Dataset Information

Evaluating the Performance of Sensor-based Bout Detection Algorithms: The Transition Pairing Method.

ABSTRACT: Bout detection algorithms are used to segment data from wearable sensors, but it is challenging to assess segmentation correctness.

Purpose

To present and demonstrate the Transition Pairing Method (TPM), a new method for evaluating the performance of bout detection algorithms.

Methods

The TPM compares predicted transitions to a criterion measure in terms of number and timing. A true positive is defined as a predicted transition that corresponds with one criterion transition in a mutually exclusive pair. The pairs are established using an extended Gale-Shapley algorithm, and the user specifies a maximum allowable within-pair time lag, above which pairs cannot be formed. Unpaired predictions and criteria are false positives and false negatives, respectively. The demonstration used raw acceleration data from 88 youth who wore ActiGraph GT9X monitors (right hip and non-dominant wrist) during simulated free-living. Youth Sojourn bout detection algorithms were applied (one for each attachment site), and the TPM was used to compare predicted bout transitions to the criterion measure (direct observation). Performance metrics were calculated for each participant, and hip-versus-wrist means were compared using paired T-tests (α = 0.05).

Results

When the maximum allowable lag was 1-s, both algorithms had recall <20% (2.4% difference from one another, p<0.01) and precision <10% (1.4% difference from one another, p<0.001). That is, >80% of criterion transitions were undetected, and >90% of predicted transitions were false positives.

Conclusion

The TPM improves on conventional analyses by providing specific information about bout detection in a standardized way that applies to any bout detection algorithm.

SUBMITTER: Hibbing PR

PROVIDER: S-EPMC8274497 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Benchmarking surveillance systems requires realistic simulations of disease outbreaks. However, obtaining these data in sufficient quantity, with a realistic shape and covering a sufficient range of agents, size and duration, is known to be very difficult. The dataset of outbreak signals generated should reflect the likely distribution of authentic situations faced by the surveillance system, including very unlikely outbreak signals. We propose and evaluate a new approach based on the use of historical outbreak data to simulate tailored outbreak signals. The method relies on a homothetic transformation of the historical distribution followed by resampling processes (Binomial, Inverse Transform Sampling Method-ITSM, Metropolis-Hasting Random Walk, Metropolis-Hasting Independent, Gibbs Sampler, Hybrid Gibbs Sampler). We carried out an analysis to identify the most important input parameters for simulation quality and to evaluate performance for each of the resampling algorithms. Our analysis confirms the influence of the type of algorithm used and simulation parameters (i.e. days, number of cases, outbreak shape, overall scale factor) on the results. We show that, regardless of the outbreaks, algorithms and metrics chosen for the evaluation, simulation quality decreased with the increase in the number of days simulated and increased with the number of cases simulated. Simulating outbreaks with fewer cases than days of duration (i.e. overall scale factor less than 1) resulted in an important loss of information during the simulation. We found that Gibbs sampling with a shrinkage procedure provides a good balance between accuracy and data dependency. If dependency is of little importance, binomial and ITSM methods are accurate. Given the constraint of keeping the simulation within a range of plausible epidemiological curves faced by the surveillance system, our study confirms that our approach can be used to generate a large spectrum of outbreak signals.

Project description:ObjectiveTo identify non-EEG-based signals and algorithms for detection of motor and non-motor seizures in people lying in bed during video-EEG (VEEG) monitoring and to test whether these algorithms work in freely moving people during mobile EEG recordings.MethodsData of three groups of adult people with epilepsy (PwE) were analyzed. Group 1 underwent VEEG with additional devices (accelerometry, ECG, electrodermal activity); group 2 underwent VEEG; and group 3 underwent mobile EEG recordings both including one-lead ECG. All seizure types were analyzed. Feature extraction and machine-learning techniques were applied to develop seizure detection algorithms. Performance was expressed as sensitivity, precision, F1 score, and false positives per 24 hours.ResultsThe algorithms were developed in group 1 (35 PwE, 33 seizures) and achieved best results (F1 score 56%, sensitivity 67%, precision 45%, false positives 0.7/24 hours) when ECG features alone were used, with no improvement by including accelerometry and electrodermal activity. In group 2 (97 PwE, 255 seizures), this ECG-based algorithm largely achieved the same performance (F1 score 51%, sensitivity 39%, precision 73%, false positives 0.4/24 hours). In group 3 (30 PwE, 51 seizures), the same ECG-based algorithm failed to meet up with the performance in groups 1 and 2 (F1 score 27%, sensitivity 31%, precision 23%, false positives 1.2/24 hours). ECG-based algorithms were also separately trained on data of groups 2 and 3 and tested on the data of the other groups, yielding maximal F1 scores between 8% and 26%.SignificanceOur results suggest that algorithms based on ECG features alone can provide clinically meaningful performance for automatic detection of all seizure types. Our study also underscores that the circumstances under which such algorithms were developed, and the selection of the training and test data sets need to be considered and limit the application of such systems to unseen patient groups behaving in different conditions.

Project description:BackgroundOutbreak detection algorithms play an important role in effective automated surveillance. Although many algorithms have been designed to improve the performance of outbreak detection, few published studies have examined how epidemic features of infectious disease impact on the detection performance of algorithms. This study compared the performance of three outbreak detection algorithms stratified by epidemic features of infectious disease and examined the relationship between epidemic features and performance of outbreak detection algorithms.MethodsExponentially weighted moving average (EWMA), cumulative sum (CUSUM) and moving percentile method (MPM) algorithms were applied. We inserted simulated outbreaks into notifiable infectious disease data in China Infectious Disease Automated-alert and Response System (CIDARS), and compared the performance of the three algorithms with optimized parameters at a fixed false alarm rate of 5% classified by epidemic features of infectious disease. Multiple linear regression was adopted to analyse the relationship of the algorithms' sensitivity and timeliness with the epidemic features of infectious diseases.ResultsThe MPM had better detection performance than EWMA and CUSUM through all simulated outbreaks, with or without stratification by epidemic features (incubation period, baseline counts and outbreak magnitude). The epidemic features were associated with both sensitivity and timeliness. Compared with long incubation, short incubation had lower probability (β* = -0.13, P < 0.001) but needed shorter time to detect outbreaks (β* = -0.57, P < 0.001). Lower baseline counts were associated with higher probability (β* = -0.20, P < 0.001) and longer time (β* = 0.14, P < 0.001). The larger outbreak magnitude was correlated with higher probability (β* = 0.55, P < 0.001) and shorter time (β* = -0.23, P < 0.001).ConclusionsThe results of this study suggest that the MPM is a prior algorithm for outbreak detection and differences of epidemic features in detection performance should be considered in automatic surveillance practice.