A rapid screening classifier for diagnosing COVID-19

Yang, Xia; Chen, Weixiang; Ren, Hongyi; Zhao, Jianping; Wang, Lihua; Jin, Rui; Zhou, Jia; Wang, Qiyuan; Yan, Fugui; Zhang, Bin; Lou, Jian; Wang, Shaobin; Li, Yongming; Zhou, Jie; Xia, Liming; Cheng, Jin; Feng, Jianjiang; Li, Wen; Shen, Huahao

doi:10.7150/ijbs.53982

Cited by 17 publications

(34 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have been complex attempts to better predict the presence of COVID-19 by creating artificial intelligence (AI) programs which process clinical data as well as imaging techniques. Xia et al [20] describe that when considering 52 clinical and laboratory coefficients, e.g., disseminated intravascular coagulation, d-dimer, procalcitonin, enlarged lymph nodes or rhabdomyolysis together with CXR features, sensitivity increased to 94% and specificity to 75%. However, the complex information required is hardly available in the setting of an ER before deciding whether a possible COVID-19 patient should be hospitalized or not.…”

Section: Discussionmentioning

confidence: 99%

Point-of-care COVID-19 antigen testing in German emergency rooms – a cost-benefit analysis

Diel

Nienhaus

2022

Pulmonology

View full text Add to dashboard Cite

Background The current COVID-19 pandemic is causing significant morbidity and death worldwide and produces significant socio-economic losses. Objective To assess the cost–benefit relation of implementing point-of-care COVID-19 antigen testing (POCT) in emergency rooms (ER) of German hospitals. Methods A deterministic decision-analytic model simulated the incremental costs of using the Sofia® SARS Antigen FIA test compared to those of using clinical judgement alone to confirm or exclude COVID-19 in adult patients in German ER, prior to hospitalization. Direct and indirect costs, with and without subsequent RT-PCR confirmation, were evaluated from the hospital perspective. Results With respect to ER patients, in base-case analysis, considering a COVID- 19 prevalence of 15.6% and a hospitalization rate among COVID-19 suspects of 10.1%, POCT testing reduces average costs of hospitalized patients by €213 per tested patient if nasopharyngeal swabs of patients suspected to have COVID-19 are also sent to external labs for RT-PCR testing. In probabilistic sensitivity analysis, under all reasonable assumptions, implementing the Sofia® SARS Antigen FIA saves on average about €210 as compared to applying the clinical-judgement-only strategy. The major part of cost savings, €159 or 75.9%, is due to the POC test´s high specificity resulting in a 21-fold lower proportion of unnecessary bed blocking at the first day of hospitalization. Conclusions Using highly specific rapid COVID-19 tests in COVID-19 suspects at German ER, despite of their sub-optimal sensitivity, may significantly reduce hospital expenditure.

show abstract

Section: Discussionmentioning

confidence: 99%

Point-of-care COVID-19 antigen testing in German emergency rooms – a cost-benefit analysis

Diel

Nienhaus

2022

Pulmonology

View full text Add to dashboard Cite

show abstract

“…Most literature studies use AI in CXR to distinguish between COVID-19 and other pneumonia and healthy patients [53][54][55]. Xia et al described the use of a rapid and economic classifier for screening of COVID-19 from influenza-A/B pneumonia which combined CXR (or CT-localizer scanogram) data with clinical features, with 91.5% sensitivity and 81.2% specificity and an AUC of 0.971 (95% CI 0.964-0.980) [56].…”

Section: Artificial Intelligence In Chest X-raymentioning

confidence: 99%

The Applications of Artificial Intelligence in Chest Imaging of COVID-19 Patients: A Literature Review

et al. 2021

View full text Add to dashboard Cite

Diagnostic imaging is regarded as fundamental in the clinical work-up of patients with a suspected or confirmed COVID-19 infection. Recent progress has been made in diagnostic imaging with the integration of artificial intelligence (AI) and machine learning (ML) algorisms leading to an increase in the accuracy of exam interpretation and to the extraction of prognostic information useful in the decision-making process. Considering the ever expanding imaging data generated amid this pandemic, COVID-19 has catalyzed the rapid expansion in the application of AI to combat disease. In this context, many recent studies have explored the role of AI in each of the presumed applications for COVID-19 infection chest imaging, suggesting that implementing AI applications for chest imaging can be a great asset for fast and precise disease screening, identification and characterization. However, various biases should be overcome in the development of further ML-based algorithms to give them sufficient robustness and reproducibility for their integration into clinical practice. As a result, in this literature review, we will focus on the application of AI in chest imaging, in particular, deep learning, radiomics and advanced imaging as quantitative CT.

show abstract

“…Previous studies on influenza diagnosis using AI remain few. Xia et al reported an AI-based classifier distinguishing influenza from COVID-19 using chest X-ray images and clinical features with an AUC of 0.9 [ 17 ]. Choo et al reported the usefulness of the patient-generated health data obtained from a mobile health application to develop an AI-based screening tool for influenza [ 18 ].…”

Section: Discussionmentioning

confidence: 99%

Relationship Between Medical Questionnaire and Influenza Rapid Test Positivity: Subjective Pretest Probability, “I Think I Have Influenza,” Contributes to the Positivity Rate

Katsuki¹,

Matsuo²

2021

Cureus

View full text Add to dashboard Cite

IntroductionRapid influenza diagnostic tests (RIDTs) are considered essential for determining when to start influenza treatment using anti-influenza drugs, but their accuracy is about 70%. Under the COVID-19 pandemic, we hope to refrain from performing unnecessary RIDTs considering droplet infection of COVID-19 and influenza. We re-examined the medical questionnaire's importance and its relationship to the positivity of RIDTs. Then we built a positivity prediction model for RIDTs using automated artificial intelligence (AI). MethodsWe retrospectively investigated 96 patients who underwent RIDTs at the outpatient department from December 2019 to March 2020. We used a questionnaire sheet with 24 items before conducting RIDTs. The factors associated with the positivity of RIDTs were statistically analyzed. We then used an automated AI framework to produce the positivity prediction model using the 24 items, sex, and age, with five-fold crossvalidation. ResultsOf the 47 women and 49 men (median age was 39 years), 56 patients were RIDT positive with influenza A. The AI-based model using 26 variables had an area under the curve (AUC) of 0.980. The stronger variables are subjective pretest probability, which is a numerically described score ranging from 0% to 100% of "I think I have influenza," cough, past hours after the onset, muscle pain, and maximum body temperature in order. ConclusionWe easily built the RIDT positivity prediction model using automated AI. Its AUC was satisfactory, and it suggested the importance of a detailed medical interview. Both the univariate analysis and AI-based model suggested that subjective pretest probability, "I think I have influenza," might be useful.

show abstract

A rapid screening classifier for diagnosing COVID-19

Cited by 17 publications

References 48 publications

Point-of-care COVID-19 antigen testing in German emergency rooms – a cost-benefit analysis

Point-of-care COVID-19 antigen testing in German emergency rooms – a cost-benefit analysis

The Applications of Artificial Intelligence in Chest Imaging of COVID-19 Patients: A Literature Review

Relationship Between Medical Questionnaire and Influenza Rapid Test Positivity: Subjective Pretest Probability, “I Think I Have Influenza,” Contributes to the Positivity Rate

Contact Info

Product

Resources

About