Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Oct 2, 2020
Open Peer Review Period: Oct 2, 2020 - Nov 27, 2020
Date Accepted: Nov 2, 2020
Date Submitted to PubMed: Dec 10, 2020
(closed for review but you can still tweet)
Ruling In and Ruling Out COVID-19: Computing SARS-CoV-2 Infection Risk From Symptoms, Imaging and Test Data.
ABSTRACT
Background:
Assigning meaningful probabilities of SARS CoV2 infection risk presents a diagnostic challenge across the continuum of care.
Objective:
Given the cognitive challenges of integrating local base-rate, symptoms and clinical test results into an accurate risk assessment for a given patient, we sought to develop and clinically validate an adaptable, personalized diagnostic model to assist providers to rule-in or rule-out SARS-CoV-2 in well and poorly resourced settings.
Methods:
We integrated prevalence, symptom and test data using machine learning and Bayesian inference to develop models that quantify individual patient risk of SARS CoV 2 infection. We trained models with 100,000 simulated patient profiles based on thirteen symptoms, estimated local prevalence, imaging, and molecular diagnostic performance from published reports. We tested these models in a clinical setting with consecutive patients who presented with a COVID 19 compatible illness at the University of California San Diego Medical Center over 14 days starting in March 2020.
Results:
We included 55 consecutive patients with fever (78%) or cough (77%) presenting for ambulatory (n=11) or hospital care (n=44). 51% (n=28) were female, 49% were age <60. Common comorbidities included diabetes (22%), hypertension (27%), cancer (16%) and cardiovascular disease (13%). 69% of these (n=38) were RT-PCR confirmed positive for SARS CoV2 infection, 11 had repeated negative nucleic acid testing and an alternate diagnosis. Bayesian inference network, distance metric learning, and ensemble models discriminated between patients with SARS CoV2 infection and alternate diagnoses with sensitivities of 81.6 to 84.2%, specificities of 58.8 to 70.6%, and accuracies of 61.4 to 71.8%. After integrating imaging and laboratory test statistics with the predictions of the Bayesian inference network, changes in diagnostic uncertainty at each step in the simulated clinical evaluation process were highly sensitive to location, symptom, and diagnostic test choices.
Conclusions:
Decision support models that incorporate symptoms and available test results can help providers diagnose SARS CoV2 infection in real world settings.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.