The Youden Index in the Generalized Receiver Operating Characteristic Curve Context

Martínez–Camblor, Pablo; Pardo–Fernández, Juan Carlos

doi:10.1515/ijb-2018-0060

Cited by 86 publications

(55 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compared the classification performance using several metrics, such as accuracy, sensitivity, specificity, area under the curve (AUC), positive predictive value (PPV), negative predictive value (NPV), F1 score, and Youden index [ 18 , 19 ]. TP and TN represent the number of true-positive and true-negative samples, respectively.…”

Section: Methodsmentioning

confidence: 99%

A deep learning algorithm using CT images to screen for Corona virus disease (COVID-19)

et al. 2021

View full text Add to dashboard Cite

Objective The outbreak of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-COV-2) has caused more than 26 million cases of Corona virus disease (COVID-19) in the world so far. To control the spread of the disease, screening large numbers of suspected cases for appropriate quarantine and treatment are a priority. Pathogenic laboratory testing is typically the gold standard, but it bears the burden of significant false negativity, adding to the urgent need of alternative diagnostic methods to combat the disease. Based on COVID-19 radiographic changes in CT images, this study hypothesized that artificial intelligence methods might be able to extract specific graphical features of COVID-19 and provide a clinical diagnosis ahead of the pathogenic test, thus saving critical time for disease control. Methods We collected 1065 CT images of pathogen-confirmed COVID-19 cases along with those previously diagnosed with typical viral pneumonia. We modified the inception transfer-learning model to establish the algorithm, followed by internal and external validation. Results The internal validation achieved a total accuracy of 89.5% with a specificity of 0.88 and sensitivity of 0.87. The external testing dataset showed a total accuracy of 79.3% with a specificity of 0.83 and sensitivity of 0.67. In addition, in 54 COVID-19 images, the first two nucleic acid test results were negative, and 46 were predicted as COVID-19 positive by the algorithm, with an accuracy of 85.2%. Conclusion These results demonstrate the proof-of-principle for using artificial intelligence to extract radiological features for timely and accurate COVID-19 diagnosis. Key Points • The study evaluated the diagnostic performance of a deep learning algorithm using CT images to screen for COVID-19 during the influenza season. • As a screening method, our model achieved a relatively high sensitivity on internal and external CT image datasets. • The model was used to distinguish between COVID-19 and other typical viral pneumonia, both of which have quite similar radiologic characteristics.

show abstract

Section: Methodsmentioning

confidence: 99%

A deep learning algorithm using CT images to screen for Corona virus disease (COVID-19)

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The results showed that the differences in AUC values and speci cities between CARS and ABC were statistically signi cant (P <0.05). The false-positive rate (1-speci city) was indicative of a lower misdiagnosis rate [19]. We found that the cut-off values of CARS and ABC were 34 and 67, respectively.…”

Section: Resultsmentioning

confidence: 71%

“…Notably, ROC curves (AUCs) represent the most commonly applied global index of diagnostic accuracy. The diagnostic capacity of an assessment tool is usually not evaluated by a single number but is instead usually assessed via two or more diagnostic procedures [19]. Diagnosis is generally based on a cut-off or threshold value [20].…”

Section: Resultsmentioning

confidence: 99%

A Comparison of the Autistic Behavior Checklist and the Childhood Autism Rating Scale for Suspected Autism in a Large Chinese Sample

Chu

Bian

Yan

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Autism is the most common clinical developmental disorder in children. The Childhood Autism Rating Scale (CARS) and Autistic Behavior Checklist (ABC) are the most commonly used assessment scales for diagnosing autism. The aim of this study is to compare the diagnostic validities of CARS and ABC based on a large Chinese sample.Methods: A receiver operating characteristic (ROC) curve was used to compare the diagnostic validities of CARS and ABC, as well as the corresponding cut-off determinations was calculated.Results: A total of 474 children with suspected autism spectrum disorder (ASD) were screened by CARS and ABC. Receiver operating characteristic (ROC) curve analysis was performed and it showed that the area-under-the-curve values of CARS is higher than ABC significantly (p <0.05) and the suggested cutoff values of CARS and ABC were 34 and 67, respectively.Conclusion: This study demonstrated that CARS was superior to ABC in terms of its diagnostic validity of assessing suspected ASD cases in children. Based on our results, we recommend the CARS could be used for the assessments for suspected ASD cases in Chinses hospitals.

show abstract

“…Youden index is a method to evaluate the authenticity of the experiment. [ 38 ] The resulting value indicated that the experimental results were better and more reliable. The ROC curve visually showed the relationship between sensitivity and specificity and reflected the effectiveness of the diagnostic method.…”

Section: Discussionmentioning

confidence: 98%

Prediction and identification of CD4+ T cell epitope for the protective antigens of Mycobacterium tuberculosis

Liu

Chen

et al. 2021

Medicine

View full text Add to dashboard Cite

CD4+T cell epitopes plays a key role in anti-tuberculosis (TB) immunity, CD4+T cell epitopes suitable for the domestic population are lacking. Therefore, we predicted and identified novel CD4+T cell epitopes. The bioinformatics software, namely, DNAStar (DNASTAR of the United States), SYFPEITHI (INTERFACTORS INSTITUT Für ZELL Biologie of Germany), RANKPEP, and NetMHC IIpan (National Cancer Institute, United States of America), were used to comprehensively predict the CD4+T cell immune epitope of Mycobacterium TB, and the predicted epitope polypeptide was synthesized by the standard Fmoc scheme. The proliferation of PBMC and CD4+T cells stimulated by peptides was preliminarily detected by the CCK8 method. Then, the candidate polypeptides screened out by the CCK8 method were verified again by the BrdU assay, and flow cytometry was performed to analyze further the extent of their stimulation on the proliferation of CD4+T cells. The changes in the secreted cytokines IFN-γ, TNF-α, IL-2, and IL-10 before and after the candidate polypeptide stimulation of CD4+T lymphocytes were detected by ELISA. The preliminary humoral immunity test was conducted by indirect ELISA to evaluate the serological diagnostic value of the CD4+T cell epitope polypeptide. In this study, 5 novel candidate CD4+T cell epitope polypeptides with the amino acid sequences of LQGQWRGAAGTAAQA, PVTLAETGSTLLYPL, AAAWGGSGSEAYQGV, QFVYAGAMSGLLDPS, and KAALTRTASNMNAAA and others that have not been reported in the research were predicted. For convenience, the 5 candidates were successively named as P 39 , P 50 , P 40 , P 185 , and P 62 . P 39 , P 62 , and the mixed peptide P 39 +P 62 could effectively induce the proliferation of CD4+T cells and increase the secretion of IFN-γ, TNF-α, and IL-2 from the CD4+T cells, while reducing the content of IL-10. The serological test showed that the sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) of P 39 were 75%, 67.71%, and 0.844, respectively. The sensitivity, specificity, and AUC of P 62 were 91.66%, 46.87%, and 0.649, respectively. The sensitivity of the mixed peptide P 39 +P 62 was 95.83%, the specificity was 97.91%, and the AUC was 0.793. The P 39 and P 62 polypeptides were predicted and identified as potential CD4+T cell immune epitope polypeptides of M. TB. The polypeptide had better diagnosis effect, which provided potential candidate epitope polypeptides for the development of TB-specific diagnosis reagents and novel TB epitope vaccines.

show abstract

The Youden Index in the Generalized Receiver Operating Characteristic Curve Context

Cited by 86 publications

References 23 publications

A deep learning algorithm using CT images to screen for Corona virus disease (COVID-19)

A deep learning algorithm using CT images to screen for Corona virus disease (COVID-19)

A Comparison of the Autistic Behavior Checklist and the Childhood Autism Rating Scale for Suspected Autism in a Large Chinese Sample

Prediction and identification of CD4+ T cell epitope for the protective antigens of Mycobacterium tuberculosis

Contact Info

Product

Resources

About