Development and internal validation of a diagnostic prediction model for COVID-19 at time of admission to hospital

Fink, Douglas; Khan, Palwasha; Goldman, Nina; Cai, James; Hone, L.; Mooney, Ciaran; El-Shakankery, Karim; Sismey, George E.; Whitford,; Marks, Michael

doi:10.1093/qjmed/hcaa305

Cited by 15 publications

(16 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As mentioned in [ 10 ], it can also be noted that the collected variables were sometimes country-specific and cannot be obtained if the model is to be put into use in a setting other than the research context. They are studies from Vieceli et al [ 12 ], Tordjman et al [ 13 ], Kurstjens et al [ 14 ], Aldobyany et al [ 15 ], Nakakubo et al [ 16 ] and Fink et al [ 17 ] and are presented in detail in the Additional file 1 : Appendix A1. For most of them, a score and cut-off values could be obtained but a binary logistic regression was only available for three studies [ 12 , 13 , 17 ].…”

Section: Methodsmentioning

confidence: 99%

Clinical prediction models for diagnosis of COVID-19 among adult patients: a validation and agreement study

et al. 2022

View full text Add to dashboard Cite

Background Since the beginning of the pandemic, hospitals have been constantly overcrowded, with several observed waves of infected cases and hospitalisations. To avoid as much as possible this situation, efficient tools to facilitate the diagnosis of COVID-19 are needed. Objective To evaluate and compare prediction models to diagnose COVID-19 identified in a systematic review published recently using performance indicators such as discrimination and calibration measures. Methods A total of 1618 adult patients present at two Emergency Department triage centers and for whom qRT-PCR tests had been performed were included in this study. Six previously published models were reconstructed and assessed using diagnostic tests as sensitivity (Se) and negative predictive value (NPV), discrimination (Area Under the Roc Curve (AUROC)) and calibration measures. Agreement was also measured between them using Kappa’s coefficient and IntraClass Correlation Coefficient (ICC). A sensitivity analysis has been conducted by waves of patients. Results Among the 6 selected models, those based only on symptoms and/or risk exposure were found to be less efficient than those based on biological parameters and/or radiological examination with smallest AUROC values (< 0.80). However, all models showed good calibration and values above > 0.75 for Se and NPV but poor agreement (Kappa and ICC < 0.5) between them. The results of the first wave were similar to those of the second wave. Conclusion Although quite acceptable and similar results were found between all models, the importance of radiological examination was also emphasized, making it difficult to find an appropriate triage system to classify patients at risk for COVID-19.

show abstract

Section: Methodsmentioning

confidence: 99%

Clinical prediction models for diagnosis of COVID-19 among adult patients: a validation and agreement study

et al. 2022

View full text Add to dashboard Cite

show abstract

“…For example, LR was applied in ( Roland et al, 2020 ; Shang et al, 2020 ; Song et al, 2020 ) to predict the severity of COVID-19 in infected patients. Also LR based system was proposed in ( Fink et al, 2020 ) for validation of the results of COVID-19 diagnostic prediction at the time of admission in the hospital.…”

Section: Literature Reviewmentioning

confidence: 99%

Application of intelligence-based computational techniques for classification and early differential diagnosis of COVID-19 disease

Akinnuwesi

Fashoto

Mbunge

et al. 2021

Data Science and Management

View full text Add to dashboard Cite

Clinical methods are used for diagnosing COVID-19 infected patients, but reports posit that, several people who were initially tested positive of COVID-19, and who had some underlying diseases, turned out having negative results, after further tests. Therefore, the performance of clinical methods is not always guaranteed. Moreover, chest X-ray image data of COVID-19 infected patients are mostly used in the computational models for COVI-19 diagnosis while the use of common symptoms such as “ Fever, Cough, Fatigue, Muscle aches, Headache etc ”, in computational models is not yet reported. In this study, we employ seven classification algorithms to empirically test and verify their efficacy when applied to diagnose COVID-19 using the aforementioned symptoms. We experimented with logistic regression (LR), support vector machine (SVM), naïve Byes (NB), decision tree (DT), multilayer perceptron (MLP), fuzzy cognitive map (FCM) and Deep neural network (DNN) algorithms. The techniques were subjected to random under-sampling and over-sampling. Our results showed that with class imbalance, MLP and DNN outperform others but without class imbalance MLP, FCM and DNN outperform others with the use of random under-sampling but DNN has the best performance with the use random oversampling. This study identified MLP, FCM and DNN as better classifiers over LR, NB, DT and SVM, that healthcare software system developers can adopt to develop intelligence-based expert systems which both medical personnel and patients can use for differential diagnosis of COVID-19 based on the aforementioned symptoms however, the test of performance must not be limited to the traditional performance metrics.

show abstract

“…Even near-patient, rapid RT-PCR platforms with assay run times of 1-2 hours can be quickly overwhelmed, especially during peaks of COVID-19 incidence [11,12]. Multivariable diagnostic risk models, including clinical criteria and thoracic imaging, are not sufficient, but may be useful as a triage test to ration expensive or scarce point-of care assays [13,14].…”

Section: Introductionmentioning

confidence: 99%

Use of the FebriDx point-of-care assay as part of a triage algorithm for medical admissions with possible COVID-19

Houston

Gupta-Wright

Deas

et al. 2021

Preprint

View full text Add to dashboard Cite

BackgroundPatients admitted to hospital with COVID-19 need rapid identification and isolation to prevent nosocomial transmission. However, isolation facilities are often limited, and SARS-CoV-2 RT-PCR results are often not available when discharged from the emergency department. We evaluated a triage algorithm to isolate patients with suspected COVID-19 using simple clinical criteria and the FebriDx assay.DesignRetrospective observational cohortSettingLarge acute care hospital in London, UKParticipantsAll medical admissions from the ED between 10th August 2020 and 4th November 2020 with valid SARS-CoV-2 RT-PCR.InterventionsMedical admissions were triaged as likely, possible or unlikely COVID-19 based on clinical criteria. Patients triaged as possible COVID-19 underwent FebriDx lateral flow assay on capillary blood, and those positive for MxA were managed as likely COVID-19.Primary Outcome measuresDiagnostic accuracy (sensitivity, specificity and predictive values) of the algorithm and the FebriDx assay compared to SARS-CoV-2 RT-PCR from nasopharyngeal swabs as the reference standard.Results4.0% (136/3,443) of medical admissions had RT-PCR confirmed COVID-19. Prevalence of COVID-19 was 45.7% (80/175) in those triaged as likely, 4.1% (50/1,225) in possible and 0.3% (6/2,033) in unlikely COVID-19. Compared to SARS-CoV-2 RT-PCR, clinical triage had sensitivity of 95.6% (95%CI: 90.5% - 98.0%) and specificity of 61.5% (95%CI: 59.8% - 63.1%), whilst the triage algorithm including FebriDx had sensitivity of 92.6% (95%CI: 86.8% - 96.0%) and specificity of 86.4% (95%CI: 85.2% - 87.5%). The triage algorithm reduced the need for 2,859 patients to be admitted to isolation rooms. Ten patients missed by the algorithm had mild or asymptomatic COVID-19.ConclusionsA triage algorithm including FebriDx assay had good sensitivity and was useful to ‘rule-out’ COVID-19 among medical admissions to hospital.STRENGTHS AND LIMITATIONS OF THIS STUDYPragmatic study including a large cohort of consecutive medical admissions providing routine clinical care.A single SARS-CoV-2 RT-PCR is an imperfect reference standard for COVID-19. Multiple RT-PCR platforms used, with different PCR targets and performance.A higher prevalence of COVID-19 or other respiratory pathogens might alter performance.Criteria for likely and possible COVID-19 groups changed subtly during the study period.

show abstract

Development and internal validation of a diagnostic prediction model for COVID-19 at time of admission to hospital

Cited by 15 publications

References 22 publications

Clinical prediction models for diagnosis of COVID-19 among adult patients: a validation and agreement study

Clinical prediction models for diagnosis of COVID-19 among adult patients: a validation and agreement study

Application of intelligence-based computational techniques for classification and early differential diagnosis of COVID-19 disease

Use of the FebriDx point-of-care assay as part of a triage algorithm for medical admissions with possible COVID-19

Contact Info

Product

Resources

About