Assessment of medical disorders is often aided by objective diagnostic tests which can lead to early intervention and appropriate treatment. In the case of brain dysfunction caused by head injury, there is an urgent need for quantitative evaluation methods to aid in acute triage of those subjects who have sustained traumatic brain injury (TBI). Current clinical tools to detect mild TBI (mTBI/concussion) are limited to subjective reports of symptoms and short neurocognitive batteries, offering little objective evidence for clinical decisions; or computed tomography (CT) scans, with radiation-risk, that are most often negative in mTBI. This paper describes a novel methodology for the development of algorithms to provide multi-class classification in a substantial population of brain injured subjects, across a broad age range and representative subpopulations. The method is based on age-regressed quantitative features (linear and nonlinear) extracted from brain electrical activity recorded from a limited montage of scalp electrodes. These features are used as input to a unique "informed data reduction" method, maximizing confidence of prospective validation and minimizing over-fitting. A training set for supervised learning was used, including: "normal control," "concussed," and "structural injury/CT positive (CT+)." The classifier function separating CT+ from the other groups demonstrated a sensitivity of 96% and specificity of 78%; the classifier separating "normal controls" from the other groups demonstrated a sensitivity of 81% and specificity of 74%, suggesting high utility of such classifiers in acute clinical settings. The use of a sequence of classifiers where the desired risk can be stratified further supports clinical utility.
The importance of safety and reliability in today's real-world complex hybrid systems, such as process plants, led to the development of various anomaly detection and diagnosis techniques. Model-based approaches established themselves among the most successful ones in the field. However, they depend on a model of a system, which usually needs to be derived manually. Manual modeling requires a lot of efforts and resources.This paper gives a procedure for anomaly detection in hybrid systems that uses automatically generated behavior models. The model is learned from logged system's measurements in a hybrid automaton framework. The presented anomaly detection algorithm utilizes the model to predict the system behavior, and to compare it with the observed behavior in an online manner. Alarms are raised whenever a discrepancy is found between these two. The effectiveness of this approach is demonstrated in detecting several types of anomalies in a real-world running production system.
This paper presents a novel model-based approach for the prediction of energy consumption in production plants in order to detect anomalies. A special Ethernet-based data acquisition approach is implemented that features real-time sampling of process and energy data. Hybrid timed automaton models of the supervised production plant are generated and executed in parallel to the system by using data samples as model input. According to comparisons of predicted energy consumption with the production plant observations, anomalies can be detected automatically. An evaluation within a small factory shows that anomalies of 10%differences in energy consumption, wrong control sequences and wrong timings can be detected with a minimum accuracy of 98 %. With this approach, downtimes of production systems can be shortened and atypical energy consumptions can be detected and adjusted to optimal operation
Background Biological disease-modifying anti-rheumatic drugs (bDMARDs) can be tapered in some rheumatoid arthritis (RA) patients in sustained remission. The purpose of this study was to assess the feasibility of building a model to estimate the individual flare probability in RA patients tapering bDMARDs using machine learning methods. Methods Longitudinal clinical data of RA patients on bDMARDs from a randomized controlled trial of treatment withdrawal (RETRO) were used to build a predictive model to estimate the probability of a flare. Four basic machine learning models were trained, and their predictions were additionally combined to train an ensemble learning method, a stacking meta-classifier model to predict the individual flare probability within 14 weeks after each visit. Prediction performance was estimated using nested cross-validation as the area under the receiver operating curve (AUROC). Predictor importance was estimated using the permutation importance approach. Results Data of 135 visits from 41 patients were included. A model selection approach based on nested cross-validation was implemented to find the most suitable modeling formalism for the flare prediction task as well as the optimal model hyper-parameters. Moreover, an approach based on stacking different classifiers was successfully applied to create a powerful and flexible prediction model with the final measured AUROC of 0.81 (95%CI 0.73–0.89). The percent dose change of bDMARDs, clinical disease activity (DAS-28 ESR), disease duration, and inflammatory markers were the most important predictors of a flare. Conclusion Machine learning methods were deemed feasible to predict flares after tapering bDMARDs in RA patients in sustained remission.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.