Towards application of one-class classification methods to medical data.
Ontology highlight
ABSTRACT:
SUBMITTER: Irigoien I
PROVIDER: S-EPMC3980920 | biostudies-other | 2014
REPOSITORIES: biostudies-other
Similar Datasets
Project description:The classification of imbalanced data streams is gaining more and more interest. However, apart from the problem that one of the class is not well represented, there are problems typical for data stream classification, such as limited resources, lack of access to the true labels and the possibility of occurrence of the concept drift. Possibility of concept drift appearing enforces design in the method adaptation mechanism. In this article, we propose the OCEIS classifier (One-Class support vector machine classifier Ensemble for Imbalanced data Stream). The main idea is to supply the committee with one-class classifiers trained on clustered data for each class separately. The results obtained from experiments carried out on synthetic and real data show that the proposed method achieves results at a similar level as the state of the art methods compared with it.
| S-EPMC7303690 | biostudies-literature
Project description:Pattern recognition approaches, such as the Support Vector Machine (SVM), have been successfully used to classify groups of individuals based on their patterns of brain activity or structure. However these approaches focus on finding group differences and are not applicable to situations where one is interested in accessing deviations from a specific class or population. In the present work we propose an application of the one-class SVM (OC-SVM) to investigate if patterns of fMRI response to sad facial expressions in depressed patients would be classified as outliers in relation to patterns of healthy control subjects. We defined features based on whole brain voxels and anatomical regions. In both cases we found a significant correlation between the OC-SVM predictions and the patients' Hamilton Rating Scale for Depression (HRSD), i.e. the more depressed the patients were the more of an outlier they were. In addition the OC-SVM split the patient groups into two subgroups whose membership was associated with future response to treatment. When applied to region-based features the OC-SVM classified 52% of patients as outliers. However among the patients classified as outliers 70% did not respond to treatment and among those classified as non-outliers 89% responded to treatment. In addition 89% of the healthy controls were classified as non-outliers.
| S-EPMC3191277 | biostudies-literature
Project description:IntroductionAutomatically identifying specific phenotypes in free-text clinical notes is critically important for the reuse of clinical data. In this study, the authors combine expert-guided feature (text) selection with one-class classification for text processing.ObjectivesTo compare the performance of one-class classification to traditional binary classification; to evaluate the utility of feature selection based on expert-selected salient text (snippets); and to determine the robustness of these models with respects to irrelevant surrounding text.MethodsThe authors trained one-class support vector machines (1C-SVMs) and two-class SVMs (2C-SVMs) to identify notes discussing breast cancer. Manually annotated visit summary notes (88 positive and 88 negative for breast cancer) were used to compare the performance of models trained on whole notes labeled as positive or negative to models trained on expert-selected text sections (snippets) relevant to breast cancer status. Model performance was evaluated using a 70:30 split for 20 iterations and on a realistic dataset of 10 000 records with a breast cancer prevalence of 1.4%.ResultsWhen tested on a balanced experimental dataset, 1C-SVMs trained on snippets had comparable results to 2C-SVMs trained on whole notes (F = 0.92 for both approaches). When evaluated on a realistic imbalanced dataset, 1C-SVMs had a considerably superior performance (F = 0.61 vs. F = 0.17 for the best performing model) attributable mainly to improved precision (p = .88 vs. p = .09 for the best performing model).Conclusions1C-SVMs trained on expert-selected relevant text sections perform better than 2C-SVMs classifiers trained on either snippets or whole notes when applied to realistically imbalanced data with low prevalence of the positive class.
| S-EPMC4986669 | biostudies-literature
Project description:G protein-coupled receptors are involved in many biological processes, relaying the extracellular signal inside the cell. Signaling is regulated by the interactions between receptors and their ligands, it can be stimulated by agonists, or inhibited by antagonists or inverse agonists. The development of a new drug targeting a member of this family requires to take into account the pharmacological profile of the designed ligands in order to elicit the desired response. The structure-based virtual screening of chemical libraries may prioritize a specific class of ligands by combining docking results and ligand binding information provided by crystallographic structures. The performance of the method depends on the relevance of the structural data, in particular the conformation of the targeted site, the binding mode of the reference ligand, and the approach used to compare the interactions formed by the docked ligand with those formed by the reference ligand in the crystallographic structure. Here, we propose a new method based on the conformational dynamics of a single protein-ligand reference complex to improve the biased selection of ligands with specific pharmacological properties in a structure-based virtual screening exercise. Interactions patterns between a reference agonist and the receptor, here exemplified on the β2 adrenergic receptor, were extracted from molecular dynamics simulations of the agonist/receptor complex and encoded in graphs used to train a one-class machine learning classifier. Different conditions were tested: low to high affinity agonists, varying simulation duration, considering or ignoring hydrophobic contacts, and tuning of the classifier parametrization. The best models applied to post-process raw data from retrospective virtual screening obtained by docking of test libraries effectively filtered out irrelevant poses, discarding inactive and non-agonist ligands while identifying agonists. Taken together, our results suggest that consistency of the binding mode during the simulation is a key to the success of the method.
| S-EPMC9617447 | biostudies-literature
Project description:A lexicostatistical classification is proposed for 20 languages and dialects of the Lezgian group of the North Caucasian family, based on meticulously compiled 110-item wordlists, published as part of the Global Lexicostatistical Database project. The lexical data have been subsequently analyzed with the aid of the principal phylogenetic methods, both distance-based and character-based: Starling neighbor joining (StarlingNJ), Neighbor joining (NJ), Unweighted pair group method with arithmetic mean (UPGMA), Bayesian Markov chain Monte Carlo (MCMC), Unweighted maximum parsimony (UMP). Cognation indexes within the input matrix were marked by two different algorithms: traditional etymological approach and phonetic similarity, i.e., the automatic method of consonant classes (Levenshtein distances). Due to certain reasons (first of all, high lexicographic quality of the wordlists and a consensus about the Lezgian phylogeny among Caucasologists), the Lezgian database is a perfect testing area for appraisal of phylogenetic methods. For the etymology-based input matrix, all the phylogenetic methods, with the possible exception of UMP, have yielded trees that are sufficiently compatible with each other to generate a consensus phylogenetic tree of the Lezgian lects. The obtained consensus tree agrees with the traditional expert classification as well as some of the previously proposed formal classifications of this linguistic group. Contrary to theoretical expectations, the UMP method has suggested the least plausible tree of all. In the case of the phonetic similarity-based input matrix, the distance-based methods (StarlingNJ, NJ, UPGMA) have produced the trees that are rather close to the consensus etymology-based tree and the traditional expert classification, whereas the character-based methods (Bayesian MCMC, UMP) have yielded less likely topologies.
| S-EPMC4342261 | biostudies-literature
Project description:Multiple-class land-cover classification approaches can be inefficient when the main goal is to classify only one or a few classes. Under this scenario one-class classification algorithms could be a more efficient alternative. Currently there are several algorithms that can fulfil this task, with MaxEnt being one of the most promising. However, there is scarce information regarding parametrization for performing land-cover classification using MaxEnt. In this study we aimed to understand how MaxEnt parameterization affects the classification accuracy of four different land-covers (i.e., built-up, irrigated grass, evergreen trees and deciduous trees) in the city of Santiago de Chile. We also evaluated if MaxEnt manual parameterization outperforms classification results obtained when using MaxEnt default parameters setting. To accomplish our objectives, we generated a set of 25,344 classification maps (i.e., 6,336 for each assessed land-cover), which are based on all the potential combination of 12 different classes of features restrictions, four regularization multipliers, four different sample sizes, three training/testing proportions, and 11 thresholds for generating the binary maps. Our results showed that with a good parameterization, MaxEnt can effectively classify different land covers with kappa values ranging from 0.68 for deciduous trees to 0.89 for irrigated grass. However, the accuracy of classification results is highly influenced by the type of land-cover being classified. Simpler models produced good classification outcomes for homogenous land-covers, but not for heterogeneous covers, where complex models provided better outcomes. In general, manual parameterization improves the accuracy of classification results, but this improvement will depend on the threshold used to generate the binary map. In fact, threshold selection showed to be the most relevant factor impacting the accuracy of the four land-cover classification. The number of sampling points for training the model also has a positive effect on classification results. However, this effect followed a logarithmic distribution, showing an improvement of kappa values when increasing the sampling from 40 to 60 points, but showing only a marginal effect if more than 60 sampling points are used. In light of these results, we suggest testing different parametrization and thresholds until satisfactory kappa or other accuracy metrics values are achieved. Our results highlight the huge potential that MaxEnt has a as a tool for one-class classification, but a good understanding of the software settings and model parameterization is needed to obtain reliable results.
| S-EPMC6542344 | biostudies-literature
Project description:As awareness of the habits and risks associated with lung cancer has increased, so has the interest in promoting and improving upon lung cancer screening procedures. Recent research demonstrates the benefits of lung cancer screening; the National Lung Screening Trial (NLST) found as its primary result that preventative screening significantly decreases the death rate for patients battling lung cancer. However, it was also noted that the false positive rate was very high (>94%).In this work, we investigated the ability of various machine learning classifiers to accurately predict lung cancer nodule status while also considering the associated false positive rate. We utilized 416 quantitative imaging biomarkers taken from CT scans of lung nodules from 200 patients, where the nodules had been verified as cancerous or benign. These imaging biomarkers were created from both nodule and parenchymal tissue. A variety of linear, nonlinear, and ensemble predictive classifying models, along with several feature selection methods, were used to classify the binary outcome of malignant or benign status. Elastic net and support vector machine, combined with either a linear combination or correlation feature selection method, were some of the best-performing classifiers (average cross-validation AUC near 0.72 for these models), while random forest and bagged trees were the worst performing classifiers (AUC near 0.60). For the best performing models, the false positive rate was near 30%, notably lower than that reported in the NLST.The use of radiomic biomarkers with machine learning methods are a promising diagnostic tool for tumor classification. The have the potential to provide good classification and simultaneously reduce the false positive rate.
| S-EPMC6917601 | biostudies-literature
Project description:Abstract Objective When correcting for the “class imbalance” problem in medical data, the effects of resampling applied on classifier algorithms remain unclear. We examined the effect on performance over several combinations of classifiers and resampling ratios. Materials and Methods Multiple classification algorithms were trained on 7 resampled datasets: no correction, random undersampling, 4 ratios of Synthetic Minority Oversampling Technique (SMOTE), and random oversampling with the Adaptive Synthetic algorithm (ADASYN). Performance was evaluated in Area Under the Curve (AUC), precision, recall, Brier score, and calibration metrics. A case study on prediction modeling for 30-day unplanned readmissions in previously admitted Urology patients was presented. Results For most algorithms, using resampled data showed a significant increase in AUC and precision, ranging from 0.74 (CI: 0.69–0.79) to 0.93 (CI: 0.92–0.94), and 0.35 (CI: 0.12–0.58) to 0.86 (CI: 0.81–0.92) respectively. All classification algorithms showed significant increases in recall, and significant decreases in Brier score with distorted calibration overestimating positives. Discussion Imbalance correction resulted in an overall improved performance, yet poorly calibrated models. There can still be clinical utility due to a strong discriminating performance, specifically when predicting only low and high risk cases is clinically more relevant. Conclusion Resampling data resulted in increased performances in classification algorithms, yet produced an overestimation of positive predictions. Based on the findings from our case study, a thoughtful predefinition of the clinical prediction task may guide the use of resampling techniques in future studies aiming to improve clinical decision support tools.
| S-EPMC10232287 | biostudies-literature
Project description:Biometric authentication is popular in authentication systems, and gesture as a carrier of behavior characteristics has the advantages of being difficult to imitate and containing abundant information. This research aims to use three-dimensional (3D) depth information of gesture movement to perform authentication with less user effort. We propose an approach based on depth cameras, which satisfies three requirements: Can authenticate from a single, customized gesture; achieves high accuracy without an excessive number of gestures for training; and continues learning the gesture during use of the system. To satisfy these requirements respectively: We use a sparse autoencoder to memorize the single gesture; we employ data augmentation technology to solve the problem of insufficient data; and we use incremental learning technology for allowing the system to memorize the gesture incrementally over time. An experiment has been performed on different gestures in different user situations that demonstrates the accuracy of one-class classification (OCC), and proves the effectiveness and reliability of the approach. Gesture authentication based on 3D depth cameras could be achieved with reduced user effort.
| S-EPMC6210771 | biostudies-literature
Project description:BackgroundDiabetic retinopathy (DR) is one of the leading causes of blindness in the United States and world-wide. DR is a silent disease that may go unnoticed until it is too late for effective treatment. Therefore, early detection could improve the chances of therapeutic interventions that would alleviate its effects.MethodologyGraded fundus photography and systemic data from 3443 ACCORD-Eye Study participants were used to estimate Random Forest (RF) and logistic regression classifiers. We studied the impact of sample size on classifier performance and the possibility of using RF generated class conditional probabilities as metrics describing DR risk. RF measures of variable importance are used to detect factors that affect classification performance.Principal findingsBoth types of data were informative when discriminating participants with or without DR. RF based models produced much higher classification accuracy than those based on logistic regression. Combining both types of data did not increase accuracy but did increase statistical discrimination of healthy participants who subsequently did or did not have DR events during four years of follow-up. RF variable importance criteria revealed that microaneurysms counts in both eyes seemed to play the most important role in discrimination among the graded fundus variables, while the number of medicines and diabetes duration were the most relevant among the systemic variables.Conclusions and significanceWe have introduced RF methods to DR classification analyses based on fundus photography data. In addition, we propose an approach to DR risk assessment based on metrics derived from graded fundus photography and systemic data. Our results suggest that RF methods could be a valuable tool to diagnose DR diagnosis and evaluate its progression.
| S-EPMC4062420 | biostudies-literature