Machine learning-empowered sleep staging classification using multi-modality signals

The goal is to enhance an automated sleep staging system's performance by leveraging the diverse signals captured through multi-modal polysomnography recordings. Three modalities of PSG signals, namely electroencephalogram (EEG), electrooculogram (EOG), and electromyogram (EMG), were considered to obtain the optimal fusions of the PSG signals, where 63 features were extracted. These include frequency-based, time-based, statistical-based, entropy-based, and non-linear-based features. We adopted the ReliefF (ReF) feature selection algorithms to find the suitable parts for each signal and superposition of PSG signals. Twelve top features were selected while correlated with the extracted feature sets' sleep stages. The selected features were fed into the AdaBoost with Random Forest (ADB + RF) classifier to validate the chosen segments and classify the sleep stages. This study's experiments were investigated by obtaining two testing schemes: epoch-wise testing and subject-wise testing. The suggested research was conducted using three publicly available datasets: ISRUC-Sleep subgroup1 (ISRUC-SG1), sleep-EDF(S-EDF), Physio bank CAP sleep database (PB-CAPSDB), and S-EDF-78 respectively. This work demonstrated that the proposed fusion strategy overestimates the common individual usage of PSG signals.

Improved likelihood ratios for face recognition in surveillance video by multimodal feature pairing

In forensic and security scenarios, accurate facial recognition in surveillance videos, often challenged by variations in pose, illumination, and expression, is essential. Traditional manual comparison methods lack standardization, revealing a critical gap in evidence reliability. We propose an enhanced images-to-video recognition approach, pairing facial images with attributes like pose and quality. Utilizing datasets such as ENFSI 2015, SCFace, XQLFW, ChokePoint, and ForenFace, we assess evidence strength using calibration methods for likelihood ratio estimation. Three models-ArcFace, FaceNet, and QMagFace-undergo validation, with the log-likelihood ratio cost (Cllr) as a key metric. Results indicate that prioritizing high-quality frames and aligning attributes with reference images optimizes recognition, yielding similar Cllr values to the top 25% best frames approach. A combined embedding weighted by frame quality emerges as the second-best method. Upon preprocessing facial images with the super resolution CodeFormer, it unexpectedly increased Cllr, undermining evidence reliability, advising against its use in such forensic applications.

Complementary structural and functional abnormalities to localise epileptogenic tissue

BACKGROUND

When investigating suitability for epilepsy surgery, people with drug-refractory focal epilepsy may have intracranial EEG (iEEG) electrodes implanted to localise seizure onset. Diffusion-weighted magnetic resonance imaging (dMRI) may be acquired to identify key white matter tracts for surgical avoidance. Here, we investigate whether structural connectivity abnormalities, inferred from dMRI, may be used in conjunction with functional iEEG abnormalities to aid localisation of the epileptogenic zone (EZ), improving surgical outcomes in epilepsy.

METHODS

We retrospectively investigated data from 43 patients (42% female) with epilepsy who had surgery following iEEG. Twenty-five patients (58%) were free from disabling seizures (ILAE 1 or 2) at one year. Interictal iEEG functional, and dMRI structural connectivity abnormalities were quantified by comparison to a normative map and healthy controls. We explored whether the resection of maximal abnormalities related to improved surgical outcomes, in both modalities individually and concurrently. Additionally, we suggest how connectivity abnormalities may inform the placement of iEEG electrodes pre-surgically using a patient case study.

FINDINGS

Seizure freedom was 15 times more likely in patients with resection of maximal connectivity and iEEG abnormalities (p = 0.008). Both modalities separately distinguished patient surgical outcome groups and when used simultaneously, a decision tree correctly separated 36 of 43 (84%) patients.

INTERPRETATION

Our results suggest that both connectivity and iEEG abnormalities may localise epileptogenic tissue, and that these two modalities may provide complementary information in pre-surgical evaluations.

FUNDING

This research was funded by UKRI, CDT in Cloud Computing for Big Data, NIH, MRC, Wellcome Trust and Epilepsy Research UK.

A scoring approach for multi-platform acquisition in metabolomics

Since the ultimate goal of untargeted metabolomics is the analysis of the broadest possible range of metabolites, some new metrics have to be used by researchers to evaluate and select different analytical strategies when multi-platform analyses are considered. In this context, we aimed at developing a scoring approach allowing to compare the performance of different LC-MS conditions for metabolomics studies. By taking into account both chromatographic and MS attributes of the analytes' peaks (i.e. retention, signal-to-noise ratio, peak intensity and shape), the newly proposed score reflects the potential of a set of LC-MS operating conditions to provide useful analytical information for a given compound. A chemical library containing 597 metabolites was used as a benchmark to apply this approach on two RPLC and three HILIC methods hyphenated to high resolution mass spectrometry (HRMS) in positive and negative ionization modes. The scores not only allowed to evaluate each analytical platform, but also to optimize the number of analytical methods needed for the analysis of metabolomics samples. As a result, the most informative combination of three LC methods and ionization modes was found, leading to a coverage of nearly 95% of the detected compounds. It was therefore demonstrated that the overall performance reached with three selected methods was almost equivalent to the performance reached when five LC-MS conditions were used.

Applying Multi-modal and Correlation Analysis on Environmental Parameters and Effect on Cardiopulmonary Endurance of Gender in Elderly People

BACKGROUND

The aim of this study was to investigate the correlation and interaction between the air pollution's components with cardiopulmonary endurance of elderly people in eight regions by using a multi-modal and correlation analysis.

METHODS

The data of air pollution was collected in eight selected regions in 2013 to 2015. At the same time, total number of 880 male and female, older than 65 year-olds, were investigated based on the cardiopulmonary endurance measurement in the same regions. The correlation, interaction and multiple linear regressions was tested between the air pollution components in each region and cardiopulmonary endurance of elderly people, also between the air pollution components in each region and gender, respectively. In this case, the regression analysis for both hypotheses was conducted.

RESULTS

There was a correlation between the level of air pollution and cardiopulmonary endurance, especially for the carbon monoxide which has a strong effect, it was followed by the effect of sulfur dioxide and fine dust, meanwhile nitrogen dioxide seems not to be effective for this measurement test. Furthermore, it was highly unlikely that gender was a significant factor for the correlation between air pollution and cardiopulmonary endurance.

CONCLUSION

The importance and correlation between air pollution and cardiopulmonary capacity is a critical determinant for the public health of a society, while at the same time having a serious impact on certain age groups. Provided that the factor of gender is highly unlikely to modify this impact, it is necessary to study the potential of other factors.