Journal: Heliyon

Article Title: Role of C5aR2 in prognosis of patients with acute respiratory distress syndrome through negative modulation of C5a: A prospective observational study

doi: 10.1016/j.heliyon.2025.e42146

Figure Lengend Snippet: Prognostic performance of C5a, C5aR2 and C5a/C5aR2 ratio for non-recovery in ARDS patients (N = 64).

Article Snippet: Area under receiver operating characteristic (AUROC) was used to analyse the prognostic performance of C5a, C5R2, and C5a/C5R2 ratio using MedCalc.

Techniques:

Journal: PLoS ONE

Article Title: The role of gadolinium in magnetic resonance imaging for early prostate cancer diagnosis: A diagnostic accuracy study

doi: 10.1371/journal.pone.0227031

Figure Lengend Snippet: Receiver Operating Characteristic (ROC) for PI-RADS with DCE (black) and without DCE (red or green). (A) ROC for the peripheral zone (Pz) IPca and CSPca merged as “all cancers,”, p = 0.96, AUC CI 95% 0.62–0.78 for both PIRADS with and without DCE. (B) ROC for CSPca in the Pz, p = 0.09, AUC CI 95% 0.65–0.81 PIRADS without DCE and 0.61–0.78.(C) ROC for CSPca sized < 11 mm in the Pz, p = 0.54, AUC CI 95% 0.54–0.80 without and 0.51–0.78 with DCE. (D) ROC for CSPca sized > 11 mm in the Pz, p = 0.20, AUC CI 95% 0.66–0.85 without and 0.63–0.83 with DCE. (E) ROC for all cancers in the transitional zone (Tz), p = 0.08, AUC CI 95% 0.68–0.81 without and 0.62–0.76 with DCE, (F) ROC for CSPca in the Tz, p = 0.14, AUC CI 95% 0.59–0.75 without and 0.53–0.69 with DCE. (G) ROC for CSPca sized < 11 mm in the Tz, p = 0.04, AUC CI 95% 0.56–0.79 without and 0.50–0.62 with DCE, (H) ROC for CSPca sized > 11 mm in the Tz, p = 0.71, AUC CI95% 0.58–0.78 without and 0.56–0.77 with DCE.All curve differences were tested with a pairwise chi-squared test. (I) Histogram of the lesion size in the Pz. The size is expressed as the maximum diameter in paraxial T2w sections. (J) Histogram of the lesion size in Tz. ADC, Apparent Diffusion Coefficient; CSPca, clinically significant prostate cancer; DCE, Dynamic Contrast Enhancement; DWI, Diffusion-Weighted Imaging; IPca, insignificant prostate cancer; PI-RADS, Prostate Image Reporting and Data System; T2w, T2 weighted imaging.

Article Snippet: The Receiver Operating Characteristics Area Under Curve (ROC-AUC), sensitivity (Se) and specificity (Spe) of PIRADS-without-DCE in the Pz was 0.70/0.47/0.86 for all cancers (IPca and CSPca merged) and 0.73/0.54/0.82 for CSPca.

Techniques: Diffusion-based Assay, Imaging

Journal: Ieee Journal of Selected Topics in Signal Processing

Article Title: Project Achoo: A Practical Model and Application for COVID-19 Detection From Recordings of Breath, Voice, and Cough

doi: 10.1109/JSTSP.2022.3142514

Figure Lengend Snippet: Distinct Variants of Ensembling Lead to Different Performance on the Test Dataset. We are Able to Change Weights in the Ensemble in Order to Maximize Specific Metrics

Article Snippet: Since the convolutional model used to get the scores is not over-parametrized to memorize the dataset, , and its architecture was shown to be effective in applications ( , and Kaggle Freesound competition https://www.kaggle.com/c/freesound-audio-tagging-2019 ), we speculated that the variability of ROC AUC and the MCC scores between the datasets could be due to the potentially mislabelled COVID status in Coswara and the EPFL datasets, which, unlike Covid19-Cough, are also highly imbalanced.

Techniques: Variant Assay

Journal: Ieee Journal of Selected Topics in Signal Processing

Article Title: Project Achoo: A Practical Model and Application for COVID-19 Detection From Recordings of Breath, Voice, and Cough

doi: 10.1109/JSTSP.2022.3142514

Figure Lengend Snippet: Classification Metrics of Different Predictors on Openly Available Crowdsourced Datasets

Article Snippet: Since the convolutional model used to get the scores is not over-parametrized to memorize the dataset, , and its architecture was shown to be effective in applications ( , and Kaggle Freesound competition https://www.kaggle.com/c/freesound-audio-tagging-2019 ), we speculated that the variability of ROC AUC and the MCC scores between the datasets could be due to the potentially mislabelled COVID status in Coswara and the EPFL datasets, which, unlike Covid19-Cough, are also highly imbalanced.

Techniques:

Journal: Ieee Journal of Selected Topics in Signal Processing

Article Title: Project Achoo: A Practical Model and Application for COVID-19 Detection From Recordings of Breath, Voice, and Cough

doi: 10.1109/JSTSP.2022.3142514

Figure Lengend Snippet: ROC AUC and Matthews Correlation Score for Different Ensembles on Data Collected From the App. Answers to the Question “do You Have Acute Respiratory Disease Right Now?” Were Considered as Ground Truth

Article Snippet: Since the convolutional model used to get the scores is not over-parametrized to memorize the dataset, , and its architecture was shown to be effective in applications ( , and Kaggle Freesound competition https://www.kaggle.com/c/freesound-audio-tagging-2019 ), we speculated that the variability of ROC AUC and the MCC scores between the datasets could be due to the potentially mislabelled COVID status in Coswara and the EPFL datasets, which, unlike Covid19-Cough, are also highly imbalanced.

Techniques: Variant Assay

Journal: Ieee Journal of Selected Topics in Signal Processing

Article Title: Project Achoo: A Practical Model and Application for COVID-19 Detection From Recordings of Breath, Voice, and Cough

doi: 10.1109/JSTSP.2022.3142514

Figure Lengend Snippet: The Average Model Performance for 10-Fold Cross-Validation With Covid19-Cough Dataset and Joined Covid19-Cough and Hospital Dataset. Testing was Performed on the Same Test Parts of CV Splits of the Covid19-Cough Dataset

Article Snippet: Since the convolutional model used to get the scores is not over-parametrized to memorize the dataset, , and its architecture was shown to be effective in applications ( , and Kaggle Freesound competition https://www.kaggle.com/c/freesound-audio-tagging-2019 ), we speculated that the variability of ROC AUC and the MCC scores between the datasets could be due to the potentially mislabelled COVID status in Coswara and the EPFL datasets, which, unlike Covid19-Cough, are also highly imbalanced.

Techniques: