kappa score
Recently Published Documents


TOTAL DOCUMENTS

102
(FIVE YEARS 73)

H-INDEX

8
(FIVE YEARS 4)

2022 ◽  
Vol 2161 (1) ◽  
pp. 012064
Author(s):  
M Dhruv ◽  
R Sai Chandra Teja ◽  
R Sri Devi ◽  
S Nagesh Kumar

Abstract COVID-19 is an emerging infectious disease that has been rampant worldwide since its onset causing Lung irregularity and severe respiratory failure due to pneumonia. The Community-Acquired Pneumonia (CAP), Normal, and COVID-19 Computed Tomography (CT) scan images are classified using Involution Receptive Field Network from Large COVID-19 CT scan slice dataset. The proposed lightweight Involution Receptive Field Network (InRFNet) is spatial specific and channel-agnostic with Receptive Field structure to enhance the feature map extraction. The InRFNet model evaluation results show high training (99%) and validation (96%) accuracy. The performance metrics of the InRFNet model are Sensitivity (94.48%), Specificity (97.87%), Recall (96.34%), F1-score (96.33%), kappa score (94.10%), ROC-AUC (99.41%), mean square error (0.04), and the total number of parameters (33100).


2021 ◽  
Author(s):  
Carly Herbert ◽  
John Broach ◽  
William Heetderks ◽  
Felicia Qashu ◽  
Laura Gibson ◽  
...  

BACKGROUND The ongoing pandemic necessitates the development of accurate, rapid, and affordable diagnostics to help curb SARS-CoV-2 disease transmission, morbidity, and mortality, as well as safely navigate social re-engagement. OBJECTIVE To describe the feasibility and acceptability of serial self-testing for SARS-CoV-2, including need for assistance and reliability of self-interpretation. METHODS A total of 206 adults in the United States with Smartphones were enrolled in this single-arm feasibility study during February and March 2021. All participants were asked to self-test for Covid-19 at home daily using an antigen-detection rapid diagnostic test over a 14-day period and use a smartphone application for testing assistance and to report their results. The main outcomes were adherence to the testing schedule, acceptability of testing and Smartphone application experiences, and reliability of participant versus study team interpretation of test results. RESULTS Among the 206 participants, 52% of study participants were women, the average age was 40.7 years, 34.43% were non-White, and half the sample (56.8%) had received a Bachelor’s degree or higher. Most participants (64.6%) showed high testing adherence. Participants’ interpretations of test results demonstrated high agreement (98.9%) with the study verified results, with a kappa score of 0.29 (p<0.001). Participants reported high satisfaction with self-testing and the smartphone application, with greater than 98% of participants reporting they would recommend the self-test and smartphone application to others. These results were consistent across age, race/ethnicity, and gender groups. CONCLUSIONS Participant’s high adherence to the recommended testing schedule, significant reliability between participant and study staff test interpretation, and acceptability of the smartphone application and self-test indicate that self-tests for SARS-CoV-2 with a smartphone application for assistance and reporting is highly feasible among a diverse population of adults in the United States.


2021 ◽  
Vol 5 (Supplement_1) ◽  
pp. 148-148
Author(s):  
Haley Gallo ◽  
Lindsay Kobayashi ◽  
Jessica Finlay

Abstract The COVID-19 pandemic was met with conflicting government strategies in the handling of the virus. Older adults were disproportionately impacted by the pandemic, yet little is known about their perspectives of the government response. Using data collected in September and October, 2020 from the online, nation-wide COVID-19 Coping Study, we conducted qualitative thematic analysis on a subsample of respondents (N=500) proportionate to the age, gender, race/ethnicity, and education of the U.S. population age 55+. Two researchers individually coded a random subsample of 50 open-ended responses to the question “How do you feel about federal government responses to and handling of the COVID-19 pandemic?” Using NVivo qualitative software, the researchers compared codes and reconciled differences to achieve a Kappa score of &gt;0.8. The first author coded the remaining responses using the established coding strategy. Analyses identified themes related to President Trump’s leadership, Congress, the broader federal government, and science. Some participants indicated that the federal government’s response to the pandemic was “inadequate,” “too political,” and “lacking coordination.” Others expressed that the president “did the best he could” or that “it’s not the federal government’s responsibility.” While some praised vaccine development efforts and expressed their appreciation for Dr. Fauci, others expressed scientific distrust. Participants’ perspectives were divergent, reflective of the country’s polarization surrounding COVID-19 policies and practices. Differences in perspectives exist by race/ethnicity, gender, geographic region, and age. Study results can help identify groups of older adults who may need targeted programs and policy support.


2021 ◽  
Vol 11 (22) ◽  
pp. 11035
Author(s):  
San-Li Yi ◽  
Xue-Lian Yang ◽  
Tian-Wei Wang ◽  
Fu-Rong She ◽  
Xin Xiong ◽  
...  

The early detection and grade diagnosis of diabetic retinopathy (DR) are very important for the avoidance of blindness, and using deep learning methods to automatically diagnose DR has attracted great attention. However, the small amount of DR data limits its application. To automatically learn the disease’s features and detect DR more accurately, we constructed a DR grade diagnostic model. To realize the model, the authors performed the following steps: firstly, we preprocess the DR images to solve the existing problems in an APTOS 2019 dataset, such as size difference, information redundancy and the data imbalance. Secondly, to extract more valid image features, a new network named RA-EfficientNet is proposed, in which a residual attention (RA) block is added to EfficientNet to extract more features and to solve the problem of small differences between lesions. EfficientNet has been previously trained on the ImageNet dataset, based on transfer learning technology, to overcome the small sample size problem of DR. Lastly, based on the extracted features, two classifiers are designed, one is a 2-grade classifier and the other a 5-grade classifier. The 2-grade classifier can diagnose DR, and the 5-grade classifier provides 5 grades of diagnosis for DR, as follows: 0 for No DR, 1 for mild DR, 2 for moderate, 3 for severe and 4 for proliferative DR. Experiments show that our proposed RA-EfficientNet can achieve better performance, with an accuracy value of 98.36% and a kappa score of 96.72% in a 2-grade classification and an accuracy value of 93.55% and a kappa score of 91.93% in a 5-grade classification. The results indicate that the proposed model effectively improves DR detection efficiency and resolves the existing limitation of manual feature extraction.


2021 ◽  
Vol 22 (3) ◽  
pp. 283-293
Author(s):  
Usha Patel ◽  
Hardik Dave ◽  
Vibha Patel

There has been extensive research in the field of Hyperspectral Image Classification using deep neural networks. The deep learning based approaches requires huge amount of labelled data samples. But in the case of Hyperspectral Image, there are less number of labelled data samples. Therefore, we can adopt Active Learning combined with deep learning based approaches to be able to extract most informative data samples. By using this technique, we can train the classifier to achieve better classification accuracies with less number of labelled data samples. There is considerable amount of research carried out for selecting diverse data samples from the pool of unlabeled data samples. We present a novel diversity-based Active Learning approach utilizing the information of clustered data distribution. We incorporate diversity criteria with Active Learning selection criteria and combine it with Convolutional Neural Network for feature extraction and classification. This approach helps us in obtaining most informative and diverse data samples. We have compared our proposed approach with three other sampling methods in terms of classification accuracies, Cohen Kappa score, which shows that our approach gives better results with comparison to other sampling methods.


Author(s):  
E. Nobels-Janssen ◽  
E. N. Postma ◽  
I. L. Abma ◽  
J. M. C. van Dijk ◽  
R. Haeren ◽  
...  

Abstract Background and objectives The modified Rankin Scale (mRS) is one of the most frequently used outcome measures in trials in patients with an aneurysmal subarachnoid hemorrhage (aSAH). The assessment method of the mRS is often not clearly described in trials, while the method used might influence the mRS score. The aim of this study is to evaluate the inter-method reliability of different assessment methods of the mRS. Methods This is a prospective, randomized, multicenter study with follow-up at 6 weeks and 6 months. Patients aged ≥ 18 years with aSAH were randomized to either a structured interview or a self-assessment of the mRS. Patients were seen by a physician who assigned an mRS score, followed by either the structured interview or the self-assessment. Inter-method reliability was assessed with the quadratic weighted kappa score and percentage of agreement. Assessment of feasibility of the self-assessment was done by a feasibility questionnaire. Results The quadratic weighted kappa was 0.60 between the assessment of the physician and structured interview and 0.56 between assessment of the physician and self-assessment. Percentage agreement was, respectively, 50.8 and 19.6%. The assessment of the mRS through a structured interview and by self-assessment resulted in systematically higher mRS scores than the mRS scored by the physician. Self-assessment of the mRS was proven feasible. Discussion The mRS scores obtained with different assessment methods differ significantly. The agreement between the scores is low, although the reliability between the assessment methods is good. This should be considered when using the mRS in clinical trials. Trial registration www.trialregister.nl; Unique identifier: NL7859.


2021 ◽  
Author(s):  
◽  
Michelle Ryder-Lewis

<p>The management of sedation in critically ill patients is a complex issue for Intensive Care Units (ICU) worldwide. Notable complications of sedation practices have been identified and efforts to modify these practices in ICUs have begun. While sedation-scoring tools have been introduced into clinical practice in intensive care few have been tested for validity and reliability. One tool which has reliability and validity established is the Sedation-Agitation Scale (SAS). This study is an extension of a previous study by Riker, Picard and Fraser (1999) to determine whether doctors and nurses rate patients similarly using the SAS in a natural ICU setting. It is essential to establish whether these different professionals provide consistent scores and have a mutual understanding of the SAS and its constituent levels. This will help ensure that clinical decisions relating to sedation-needs can be made appropriately and consistently. This quasi-experimental reliability study was set in a 12-bed tertiary general ICU in New Zealand. The SAS had recently been introduced into this unit and a convenience sample of 42 nursing and medical staff performed paired ratings on 69 randomly selected adult ICU patients over an eight week time frame. The mean patient age was 58 years, and 79% of patients were on continuous infusions of Propofol. Intubated patients made up 91% of the sample. 74% of patients were given the same SAS score by the doctor-nurse pair. The weighted kappa score for inter-rater agreement was 0.82 indicating very good agreement. Of the 26% of scores where there was a difference, the two readings were only one score apart. Most of the difference occurred around SAS scores of 1-2 and 3-4. Further analysis found no staff or patient variables to be statistically significant in impacting on the ratings. The SAS was found to be a reliable sedation-scoring tool in a general ICU when used by nurses and doctors of varying experience. The implementation of the SAS should improve the quality of sedation management in critically ill patients, facilitate communication between nurses and medical staff with regard to the effectiveness of sedation regimes, and assist with the development of optimal sedation and analgesia guidelines for ICU patients.</p>


2021 ◽  
Author(s):  
◽  
Michelle Ryder-Lewis

<p>The management of sedation in critically ill patients is a complex issue for Intensive Care Units (ICU) worldwide. Notable complications of sedation practices have been identified and efforts to modify these practices in ICUs have begun. While sedation-scoring tools have been introduced into clinical practice in intensive care few have been tested for validity and reliability. One tool which has reliability and validity established is the Sedation-Agitation Scale (SAS). This study is an extension of a previous study by Riker, Picard and Fraser (1999) to determine whether doctors and nurses rate patients similarly using the SAS in a natural ICU setting. It is essential to establish whether these different professionals provide consistent scores and have a mutual understanding of the SAS and its constituent levels. This will help ensure that clinical decisions relating to sedation-needs can be made appropriately and consistently. This quasi-experimental reliability study was set in a 12-bed tertiary general ICU in New Zealand. The SAS had recently been introduced into this unit and a convenience sample of 42 nursing and medical staff performed paired ratings on 69 randomly selected adult ICU patients over an eight week time frame. The mean patient age was 58 years, and 79% of patients were on continuous infusions of Propofol. Intubated patients made up 91% of the sample. 74% of patients were given the same SAS score by the doctor-nurse pair. The weighted kappa score for inter-rater agreement was 0.82 indicating very good agreement. Of the 26% of scores where there was a difference, the two readings were only one score apart. Most of the difference occurred around SAS scores of 1-2 and 3-4. Further analysis found no staff or patient variables to be statistically significant in impacting on the ratings. The SAS was found to be a reliable sedation-scoring tool in a general ICU when used by nurses and doctors of varying experience. The implementation of the SAS should improve the quality of sedation management in critically ill patients, facilitate communication between nurses and medical staff with regard to the effectiveness of sedation regimes, and assist with the development of optimal sedation and analgesia guidelines for ICU patients.</p>


2021 ◽  
Vol 23 (Supplement_6) ◽  
pp. vi120-vi121
Author(s):  
Mircea Tesileanu ◽  
Pim French ◽  
Marc Sanson ◽  
Alba Ariela Brandes ◽  
Wolfgang Wick ◽  
...  

Abstract BACKGROUND Temozolomide efficacy in high-grade glioma is related to MGMTp methylation. We compared the prognostic and predictive effect of MGMTp between DNA methylation profiling (MGMT-STP27 model) and qMS-PCR in IDH1/2mt anaplastic astrocytoma patients. METHODS The 2x2 factorial design phase III CATNON trial randomized 751 adult patients with newly diagnosed 1p/19q non-codeleted anaplastic glioma to 59.4Gy radiotherapy, radiotherapy with concurrent temozolomide, radiotherapy with 12 cycles of adjuvant temozolomide, or radiotherapy with concurrent and adjuvant temozolomide. MGMTp methylation status was assessed with the MGMT-STP27 model using 850k EPIC data, and qMS-PCR. IDH1/2 mutation status was determined with next-generation sequencing. OS was measured from randomization date. RESULTS We identified 444 IDH1/2mt anaplastic astrocytoma patients. MGMTp was methylated in 365/440 patients (83.0%) with MGMT-STP27 data, and 168/361 patients (46.5%) with qMS-PCR data. The agreement between both modalities is 59.9% (Cohen’s Kappa score 0.229). At database lock, 289 patients with MGMT-STP27 data were alive and 236 patients with qMS-PCR data. The median OS of MGMTp methylated glioma patients was 9.1 yrs [95%CI 7.5-not reached] for the MGMT-STP27 model, and not reached [95%CI 9.1-not reached] for qMS-PCR. For MGMTp unmethylated glioma patients, the median OS was 6.9 yrs [95%CI 6.2-not reached] for the MGMT-STP27 model, and 6.8 yrs [95%CI 6.2-9.7] for qMS-PCR. The HR for OS based on MGMTp methylation was 0.88 [95%CI 0.58-1.31] for the MGMT-STP27 model, and 0.72 [95%CI 0.50-1.03]) for qMS-PCR. The HR for OS after radiotherapy with any temozolomide vs radiotherapy alone for the MGMT-STP27 model was 0.53 [95%CI 0.37-0.78] for MGMTp methylated, and 0.54 [95%CI 0.25-1.18] for MGMTp unmethylated glioma patients; and for MS-PCR was 0.34 [95%CI 0.19-0.61] for MGMTp methylated, and 0.53 [95%CI 0.33-0.85] for MGMTp unmethylated glioma patients. CONCLUSION MGMTp methylation, regardless of assay, was neither prognostic nor predictive for outcome to temozolomide in IDH1/2mt anaplastic astrocytoma patients.


2021 ◽  
Vol 10 (1) ◽  
pp. 6
Author(s):  
Fattah Hatami Maskouni ◽  
Seyd Teymoor Seydi

Forest areas are profoundly important to the planet, since they offer considerable advantages. The mapping and estimation of burned areas covered with trees are critical during decision making processes. In such cases, remote sensing can be of great help. This paper presents a method to estimate burned areas based on the Sentinel-2 imagery using a convolutional neural network (CNN) algorithm. The framework touches change detection using pre- and post-fire datasets. The proposed framework utilizes a multi-scale convolution block to extract deep features. We investigate the performance of the proposed method via visual and numerical analyses. The case study for this research is Golestan Forest, which is located in the north of Iran. The results of the burned area detection process show that the proposed method produces a performance accuracy rate of more than 97% in terms of overall accuracy, with a Kappa score greater than 0.933.


Sign in / Sign up

Export Citation Format

Share Document