Explore the vast range of titles available.

The need to search for new measures describing the classification of a logistic regression model stems from the difficulty in searching for previously unknown factors that predict the occurrence of a disease. A classification quality assessment can be performed by testing the change in the area under the receiver operating characteristic curve (AUC). Another approach is to use the Net Reclassification Improvement (NRI), which is based on a comparison between the predicted risk, determined on the basis of the basic model, and the predicted risk that comes from the model enriched with an additional factor. In this paper, we draw attention to Cohen’s Kappa coefficient, which examines the actual agreement in the correction of a random agreement. We proposed to extend this coefficient so that it may be used to detect the quality of a logistic regression model reclassification. The results provided by Kappa‘s reclassification were compared with the results obtained using NRI. The random variables’ distribution attached to the model on the classification change, measured by NRI, Kappa, and AUC, was presented. A simulation study was conducted on the basis of a cohort containing 3971 Poles obtained during the implementation of a lower limb atherosclerosis prevention program.

PurposeValidation of a recently described central serous chorioretinopathy (CSCR) classification system and assessment of levels of agreement among 10 retina physicians.MethodsThis was a cross-sectional (inter-reader agreement) study. Ten retina physicians (assigned a role of masked grader) were provided with a comprehensive dataset of 61 eyes of 34 patients of presumed CSCR. Relevant clinical details and multimodal imaging (fundus autofluorescence, fluorescein and indocyanine green angiography, optical coherence tomography) of both involved and fellow eye were electronically shared. Later, only the fellow eye images were resent to understand the influence of affected eye on the grading of the fellow eye. Multiple inter-grader agreement using Fleiss Kappa was performed to determine the level of agreement among the 10 graders. p value of ≤ 0.05 was considered statistically significant.ResultsSixty-one eyes of 34 patients were evaluated. There was moderate agreement for major criteria with Fleiss Kappa value of 0.50 (p < 0.0001) with a single outlier observer. After excluding that observer, the Fleiss Kappa value increased to 0.57 (p < 0.0001) with statistically significant p values among all categories, i.e., simple CSC (κ = 0.575), complex CSC (κ = 0.621), and no CSC (κ = 0.452). Overall, moderate to substantial agreement was noted among the subtypes (primary, recurrent, and resolved). The influence of the affected eye on fellow eye grading was studied. The global Fleiss Kappa coefficient (κ = 0.642, p < 0.0001) showed substantial agreement when observers were aware of the affected eye grading. However, without prior available information on the affected eye, the inter-grader agreement was significantly lower (global κ = 0.255, p < 0.0001).ConclusionA fair-moderate inter-grader agreement among the masked graders suggests a need for further refinement of this novel classification system. Disease grading should include both eyes as lack of information on affected eye has a bearing on fellow eye grading and inter-grader agreement as shown by a significant difference in global κ values.

Human life necessitates high-quality sleep. However, humans suffer from a lower quality of life because of sleep disorders. The identification of sleep stages is necessary to predict the quality of sleep. Manual sleep-stage scoring is frequently conducted through sleep experts’ visually evaluations of a patient’s neurophysiological data, gathered in sleep laboratories. Manually scoring sleep is a tough, time-intensive, tiresome, and highly subjective activity. Hence, the need of creating automatic sleep-stage classification has risen due to the limitations imposed by manual sleep-stage scoring methods. In this study, a novel machine learning model is developed using dual-channel unipolar electroencephalogram (EEG), chin electromyogram (EMG), and dual-channel electrooculgram (EOG) signals. Using an optimum orthogonal filter bank, sub-bands are obtained by decomposing 30 s epochs of signals. Tsallis entropies are then calculated from the coefficients of these sub-bands. Then, these features are fed an ensemble bagged tree (EBT) classifier for automated sleep classification. We developed our automated sleep classification model using the Sleep Heart Health Study (SHHS) database, which contains two parts, SHHS-1 and SHHS-2, containing more than 8455 subjects with more than 75,000 h of recordings. The proposed model separated three classes if sleep: rapid eye movement (REM), non-REM, and wake, with a classification accuracy of 90.70% and 91.80% using the SHHS-1 and SHHS-2 datasets, respectively. For the five-class problem, the model produces a classification accuracy of 84.3% and 86.3%, corresponding to the SHHS-1 and SHHS-2 databases, respectively, to classify wake, N1, N2, N3, and REM sleep stages. The model acquired Cohen’s kappa (κ) coefficients as 0.838 with SHHS-1 and 0.86 with SHHS-2 for the three-class classification problem. Similarly, the model achieved Cohen’s κ of 0.7746 for SHHS-1 and 0.8007 for SHHS-2 in five-class classification tasks. The model proposed in this study has achieved better performance than the best existing methods. Moreover, the model that has been proposed has been developed to classify sleep stages for both good sleepers as well as patients suffering from sleep disorders. Thus, the proposed wavelet Tsallis entropy-based model is robust and accurate and may help clinicians to comprehend and interpret sleep stages efficiently.

Synthetic Aperture Radar (SAR) observations are widely used in emergency response for flood mapping and monitoring. However, the current operational services are mainly focused on flood in rural areas and flooded urban areas are less considered. In practice, urban flood mapping is challenging due to the complicated backscattering mechanisms in urban environments and in addition to SAR intensity other information is required. This paper introduces an unsupervised method for flood detection in urban areas by synergistically using SAR intensity and interferometric coherence under the Bayesian network fusion framework. It leverages multi-temporal intensity and coherence conjunctively to extract flood information of varying flooded landscapes. The proposed method is tested on the Houston (US) 2017 flood event with Sentinel-1 data and Joso (Japan) 2015 flood event with ALOS-2/PALSAR-2 data. The flood maps produced by the fusion of intensity and coherence and intensity alone are validated by comparison against high-resolution aerial photographs. The results show an overall accuracy of 94.5% (93.7%) and a kappa coefficient of 0.68 (0.60) for the Houston case, and an overall accuracy of 89.6% (86.0%) and a kappa coefficient of 0.72 (0.61) for the Joso case with the fusion of intensity and coherence (only intensity). The experiments demonstrate that coherence provides valuable information in addition to intensity in urban flood mapping and the proposed method could be a useful tool for urban flood mapping tasks.

Accurately predicting students' exam performance is crucial for fostering academic success and timely interventions. This study addresses the significant challenge of predicting whether a student will pass or fail based on key factors such as study hours and previous exam scores. Using a dataset of 500 students sourced from Kaggle, we introduce a novel customized ensemble machine learning model, combining Random Forest (RF) and AdaBoost classifiers with a custom-weighted soft voting method (weights of 0.2 for RF and 0.8 for AdaBoost). The model's hyperparameters were optimized via GridSearchCV with 10-fold cross-validation, ensuring robustness. The performance of the ensemble model was evaluated using metrics like Cohen's Kappa, achieving superior predictive accuracy compared to baseline models. Our findings indicate that the proposed model not only improves prediction accuracy but also reduces prediction time, offering practical implications for educators and policymakers to design tailored interventions for at-risk students, ultimately enhancing educational outcomes.

Spatiotemporal scale is a basic component of geographical problems because the size of spatiotemporal units may have a significant impact on the aggregation of spatial data and the corresponding analysis results. However, there is no clear standard for measuring the representativeness of conclusions when geographical data with different temporal and spatial units are used in geographical calculations. Therefore, a spatiotemporal analysis unit optimization framework is proposed to evaluate candidate analysis units using the distribution patterns of spatiotemporal data. The framework relies on Pareto optimality to select the spatiotemporal analysis unit, thereby overcoming the subjectivity and randomness of traditional unit setting methods and mitigating the influence of the modifiable areal unit problem (MAUP) to a certain extent. The framework is used to analyze floating car trajectory data, and the spatiotemporal analysis unit is optimized by using a combination of global spatial autocorrelation coefficients and the coefficients of variation of local spatial autocorrelation. Moreover, based on urban hotspot calculations, the effectiveness of the framework is further verified. The proposed optimization framework for spatiotemporal analysis units based on multiple criteria can provide suitable spatiotemporal analysis scales for studies of geographical phenomena.

Accurately classifying land use and land cover (LULC) is crucial for understanding Earth’s dynamics under human influence. This study proposes a novel approach to assess LULC classification accuracy using Sentinel-2 data. Authors have compared traditional and Principal Component Analysis (PCA)-based approaches for Maximum Likelihood Classification, Random Forest, and Support Vector Machine (SVM) classifiers. Four key classes (agricultural land, water bodies, built-up areas, and wastelands) are classified using supervised learning. Accuracy is evaluated using producer, user, overall accuracy, and kappa coefficient. Our findings reveal superior accuracy with PCA-SVM compared to other methods. PCA effectively reduces data redundancy, extracting essential spectral information. This study highlights the value of combining PCA with SVM for LULC classification, empowering policymakers with enhanced decision-making tools and fostering informed policy development.

The paper’s primary goal was to analyze and find interactive piano learning systems using the Suzuki method. The sample of respondents engaged in the investigation was made up of 200 students from the [Zhejiang Conservatory of Music]. The estimated Cohen’s kappa coefficient determined the level playing field of control and experimental groups at the start of training, as the coefficient was equal to 0.08. The survey measured the control and experimental group members’ awareness of the Suzuki method. 29% of students in the control group and 18% of students in the experimental group were somewhat aware of the Suzuki method and relevant theoretical background. The training program was based on: learning sheet music by listening with Modartt Pianote app; developing fine motor skills using Garritan; teamwork based on YOUSICIAN (for the experimental group) and Ding Talk (for the group of children); regular homework using Native Instruments GarageBand (for the experimental group) and WeChat (for children) mobile apps. After a year of study, 54% of students learned to comprehend melodies of varying complexity by ear with further playing on the piano. 58% of control group members learned to play sophisticated tunes using musical notation. During the second phase, which involved 5-7-year-old children, most of group 3 members acquired strong knowledge. Involvement of 5–7-year-olds was done to compare the effectiveness of the developed program for different age categories.

The colorimetric catalytic assay based on the use of 1,2-o-dilauryl-rac-glycero-3-glutaric acid-(6′-methylresorufin) (DGGR) ester as a substrate for pancreatic lipase activity is commonly used for the diagnosis of pancreatitis in dogs and cats. Even though the assay has generally been shown to yield consistent results with feline pancreatic lipase immunoreactivity (fPLI) assay, the agreement may vary between assays of different manufacturers. In this study, the chance-corrected agreement between a DGGR-lipase assay offered by one of the biggest providers of diagnostic solutions in Poland and fPLI assay was investigated. The study was carried out on 50 cats in which DGGR-lipase activity and fPLI were tested in the same blood sample. The chance-corrected agreement was determined using Gwet’s AC1 coefficient separately for the fPLI assay’s cut-off values of >3.5 μg/L and >5.3 μg/L. The DGGR-lipase activity significantly positively correlated with fPLI (Rs = 0.665; CI 95%: 0.451, 0.807, p < 0.001). The chance-corrected agreement between the fPLI assay and DGGR-lipase assay differed considerably depending on the cut-off values of the DGGR-lipase assay. When the cut-off value reported in the literature (>26 U/L) was used, it was poor to fair. It was moderate at the cut-off value recommended by the laboratory (>45 U/L), and good at the cut-off value recommended by the assay’s manufacturer (>60 U/L). The highest agreement was obtained between the fPLI assay at the cut-off value of 3.5 μg/L and the DGGR-lipase assay at the cut-off value of 55 U/L (AC1 = 0.725; CI 95%: 0.537, 0.914) and between the fPLI assay at the cut-off value of 5.3 μg/L and the DGGR-lipase assay at the cut-off value of 70 U/L (AC1 = 0.749; CI 95%: 0.577, 0.921). The study confirms that the chance-corrected agreement between the two assays is good. Prospective studies comparing both assays to a diagnostic gold standard are needed to determine which of them is more accurate.

The aim of this article is to provide a systematic review of reliability studies of the sleep–wake disorder diagnostic criteria of the international classifications used in sleep medicine. Electronic databases (ubMed (1946–2021) and Web of Science (—2021)) were searched up to December 2021 for studies computing the Cohen’s kappa coefficient of diagnostic criteria for the main sleep–wake disorder categories described in the principal classifications. Cohen’s kappa coefficients were extracted for each main sleep–wake disorder category, for each classification subtype, and for the different types of methods used to test the degree of agreement about a diagnosis. The database search identified 383 studies. Fifteen studies were analyzed in this systematic review. Insomnia disorder (10/15) and parasomnia disorder (7/15) diagnostic criteria were the most studied. The reliability of all sleep–wake disorders presented a Cohen’s kappa with substantial agreement (Cohen’s kappa mean = 0.66). The two main reliability methods identified were “test–retest reliability” (11/15), principally used for International Classification of Sleep Disorders (ICSD), and “joint interrater reliability” (4/15), principally used for Diagnostic and Statistical Manual of Mental Disorders (DSM) subtype diagnostic criteria, in particularl, the DSM-5. The implications in terms of the design of the methods used to test the degree of agreement about a diagnosis in sleep medicine are discussed.