate to critical form.Key points• Qualitative CT scan analyses with simple clinical and biological parameters can predict which patients with an initial mild COVID-19 and respiratory symptoms would worsen with a c-index of 0.70. • Adding CT scan quantification improves the performance of the clinical prediction model to an AUC of 0.73. • Radiomics analyses slightly improve the performance of the model to a c-index of 0.77.
| S-EPMC10667132 | biostudies-literature
Project description:Objectives backgroundTo externally validate clinical prediction models that aim to predict progression to invasive ventilation or death on the ICU in patients admitted with confirmed COVID-19 pneumonitis.DesignSingle-center retrospective external validation study.Data sourcesRoutinely collected healthcare data in the ICU electronic patient record. Curated data recorded for each ICU admission for the purposes of the U.K. Intensive Care National Audit and Research Centre (ICNARC).SettingThe ICU at Manchester Royal Infirmary, Manchester, United Kingdom.PatientsThree hundred forty-nine patients admitted to ICU with confirmed COVID-19 Pneumonitis, older than 18 years, from March 1, 2020, to February 28, 2022. Three hundred two met the inclusion criteria for at least one model. Fifty-five of the 349 patients were admitted before the widespread adoption of dexamethasone for the treatment of severe COVID-19 (pre-dexamethasone patients).OutcomesAbility to be externally validated, discriminate, and calibrate.MethodsArticles meeting the inclusion criteria were identified, and those that gave sufficient details on predictors used and methods to generate predictions were tested in our cohort of patients, which matched the original publications' inclusion/exclusion criteria and endpoint.ResultsThirteen clinical prediction articles were identified. There was insufficient information available to validate models in five of the articles; a further three contained predictors that were not routinely measured in our ICU cohort and were not validated; three had performance that was substantially lower than previously published (range C-statistic = 0.483-0.605 in pre-dexamethasone patients and C = 0.494-0.564 among all patients). One model retained its discriminative ability in our cohort compared with previously published results (C = 0.672 and 0.686), and one retained performance among pre-dexamethasone patients but was poor in all patients (C = 0.793 and 0.596). One model could be calibrated but with poor performance.ConclusionsOur findings, albeit from a single center, suggest that the published performance of COVID-19 prediction models may not be replicated when translated to other institutions. In light of this, we would encourage bedside intensivists to reflect on the role of clinical prediction models in their own clinical decision-making.
| S-EPMC10977519 | biostudies-literature
Project description:BackgroundCoronavirus disease 2019 (COVID-19) carries high morbidity and mortality globally. Identification of patients at risk for clinical deterioration upon presentation would aid in triaging, prognostication, and allocation of resources and experimental treatments.Research questionCan we develop and validate a web-based risk prediction model for identification of patients who may develop severe COVID-19, defined as intensive care unit (ICU) admission, mechanical ventilation, and/or death?MethodsThis retrospective cohort study reviewed 415 patients admitted to a large urban academic medical center and community hospitals. Covariates included demographic, clinical, and laboratory data. The independent association of predictors with severe COVID-19 was determined using multivariable logistic regression. A derivation cohort (n=311, 75%) was used to develop the prediction models. The models were tested by a validation cohort (n=104, 25%).ResultsThe median age was 66 years (Interquartile range [IQR] 54-77) and the majority were male (55%) and non-White (65.8%). The 14-day severe COVID-19 rate was 39.3%; 31.7% required ICU, 24.6% mechanical ventilation, and 21.2% died. Machine learning algorithms and clinical judgment were used to improve model performance and clinical utility, resulting in the selection of eight predictors: age, sex, dyspnea, diabetes mellitus, troponin, C-reactive protein, D-dimer, and aspartate aminotransferase. The discriminative ability was excellent for both the severe COVID-19 (training area under the curve [AUC]=0.82, validation AUC=0.82) and mortality (training AUC= 0.85, validation AUC=0.81) models. These models were incorporated into a mobile-friendly website.ConclusionsThis web-based risk prediction model can be used at the bedside for prediction of severe COVID-19 using data mostly available at the time of presentation.
| S-EPMC8141270 | biostudies-literature
Project description:Multiple prediction models for risk of in-hospital mortality from COVID-19 have been developed, but not applied, to patient cohorts different to those from which they were derived. The MEDLINE, EMBASE, Scopus, and Web of Science (WOS) databases were searched. Risk of bias and applicability were assessed with PROBAST. Nomograms, whose variables were available in a well-defined cohort of 444 patients from our site, were externally validated. Overall, 71 studies, which derived a clinical prediction rule for mortality outcome from COVID-19, were identified. Predictive variables consisted of combinations of patients' age, chronic conditions, dyspnea/taquipnea, radiographic chest alteration, and analytical values (LDH, CRP, lymphocytes, D-dimer); and markers of respiratory, renal, liver, and myocardial damage, which were mayor predictors in several nomograms. Twenty-five models could be externally validated. Areas under receiver operator curve (AUROC) in predicting mortality ranged from 0.71 to 1 in derivation cohorts; C-index values ranged from 0.823 to 0.970. Overall, 37/71 models provided very-good-to-outstanding test performance. Externally validated nomograms provided lower predictive performances for mortality in their respective derivation cohorts, with the AUROC being 0.654 to 0.806 (poor to acceptable performance). We can conclude that available nomograms were limited in predicting mortality when applied to different populations from which they were derived.
| S-EPMC9599062 | biostudies-literature
Project description: Not available
| S-EPMC9010282 | biostudies-literature
Project description:(1) Background: the aim of this study was to create a score to predict the incidence of CPAP failure in COVID-19 patients early. (2) Methods: in this retrospective observational study, we included all consecutive adult patients admitted between February and April 2021. The main outcome was the failure of CPAP support (intubation or death). (3) Results: two-hundred and sixty-three COVID-19 patients were managed with CPAP. The population was divided in short-CPAP (CPAP days ≤ 10; 72.6%) and long-CPAP (>10; 27.4%) groups. After balancing the entire population using a stabilized IPTW method, we applied a multivariable logistic regression analysis to identify the risk factors for CPAP failure. We used the identified covariates to create a mathematical model, the CPAP Failure Score (CPAP-FS). The multivariable logistic regression analysis identified four variables: SpO2 (OR = 0.86; p-value = 0.001), P/F ratio (OR = 0.99; p-value = 0.008), the Call Score (OR = 1.44; p-value = 0.02), and a pre-existing chronic lung disease (OR = 3.08; p-value = 0.057). The beta-coefficients obtained were used to develop the CPAP-FS, whose diagnostic ability outperformed other relevant COVID-19-related parameters (AUC = 0.87; p-value < 0.0001). We validated the CPAP-FS using a 10-fold internal cross-validation method which confirmed the observed results (AUCs 0.76-0.80; p-values < 0.0001). (4) Conclusions: the CPAP-FS can early identify COVID-19 patients who are at risk of CPAP failure.
| S-EPMC9104739 | biostudies-literature
Project description:BackgroundPredicting early respiratory failure due to COVID-19 can help triage patients to higher levels of care, allocate scarce resources, and reduce morbidity and mortality by appropriately monitoring and treating the patients at greatest risk for deterioration. Given the complexity of COVID-19, machine learning approaches may support clinical decision making for patients with this disease.ObjectiveOur objective is to derive a machine learning model that predicts respiratory failure within 48 hours of admission based on data from the emergency department.MethodsData were collected from patients with COVID-19 who were admitted to Northwell Health acute care hospitals and were discharged, died, or spent a minimum of 48 hours in the hospital between March 1 and May 11, 2020. Of 11,525 patients, 933 (8.1%) were placed on invasive mechanical ventilation within 48 hours of admission. Variables used by the models included clinical and laboratory data commonly collected in the emergency department. We trained and validated three predictive models (two based on XGBoost and one that used logistic regression) using cross-hospital validation. We compared model performance among all three models as well as an established early warning score (Modified Early Warning Score) using receiver operating characteristic curves, precision-recall curves, and other metrics.ResultsThe XGBoost model had the highest mean accuracy (0.919; area under the curve=0.77), outperforming the other two models as well as the Modified Early Warning Score. Important predictor variables included the type of oxygen delivery used in the emergency department, patient age, Emergency Severity Index level, respiratory rate, serum lactate, and demographic characteristics.ConclusionsThe XGBoost model had high predictive accuracy, outperforming other early warning scores. The clinical plausibility and predictive ability of XGBoost suggest that the model could be used to predict 48-hour respiratory failure in admitted patients with COVID-19.
| S-EPMC7879728 | biostudies-literature
Project description:BackgroundContinuous positive airway pressure (CPAP) has been increasingly deployed to manage patients with COVID-19 and acute respiratory failure, often for protracted periods. However, concerns about protracted CPAP have been raised. This study aimed to examine the use of CPAP for patients with COVID-19 and the outcomes after protracted use.MethodsThis was a national cohort study of all adults admitted to Scottish critical care units with COVID-19 from March 1, 2020 to December 25, 2021 who received CPAP. Protracted CPAP was defined as ≥ 5 continuous days of CPAP. Outcomes included CPAP failure rate (institution of invasive mechanical ventilation [IMV] or death), mortality, and outcomes after institution of IMV. Multivariable logistic regression was performed to assess the impact of protracted CPAP on mortality after IMV.ResultsA total of 1961 patients with COVID-19 received CPAP for COVID-19 pneumonitis, with 733 patients (37.4%) receiving protracted CPAP. CPAP failure occurred in 891 (45.4%): 544 patients (27.7%) received IMV and 347 patients (17.7%) died in critical care without IMV. Hospital mortality rate was 41.3% for the population. For patients who subsequently commenced IMV, hospital mortality was 58.7% for the standard duration CPAP group and 73.9% for the protracted duration CPAP group (P=0.003); however, there was no statistical difference in hospital mortality after adjustment for confounders (odds ratio 1.4, 95% confidence interval 0.84-2.33, P=0.195).ConclusionsProtracted CPAP was used frequently for managing patients with COVID-19. Whilst it was not associated with worse outcomes for those patients who subsequently required IMV, this might be due to residual confounding and differences in processes of care.
| S-EPMC10209449 | biostudies-literature