catch22: CAnonical Time-series CHaracteristics

Frequency-specific dual-attention based adversarial network for blood oxygen level-dependent time series prediction

Functional magnetic resonance imaging (fMRI) is currently one of the most popular technologies for measuring brain activity in both research and clinical contexts. However, clinical constraints often result in short fMRI scan durations, limiting the diagnostic performance for brain disorders. To address this limitation, we developed an end-to-end frequency-specific dual-attention-based adversarial network (FDAA-Net) to extend the time series of existing blood oxygen level-dependent (BOLD) data, enhancing their diagnostic utility. Our approach leverages the frequency-dependent nature of fMRI signals using variational mode decomposition (VMD), which adaptively tracks brain activity across different frequency bands. We integrated the generative adversarial network (GAN) with a spatial-temporal attention mechanism to fully capture relationships among spatially distributed brain regions and temporally continuous time windows. We also introduced a novel loss function to estimate the upward and downward trends of each frequency component. We validated FDAA-Net on the Human Connectome Project (HCP) database by comparing the original and predicted time series of brain regions in the default mode network (DMN), a key network activated during rest. FDAA-Net effectively overcame linear frequency-specific challenges and outperformed other popular prediction models. Test-retest reliability experiments demonstrated high consistency between the functional connectivity of predicted outcomes and targets. Furthermore, we examined the clinical applicability of FDAA-Net using short-term fMRI data from individuals with autism spectrum disorder (ASD) and major depressive disorder (MDD). The model achieved a maximum predicted sequence length of 40% of the original scan durations. The prolonged time series improved diagnostic performance by 8.0% for ASD and 11.3% for MDD compared with the original sequences. These findings highlight the potential of fMRI time series prediction to enhance diagnostic power of brain disorders in short fMRI scans.

Detection Method for Three-Phase Electricity Theft Based on Multi-Dimensional Feature Extraction

The advent of smart grids has facilitated data-driven methods for detecting electricity theft, with a preponderance of research efforts focused on user electricity consumption data. The multi-dimensional power state data captured by Advanced Metering Infrastructure (AMI) encompasses rich information, the exploration of which, in relation to electricity usage behaviors, holds immense potential for enhancing the efficiency of theft detection. In light of this, we propose the Catch22-Conv-Transformer method, a multi-dimensional feature extraction-based approach tailored for the detection of anomalous electricity usage patterns. This methodology leverages both the Catch22 feature set and complementary features to extract sequential features, subsequently employing convolutional networks and the Transformer architecture to discern various types of theft behaviors. Our evaluation, utilizing a three-phase power state and daily electricity usage data provided by the State Grid Corporation of China, demonstrates the efficacy of our approach in accurately identifying theft modalities, including evasion, tampering, and data manipulation.

Intricate response dynamics enhances stimulus discrimination in the resource-limited C. elegans chemosensory system

BACKGROUND

Sensory systems evolved intricate designs to accurately encode perplexing environments. However, this encoding task may become particularly challenging for animals harboring a small number of sensory neurons. Here, we studied how the compact resource-limited chemosensory system of Caenorhabditis elegans uniquely encodes a range of chemical stimuli.

RESULTS

We find that each stimulus is encoded using a small and unique subset of neurons, where only a portion of the encoding neurons sense the stimulus directly, and the rest are recruited via inter-neuronal communication. Furthermore, while most neurons show stereotypical response dynamics, some neurons exhibit versatile dynamics that are either stimulus specific or network-activity dependent. Notably, it is the collective dynamics of all responding neurons which provides valuable information that ultimately enhances stimulus identification, particularly when required to discriminate between closely related stimuli.

CONCLUSIONS

Together, these findings demonstrate how a compact and resource-limited chemosensory system can efficiently encode and discriminate a diverse range of chemical stimuli.

Portable multi-focal visual evoked potential diagnostics for multiple sclerosis/optic neuritis patients

PURPOSE

Multiple sclerosis (MS) is a neuro-inflammatory disease affecting the central nervous system (CNS), where the immune system targets and damages the protective myelin sheath surrounding nerve fibers, inhibiting axonal signal transmission. Demyelinating optic neuritis (ON), a common MS symptom, involves optic nerve damage. We've developed NeuroVEP, a portable, wireless diagnostic system that delivers visual stimuli through a smartphone in a headset and measures evoked potentials at the visual cortex from the scalp using custom electroencephalography electrodes.

METHODS

Subject vision is evaluated using a short 2.5-min full-field visual evoked potentials (ffVEP) test, followed by a 12.5-min multifocal VEP (mfVEP) test. The ffVEP evaluates the integrity of the visual pathway by analyzing the P100 component from each eye, while the mfVEP evaluates 36 individual regions of the visual field for abnormalities. Extensive signal processing, feature extraction methods, and machine learning algorithms were explored for analyzing the mfVEPs. Key metrics from patients' ffVEP results were statistically evaluated against data collected from a group of subjects with normal vision. Custom visual stimuli with simulated defects were used to validate the mfVEP results which yielded 91% accuracy of classification.

RESULTS

20 subjects, 10 controls and 10 with MS and/or ON were tested with the NeuroVEP device and a standard-of-care (SOC) VEP testing device which delivers only ffVEP stimuli. In 91% of the cases, the ffVEP results agreed between NeuroVEP and SOC device. Where available, the NeuroVEP mfVEP results were in good agreement with Humphrey Automated Perimetry visual field analysis. The lesion locations deduced from the mfVEP data were consistent with Magnetic Resonance Imaging and Optical Coherence Tomography findings.

CONCLUSION

This pilot study indicates that NeuroVEP has the potential to be a reliable, portable, and objective diagnostic device for electrophysiology and visual field analysis for neuro-visual disorders.

Uncertainty quantification in neural-network based pain intensity estimation

Improper pain management leads to severe physical or mental consequences, including suffering, a negative impact on quality of life, and an increased risk of opioid dependency. Assessing the presence and severity of pain is imperative to prevent such outcomes and determine the appropriate intervention. However, the evaluation of pain intensity is a challenging task because different individuals experience pain differently. To overcome this, many researchers in the field have employed machine learning models to evaluate pain intensity objectively using physiological signals. However, these efforts have primarily focused on pain point estimation, disregarding inherent uncertainty and variability in the data and model. A point estimate, which provides only partial information, is not sufficient for sound clinical decision-making. This study proposes a neural network-based method for objective pain interval estimation, and quantification of uncertainty. Our approach, which enables objective pain intensity estimation with desired confidence probabilities, affords clinicians a better understanding of a person's pain intensity. We explored three distinct algorithms: the bootstrap method, lower and upper bound estimation (LossL) optimized by genetic algorithm, and modified lower and upper bound estimation (LossS) optimized by gradient descent algorithm. Our empirical results demonstrate that LossS outperforms the other two by providing narrower prediction intervals. For 50%, 75%, 85%, and 95% prediction interval coverage probability, LossS provides average interval widths that are 22.4%, 7.9%, 16.7%, and 9.1% narrower than those of LossL, and 19.3%, 21.1%, 23.6%, and 26.9% narrower than those of bootstrap. As LossS outperforms, we assessed its performance in three different model-building approaches: (1) a generalized approach using a single model for the entire population, (2) a personalized approach with separate models for each individual, and (3) a hybrid approach with models for clusters of individuals. Results demonstrate that the hybrid model-building approach provides the best performance.

Eigen-entropy based time series signatures to support multivariate time series classification

Most current algorithms for multivariate time series classification tend to overlook the correlations between time series of different variables. In this research, we propose a framework that leverages Eigen-entropy along with a cumulative moving window to derive time series signatures to support the classification task. These signatures are enumerations of correlations among different time series considering the temporal nature of the dataset. To manage dataset's dynamic nature, we employ preprocessing with dense multi scale entropy. Consequently, the proposed framework, Eigen-entropy-based Time Series Signatures, captures correlations among multivariate time series without losing its temporal and dynamic aspects. The efficacy of our algorithm is assessed using six binary datasets sourced from the University of East Anglia, in addition to a publicly available gait dataset and an institutional sepsis dataset from the Mayo Clinic. We use recall as the evaluation metric to compare our approach against baseline algorithms, including dependent dynamic time warping with 1 nearest neighbor and multivariate multi-scale permutation entropy. Our method demonstrates superior performance in terms of recall for seven out of the eight datasets.

Purinergic Ca2+ Signaling as a Novel Mechanism of Drug Tolerance in BRAF-Mutant Melanoma

Drug tolerance is a major cause of relapse after cancer treatment. Despite intensive efforts, its molecular basis remains poorly understood, hampering actionable intervention. We report a previously unrecognized signaling mechanism supporting drug tolerance in BRAF-mutant melanoma treated with BRAF inhibitors that could be of general relevance to other cancers. Its key features are cell-intrinsic intracellular Ca2+ signaling initiated by P2X7 receptors (purinergic ligand-gated cation channels) and an enhanced ability for these Ca2+ signals to reactivate ERK1/2 in the drug-tolerant state. Extracellular ATP, virtually ubiquitous in living systems, is the ligand that can initiate Ca2+ spikes via P2X7 channels. ATP is abundant in the tumor microenvironment and is released by dying cells, ironically implicating treatment-initiated cancer cell death as a source of trophic stimuli that leads to ERK reactivation and drug tolerance. Such a mechanism immediately offers an explanation of the inevitable relapse after BRAFi treatment in BRAF-mutant melanoma and points to actionable strategies to overcome it.

Extracting interpretable signatures of whole-brain dynamics through systematic comparison

The brain's complex distributed dynamics are typically quantified using a limited set of manually selected statistical properties, leaving the possibility that alternative dynamical properties may outperform those reported for a given application. Here, we address this limitation by systematically comparing diverse, interpretable features of both intra-regional activity and inter-regional functional coupling from resting-state functional magnetic resonance imaging (rs-fMRI) data, demonstrating our method using case-control comparisons of four neuropsychiatric disorders. Our findings generally support the use of linear time-series analysis techniques for rs-fMRI case-control analyses, while also identifying new ways to quantify informative dynamical fMRI structures. While simple statistical representations of fMRI dynamics performed surprisingly well (e.g., properties within a single brain region), combining intra-regional properties with inter-regional coupling generally improved performance, underscoring the distributed, multifaceted changes to fMRI dynamics in neuropsychiatric disorders. The comprehensive, data-driven method introduced here enables systematic identification and interpretation of quantitative dynamical signatures of multivariate time-series data, with applicability beyond neuroimaging to diverse scientific problems involving complex time-varying systems.

Enhancing pathological complete response prediction in breast cancer: the role of dynamic characterization of DCE-MRI and its association with tumor heterogeneity

BACKGROUND

Early prediction of pathological complete response (pCR) is important for deciding appropriate treatment strategies for patients. In this study, we aimed to quantify the dynamic characteristics of dynamic contrast-enhanced magnetic resonance images (DCE-MRI) and investigate its value to improve pCR prediction as well as its association with tumor heterogeneity in breast cancer patients.

METHODS

The DCE-MRI, clinicopathologic record, and full transcriptomic data of 785 breast cancer patients receiving neoadjuvant chemotherapy were retrospectively included from a public dataset. Dynamic features of DCE-MRI were computed from extracted phase-varying radiomic feature series using 22 CAnonical Time-sereis CHaracteristics. Dynamic model and radiomic model were developed by logistic regression using dynamic features and traditional radiomic features respectively. Various combined models with clinical factors were also developed to find the optimal combination and the significance of each components was evaluated. All the models were evaluated in independent test set in terms of area under receiver operating characteristic curve (AUC). To explore the potential underlying biological mechanisms, radiogenomic analysis was implemented on patient subgroups stratified by dynamic model to identify differentially expressed genes (DEGs) and enriched pathways.

RESULTS

A 10-feature dynamic model and a 4-feature radiomic model were developed (AUC = 0.688, 95%CI: 0.635-0.741 and AUC = 0.650, 95%CI: 0.595-0.705) and tested (AUC = 0.686, 95%CI: 0.594-0.778 and AUC = 0.626, 95%CI: 0.529-0.722), with the dynamic model showing slightly higher AUC (train p = 0.181, test p = 0.222). The combined model of clinical, radiomic, and dynamic achieved the highest AUC in pCR prediction (train: 0.769, 95%CI: 0.722-0.816 and test: 0.762, 95%CI: 0.679-0.845). Compared with clinical-radiomic combined model (train AUC = 0.716, 95%CI: 0.665-0.767 and test AUC = 0.695, 95%CI: 0.656-0.714), adding the dynamic component brought significant improvement in model performance (train p < 0.001 and test p = 0.005). Radiogenomic analysis identified 297 DEGs, including CXCL9, CCL18, and HLA-DPB1 which are known to be associated with breast cancer prognosis or angiogenesis. Gene set enrichment analysis further revealed enrichment of gene ontology terms and pathways related to immune system.

CONCLUSION

Dynamic characteristics of DCE-MRI were quantified and used to develop dynamic model for improving pCR prediction in breast cancer patients. The dynamic model was associated with tumor heterogeniety in prognostic-related gene expression and immune-related pathways.

Human-in-the-Loop: Visual Analytics for Building Models Recognizing Behavioral Patterns in Time Series

Detecting complex behavioral patterns in temporal data, such as moving object trajectories, often relies on precise formal specifications derived from vague domain concepts. However, such methods are sensitive to noise and minor fluctuations, leading to missed pattern occurrences. Conversely, machine learning (ML) approaches require abundant labeled examples, posing practical challenges. Our visual analytics approach enables domain experts to derive, test, and combine interval-based features to discriminate patterns and generate training data for ML algorithms. Visual aids enhance recognition and characterization of expected patterns and discovery of unexpected ones. Case studies demonstrate feasibility and effectiveness of the approach, which offers a novel framework for integrating human expertise and analytical reasoning with ML techniques, advancing data analytics.

DeePhys: A machine learning-assisted platform for electrophysiological phenotyping of human neuronal networks

Reproducible functional assays to study in vitro neuronal networks represent an important cornerstone in the quest to develop physiologically relevant cellular models of human diseases. Here, we introduce DeePhys, a MATLAB-based analysis tool for data-driven functional phenotyping of in vitro neuronal cultures recorded by high-density microelectrode arrays. DeePhys is a modular workflow that offers a range of techniques to extract features from spike-sorted data, allowing for the examination of functional phenotypes both at the individual cell and network levels, as well as across development. In addition, DeePhys incorporates the capability to integrate novel features and to use machine-learning-assisted approaches, which facilitates a comprehensive evaluation of pharmacological interventions. To illustrate its practical application, we apply DeePhys to human induced pluripotent stem cell-derived dopaminergic neurons obtained from both patients and healthy individuals and showcase how DeePhys enables phenotypic screenings.

Automated identification of abnormal infant movements from smart phone videos

Cerebral palsy (CP) is the most common cause of physical disability during childhood, occurring at a rate of 2.1 per 1000 live births. Early diagnosis is key to improving functional outcomes for children with CP. The General Movements (GMs) Assessment has high predictive validity for the detection of CP and is routinely used in high-risk infants but only 50% of infants with CP have overt risk factors when they are born. The implementation of CP screening programs represents an important endeavour, but feasibility is limited by access to trained GMs assessors. To facilitate progress towards this goal, we report a deep-learning framework for automating the GMs Assessment. We acquired 503 videos captured by parents and caregivers at home of infants aged between 12- and 18-weeks term-corrected age using a dedicated smartphone app. Using a deep learning algorithm, we automatically labelled and tracked 18 key body points in each video. We designed a custom pipeline to adjust for camera movement and infant size and trained a second machine learning algorithm to predict GMs classification from body point movement. Our automated body point labelling approach achieved human-level accuracy (mean ± SD error of 3.7 ± 5.2% of infant length) compared to gold-standard human annotation. Using body point tracking data, our prediction model achieved a cross-validated area under the curve (mean ± S.D.) of 0.80 ± 0.08 in unseen test data for predicting expert GMs classification with a sensitivity of 76% ± 15% for abnormal GMs and a negative predictive value of 94% ± 3%. This work highlights the potential for automated GMs screening programs to detect abnormal movements in infants as early as three months term-corrected age using digital technologies.

Cortical timescales and the modular organization of structural and functional brain networks

Recent years have seen growing interest in characterizing the properties of regional brain dynamics and their relationship to other features of brain structure and function. In particular, multiple studies have observed regional differences in the "timescale" over which activity fluctuates during periods of quiet rest. In the cerebral cortex, these timescales have been associated with both local circuit properties as well as patterns of inter-regional connectivity, including the extent to which each region exhibits widespread connectivity to other brain areas. In the current study, we build on prior observations of an association between connectivity and dynamics in the cerebral cortex by investigating the relationship between BOLD fMRI timescales and the modular organization of structural and functional brain networks. We characterize network community structure across multiple scales and find that longer timescales are associated with greater within-community functional connectivity and diverse structural connectivity. We also replicate prior observations of a positive correlation between timescales and structural connectivity degree. Finally, we find evidence for preferential functional connectivity between cortical areas with similar timescales. We replicate these findings in an independent dataset. These results contribute to our understanding of functional brain organization and structure-function relationships in the human brain, and support the notion that regional differences in cortical dynamics may in part reflect the topological role of each region within macroscale brain networks.

Deep evolutionary fusion neural network: a new prediction standard for infectious disease incidence rates

BACKGROUND

Previously, many methods have been used to predict the incidence trends of infectious diseases. There are numerous methods for predicting the incidence trends of infectious diseases, and they have exhibited varying degrees of success. However, there are a lack of prediction benchmarks that integrate linear and nonlinear methods and effectively use internet data. The aim of this paper is to develop a prediction model of the incidence rate of infectious diseases that integrates multiple methods and multisource data, realizing ground-breaking research.

RESULTS

The infectious disease dataset is from an official release and includes four national and three regional datasets. The Baidu index platform provides internet data. We choose a single model (seasonal autoregressive integrated moving average (SARIMA), nonlinear autoregressive neural network (NAR), and long short-term memory (LSTM)) and a deep evolutionary fusion neural network (DEFNN). The DEFNN is built using the idea of neural evolution and fusion, and the DEFNN + is built using multisource data. We compare the model accuracy on reference group data and validate the model generalizability on external data. (1) The loss of SA-LSTM in the reference group dataset is 0.4919, which is significantly better than that of other single models. (2) The loss values of SA-LSTM on the national and regional external datasets are 0.9666, 1.2437, 0.2472, 0.7239, 1.4026, and 0.6868. (3) When multisource indices are added to the national dataset, the loss of the DEFNN + increases to 0.4212, 0.8218, 1.0331, and 0.8575.

CONCLUSIONS

We propose an SA-LSTM optimization model with good accuracy and generalizability based on the concept of multiple methods and multiple data fusion. DEFNN enriches and supplements infectious disease prediction methodologies, can serve as a new benchmark for future infectious disease predictions and provides a reference for the prediction of the incidence rates of various infectious diseases.

Personalising intravenous to oral antibiotic switch decision making through fair interpretable machine learning

Antimicrobial resistance (AMR) and healthcare associated infections pose a significant threat globally. One key prevention strategy is to follow antimicrobial stewardship practices, in particular, to maximise targeted oral therapy and reduce the use of indwelling vascular devices for intravenous (IV) administration. Appreciating when an individual patient can switch from IV to oral antibiotic treatment is often non-trivial and not standardised. To tackle this problem we created a machine learning model to predict when a patient could switch based on routinely collected clinical parameters. 10,362 unique intensive care unit stays were extracted and two informative feature sets identified. Our best model achieved a mean AUROC of 0.80 (SD 0.01) on the hold-out set while not being biased to individuals protected characteristics. Interpretability methodologies were employed to create clinically useful visual explanations. In summary, our model provides individualised, fair, and interpretable predictions for when a patient could switch from IV-to-oral antibiotic treatment. Prospectively evaluation of safety and efficacy is needed before such technology can be applied clinically.

Portable Multi-focal Visual Evoked Potential Diagnostics for Multiple Sclerosis/Optic Neuritis patients

Purpose

Multiple Sclerosis (MS) is a neuro-inflammatory disease of the Central Nervous System (CNS) in which the body's immune system attacks and destroys myelin sheath that protects nerve fibers and causes disruption in axonal signal transmission. Demyelinating Optic Neuritis (ON) is often a manifestation of MS and involves inflammation of the optic nerve. ON can cause vision loss, pain and discomfort in the eyes, and difficulties in color perception.In this study, we developed NeuroVEP, a portable, wireless diagnostic system that delivers visual stimuli through a smartphone in a headset and measures evoked potentials at the visual cortex from near the O1, Oz, O2, O9 and O10 locations on the scalp (extended 10-20 system) using custom electroencephalography (EEG) electrodes.

Methods

Each test session is constituted by a short 2.5-minute full-field visual evoked potentials (ffVEP) test, followed by a 12.5-minute multifocal VEP (mfVEP) test. The ffVEP test evaluates the integrity of the visual pathway by analyzing the P1 (also known as P100) component of responses from each eye, while the mfVEP test evaluates 36 individual regions of the visual field for abnormalities. Extensive signal processing, feature extraction methods, and machine learning algorithms were explored for analyzing the mfVEP responses. The results of the ffVEP test for patients were evaluated against normative data collected from a group of subjects with normal vision. Custom visual stimuli with simulated defects were used to validate the mfVEP results which yielded 91% accuracy of classification.

Results

20 subjects, 10 controls and 10 with MS and/or ON were tested with the NeuroVEP device and a standard-of-care (SOC) VEP testing device which delivers only ffVEP stimuli. In 91% of the cases, the ffVEP results agreed between NeuroVEP and SOC device. Where available, the NeuroVEP mfVEP results were in good agreement with Humphrey Automated Perimetry visual field analysis. The lesion locations deduced from the mfVEP data were consistent with Magnetic Resonance Imaging (MRI) and Optical Coherence Tomography (OCT) findings.

Conclusion

This pilot study indicates that NeuroVEP has the potential to be a reliable, portable, and objective diagnostic device for electrophysiology and visual field analysis for neuro-visual disorders.

A reductionist paradigm for high-throughput behavioural fingerprinting in Drosophila melanogaster

Understanding how the brain encodes behaviour is the ultimate goal of neuroscience and the ability to objectively and reproducibly describe and quantify behaviour is a necessary milestone on this path. Recent technological progresses in machine learning and computational power have boosted the development and adoption of systems leveraging on high-resolution video recording to track an animal pose and describe behaviour in all four dimensions. However, the high temporal and spatial resolution that these systems offer must come as a compromise with their throughput and accessibility. Here, we describe coccinella, an open-source reductionist framework combining high-throughput analysis of behaviour using real-time tracking on a distributed mesh of microcomputers (ethoscopes) with resource-lean statistical learning (HCTSA/Catch22). Coccinella is a reductionist system, yet outperforms state-of-the-art alternatives when exploring the pharmacobehaviour in Drosophila melanogaster.

Automatic classification of hyperkinetic, tonic, and tonic-clonic seizures using unsupervised clustering of video signals

Introduction

This study evaluated the accuracy of motion signals extracted from video monitoring data to differentiate epileptic motor seizures in patients with drug-resistant epilepsy. 3D near-infrared video was recorded by the Nelli® seizure monitoring system (Tampere, Finland).

Methods

10 patients with 130 seizures were included in the training dataset, and 17 different patients with 98 seizures formed the testing dataset. Only seizures with unequivocal hyperkinetic, tonic, and tonic-clonic semiology were included. Motion features from the catch22 feature collection extracted from video were explored to transform the patients' videos into numerical time series for clustering and visualization.

Results

Changes in feature generation provided incremental discrimination power to differentiate between hyperkinetic, tonic, and tonic-clonic seizures. Temporal motion features showed the best results in the unsupervised clustering analysis. Using these features, the system differentiated hyperkinetic, tonic and tonic-clonic seizures with 91, 88, and 45% accuracy after 100 cross-validation runs, respectively. F1-scores were 93, 90, and 37%, respectively. Overall accuracy and f1-score were 74%.

Conclusion

The selected features of motion distinguished semiological differences within epileptic seizure types, enabling seizure classification to distinct motor seizure types. Further studies are needed with a larger dataset and additional seizure types. These results indicate the potential of video-based hybrid seizure monitoring systems to facilitate seizure classification improving the algorithmic processing and thus streamlining the clinical workflow for human annotators in hybrid (algorithmic-human) seizure monitoring systems.

Neuromodulation of striatal D1 cells shapes BOLD fluctuations in anatomically connected thalamic and cortical regions

Understanding how the brain's macroscale dynamics are shaped by underlying microscale mechanisms is a key problem in neuroscience. In animal models, we can now investigate this relationship in unprecedented detail by directly manipulating cellular-level properties while measuring the whole-brain response using resting-state fMRI. Here, we focused on understanding how blood-oxygen-level-dependent (BOLD) dynamics, measured within a structurally well-defined striato-thalamo-cortical circuit in mice, are shaped by chemogenetically exciting or inhibiting D1 medium spiny neurons (MSNs) of the right dorsomedial caudate putamen (CPdm). We characterize changes in both the BOLD dynamics of individual cortical and subcortical brain areas, and patterns of inter-regional coupling (functional connectivity) between pairs of areas. Using a classification approach based on a large and diverse set of time-series properties, we found that CPdm neuromodulation alters BOLD dynamics within thalamic subregions that project back to dorsomedial striatum. In the cortex, changes in local dynamics were strongest in unimodal regions (which process information from a single sensory modality) and weakened along a hierarchical gradient towards transmodal regions. In contrast, a decrease in functional connectivity was observed only for cortico-striatal connections after D1 excitation. Our results show that targeted cellular-level manipulations affect local BOLD dynamics at the macroscale, such as by making BOLD dynamics more predictable over time by increasing its self-correlation structure. This contributes to ongoing attempts to understand the influence of structure-function relationships in shaping inter-regional communication at subcortical and cortical levels.

Unifying pairwise interactions in complex dynamics

Scientists have developed hundreds of techniques to measure the interactions between pairs of processes in complex systems, but these computational methods-from contemporaneous correlation coefficients to causal inference methods-define and formulate interactions differently, using distinct quantitative theories that remain largely disconnected. Here we introduce a large assembled library of 237 statistics of pairwise interactions, and assess their behavior on 1,053 multivariate time series from a wide range of real-world and model-generated systems. Our analysis highlights commonalities between disparate mathematical formulations of interactions, providing a unified picture of a rich interdisciplinary literature. Using three real-world case studies, we then show that simultaneously leveraging diverse methods can uncover those most suitable for addressing a given problem, facilitating interpretable understanding of the quantitative formulation of pairwise dependencies that drive successful performance. Our results and accompanying software enable comprehensive analysis of time-series interactions by drawing on decades of diverse methodological contributions.

Depression prediction based on LassoNet-RNN model: A longitudinal study

Depression has become a widespread health concern today. Understanding the influencing factors can promote human mental health as well as provide a basis for exploring preventive measures. Combining LassoNet with recurrent neural network (RNN), this study constructed a screening model ,LassoNet-RNN, for identifying influencing factors of individual depression. Based on multi-wave surveys of China Health and Retirement Longitudinal Study (CHARLS) dataset (11,661 observations), we analyzed the multivariate time series data and recognized 27 characteristic variables selected from four perspectives: demographics, health-related risk factors, household economic status, and living environment. Additionally, the importance rankings of the characteristic variables were obtained. These results offered insightful recommendations for theoretical developments and practical decision making in public health.

Neurophysiological signatures of cortical micro-architecture

Systematic spatial variation in micro-architecture is observed across the cortex. These micro-architectural gradients are reflected in neural activity, which can be captured by neurophysiological time-series. How spontaneous neurophysiological dynamics are organized across the cortex and how they arise from heterogeneous cortical micro-architecture remains unknown. Here we extensively profile regional neurophysiological dynamics across the human brain by estimating over 6800 time-series features from the resting state magnetoencephalography (MEG) signal. We then map regional time-series profiles to a comprehensive multi-modal, multi-scale atlas of cortical micro-architecture, including microstructure, metabolism, neurotransmitter receptors, cell types and laminar differentiation. We find that the dominant axis of neurophysiological dynamics reflects characteristics of power spectrum density and linear correlation structure of the signal, emphasizing the importance of conventional features of electromagnetic dynamics while identifying additional informative features that have traditionally received less attention. Moreover, spatial variation in neurophysiological dynamics is co-localized with multiple micro-architectural features, including gene expression gradients, intracortical myelin, neurotransmitter receptors and transporters, and oxygen and glucose metabolism. Collectively, this work opens new avenues for studying the anatomical basis of neural activity.

Ethoscopy and ethoscope-lab: a framework for behavioural analysis to lower entrance barrier and aid reproducibility

Summary

High-throughput analysis of behaviour is a pivotal instrument in modern neuroscience, allowing researchers to combine modern genetics breakthrough to unbiased, objective, reproducible experimental approaches. To this extent, we recently created an open-source hardware platform (ethoscope; Geissmann Q, Garcia Rodriguez L, Beckwith EJ et al. Rethomics: an R framework to analyse high-throughput behavioural data. PLoS One 2019;14:e0209331) that allows for inexpensive, accessible, high-throughput analysis of behaviour in Drosophila or other animal models. Here we equip ethoscopes with a Python framework for data analysis, ethoscopy, designed to be a user-friendly yet powerful platform, meeting the requirements of researchers with limited coding expertise as well as experienced data scientists.

Availability and implementation

Ethoscopy is best consumed in a prebaked Jupyter-based docker container, ethoscope-lab, to improve accessibility and to encourage the use of notebooks as a natural platform to share post-publication data analysis. Ethoscopy is a Python package available on GitHub and PyPi. Ethoscope-lab is a docker container available on DockerHub. A landing page aggregating all the code and documentation is available at https://lab.gilest.ro/ethoscopy.

A novel systematic pipeline for increased predictability and explainability of growth patterns in children using trajectory features

OBJECTIVE

Longitudinal patterns of growth in early childhood are associated with health conditions throughout life. Knowledge of such patterns and the ability to predict them can lead to better prevention and improved health promotion in adulthood. However, growth analyses are characterized by significant variability, and pattern detection is affected by the method applied. Moreover, pattern labelling is typically performed based on ad hoc methods, such as visualizations or clinical experience. Here, we propose a novel pipeline using features extracted from growth trajectories using mathematical, statistical and machine-learning approaches to predict growth patterns and label them in a systematic and unequivocal manner.

METHODS

We extracted mathematical and clinical features from 9577 children growth trajectories embedded with machine-learning predictions of the growth patterns. We experimented with two sets of features (CAnonical Time-series Characteristics and trajectory features specific to growth), developmental periods and six machine-learning classifiers. Clinical experts provided labels for the detected patterns and decision rules were created to associate the features with the labelled patterns. The predictive capacity of the extracted features was validated on two heterogenous populations (The Applied Research Group for Kids and the 2004 Pelotas Birth Cohort, based in Canada and Brazil, respectively).

RESULTS

Features predictive ability measured by accuracy and F1 score was ≥ 80% and ≥ 0.76 respectively in both cohorts. A small number of features (n = 74) was sufficient to distinguish between growth patterns in both cohorts. Slope, intercept of the trajectory, age at peak value, start value and change of the growth measure were among the top identified features.

CONCLUSION

Growth features can be reliably used as predictors of growth patterns and provide an unbiased understanding of growth patterns. They can be used as tool to reduce the effort to repeat analysis and variability concerning anthropometric measures, time points and analytical methods, in the context of the same or similar populations.

Physiological Signals and Affect as Predictors of Advertising Engagement

This study investigated the use of affect and physiological signals of heart rate, electrodermal activity, pupil dilation, and skin temperature to classify advertising engagement. The ground truth for the affective and behavioral aspects of ad engagement was collected from 53 young adults using the User Engagement Scale. Three gradient-boosting classifiers, LightGBM (LGBM), HistGradientBoostingClassifier (HGBC), and XGBoost (XGB), were used along with signal fusion to evaluate the performance of different signal combinations as predictors of engagement. The classifiers trained on the fusion of skin temperature, valence, and tiredness (features n = 5) performed better than those trained on all signals (features n = 30). The average AUC ROC scores for the fusion set were XGB = 0.68 (0.10), LGBM = 0.69 (0.07), and HGBC = 0.70 (0.11), compared to the lower scores for the set of all signals (XGB = 0.65 (0.11), LGBM = 0.66 (0.11), HGBC = 0.64 (0.10)). The results also show that the signal fusion set based on skin temperature outperforms the fusion sets of the other three signals. The main finding of this study is the role of specific physiological signals and how their fusion aids in more effective modeling of ad engagement while reducing the number of features.

Predicting mortality risk after a fall in older adults using health care spending patterns: a population-based cohort study

OBJECTIVE

To develop a prognostic model of 1-year mortality for individuals aged 65+ presenting at the emergency department (ED) with a fall based on health care spending patterns to guide clinical decision-making.

DESIGN

Population-based cohort study (n = 35,997) included with a fall in 2013 and followed 1 year.

METHODS

Health care spending indicators (dynamical indicators of resilience, DIORs) 2 years before admission were evaluated as potential predictors, along with age, sex and other clinical and sociodemographic covariates. Multivariable logistic regression models were developed and internally validated (10-fold cross-validation). Performance was assessed via discrimination (area under the receiver operating characteristic curve, AUC), Brier scores, calibration and decision curve analysis.

RESULTS

The AUC of age and sex for mortality was 72.5% [95% confidence interval 71.8 to 73.2]. The best model included age, sex, number of medications and health care spending DIORs. It exhibited high discrimination (AUC: 81.1 [80.5 to 81.6]), good calibration and potential clinical benefit for various threshold probabilities. Overall, health care spending patterns improved predictive accuracy the most while also exhibiting superior performance and clinical benefit.

CONCLUSIONS

Patterns of health care spending have the potential to significantly improve assessments on who is at high risk of dying following admission to the ED with a fall. The proposed methodology can assist in predicting the prognosis of fallers, emphasising the added predictive value of longitudinal health-related information next to clinical and sociodemographic predictors.

Cortical timescales and the modular organization of structural and functional brain networks

Recent years have seen growing interest in characterizing the properties of regional brain dynamics and their relationship to other features of brain structure and function. In particular, multiple studies have observed regional differences in the "timescale" over which activity fluctuates during periods of quiet rest. In the cerebral cortex, these timescales have been associated with both local circuit properties as well as patterns of inter-regional connectivity, including the extent to which each region exhibits widespread connectivity to other brain areas. In the current study, we build on prior observations of an association between connectivity and dynamics in the cerebral cortex by investigating the relationship between BOLD fMRI timescales and the modular organization of structural and functional brain networks. We characterize network community structure across multiple scales and find that longer timescales are associated with greater within-community functional connectivity and diverse structural connectivity. We also replicate prior observations of a positive correlation between timescales and structural connectivity degree. Finally, we find evidence for preferential functional connectivity between cortical areas with similar timescales. We replicate these findings in an independent dataset. These results contribute to our understanding of functional brain organization and structure-function relationships in the human brain, and support the notion that regional differences in cortical dynamics may in part reflect the topological role of each region within macroscale brain networks.

Scalable Gromov-Wasserstein Based Comparison of Biological Time Series

A time series is an extremely abundant data type arising in many areas of scientific research, including the biological sciences. Any method that compares time series data relies on a pairwise distance between trajectories, and the choice of distance measure determines the accuracy and speed of the time series comparison. This paper introduces an optimal transport type distance for comparing time series trajectories that are allowed to lie in spaces of different dimensions and/or with differing numbers of points possibly unequally spaced along each trajectory. The construction is based on a modified Gromov-Wasserstein distance optimization program, reducing the problem to a Wasserstein distance on the real line. The resulting program has a closed-form solution and can be computed quickly due to the scalability of the one-dimensional Wasserstein distance. We discuss theoretical properties of this distance measure, and empirically demonstrate the performance of the proposed distance on several datasets with a range of characteristics commonly found in biologically relevant data. We also use our proposed distance to demonstrate that averaging oscillatory time series trajectories using the recently proposed Fused Gromov-Wasserstein barycenter retains more characteristics in the averaged trajectory when compared to traditional averaging, which demonstrates the applicability of Fused Gromov-Wasserstein barycenters for biological time series. Fast and user friendly software for computing the proposed distance and related applications is provided. The proposed distance allows fast and meaningful comparison of biological time series and can be efficiently used in a wide range of applications.

Towards an objective theory of subjective liking: A first step in understanding the sense of beauty

The study of the electroencephalogram signals recorded from subjects during an experience is a way to understand the brain processes that underlie their physical and emotional involvement. Such signals have the form of time series, and their analysis could benefit from applying techniques that are specific to this kind of data. Neuroaesthetics, as defined by Zeki in 1999, is the scientific approach to the study of aesthetic perceptions of art, music, or any other experience that can give rise to aesthetic judgments, such as liking or disliking a painting. Starting from a proprietary dataset of 248 trials from 16 subjects exposed to art paintings, using a real ecological context, this paper analyses the application of a novel symbolic machine learning technique, specifically designed to extract information from unstructured data and to express it in form of logical rules. Our purpose is to extract qualitative and quantitative logical rules, to relate the voltage at specific frequencies and in specific electrodes, and that, within the limits of the experiment, may help to understand the brain process that drives liking or disliking experiences in human subjects.

The voice of COVID-19: Breath and cough recording classification with temporal decision trees and random forests

Symbolic learning is the logic-based approach to machine learning, and its mission is to provide algorithms and methodologies to extract logical information from data and express it in an interpretable way. Interval temporal logic has been recently proposed as a suitable tool for symbolic learning, specifically via the design of an interval temporal logic decision tree extraction algorithm. In order to improve their performances, interval temporal decision trees can be embedded into interval temporal random forests, mimicking the corresponding schema at the propositional level. In this article we consider a dataset of cough and breath sample recordings of volunteer subjects, labeled with their COVID-19 status, originally collected by the University of Cambridge. By interpreting such recordings as multivariate time series, we study the problem of their automated classification using interval temporal decision trees and forests. While this problem has been approached with the same dataset as well as with other datasets, in all cases, non-symbolic learning methods (usually, deep learning-based) have been applied to solve it; in this article we apply a symbolic approach, and show that it does not only outperform the state-of-the-art obtained with the same dataset, but its results are also superior to those of most non-symbolic techniques applied on other datasets. As an added bonus, thanks to the symbolic nature of our approach, we are also able to extract explicit knowledge to help physicians characterize typical COVID-positive cough and breath.

Neurophysiological signatures of cortical micro-architecture

Systematic spatial variation in micro-architecture is observed across the cortex. These micro-architectural gradients are reflected in neural activity, which can be captured by neurophysiological time-series. How spontaneous neurophysiological dynamics are organized across the cortex and how they arise from heterogeneous cortical micro-architecture remains unknown. Here we extensively profile regional neurophysiological dynamics across the human brain by estimating over 6 800 timeseries features from the resting state magnetoencephalography (MEG) signal. We then map regional time-series profiles to a comprehensive multi-modal, multi-scale atlas of cortical micro-architecture, including microstructure, metabolism, neurotransmitter receptors, cell types and laminar differentiation. We find that the dominant axis of neurophysiological dynamics reflects characteristics of power spectrum density and linear correlation structure of the signal, emphasizing the importance of conventional features of electromagnetic dynamics while identifying additional informative features that have traditionally received less attention. Moreover, spatial variation in neurophysiological dynamics is colocalized with multiple micro-architectural features, including genomic gradients, intracortical myelin, neurotransmitter receptors and transporters, and oxygen and glucose metabolism. Collectively, this work opens new avenues for studying the anatomical basis of neural activity.

Subtyping patients with chronic disease using longitudinal BMI patterns

Obesity is a major health problem, increasing the risk of various major chronic diseases, such as diabetes, cancer, and stroke. While the role of obesity identified by cross-sectional BMI recordings has been heavily studied, the role of BMI trajectories is much less explored. In this study, we use a machine learning approach to subtype individuals' risk of developing 18 major chronic diseases by using their BMI trajectories extracted from a large and geographically diverse EHR dataset capturing the health status of around two million individuals for a period of six years. We define nine new interpretable and evidence-based variables based on the BMI trajectories to cluster the patients into subgroups using the k-means clustering method. We thoroughly review each cluster's characteristics in terms of demographic, socioeconomic, and physiological measurement variables to specify the distinct properties of the patients in the clusters. In our experiments, the direct relationship of obesity with diabetes, hypertension, Alzheimer's, and dementia has been re-established and distinct clusters with specific characteristics for several of the chronic diseases have been found to be conforming or complementary to the existing body of knowledge.

Passive Fingerprinting of Same-Model Electrical Devices by Current Consumption

One possible device authentication method is based on device fingerprints, such as software- or hardware-based unique characteristics. In this paper, we propose a fingerprinting technique based on passive externally measured information, i.e., current consumption from the electrical network. The key insight is that small hardware discrepancies naturally exist even between same-electrical-circuit devices, making it feasible to identify slight variations in the consumed current under steady-state conditions. An experimental database of current consumption signals of two similar groups containing 20 same-model computer displays was collected. The resulting signals were classified using various state-of-the-art time-series classification (TSC) methods. We successfully identified 40 similar (same-model) electrical devices with about 94% precision, while most errors were concentrated in confusion between a small number of devices. A simplified empirical wavelet transform (EWT) paired with a linear discriminant analysis (LDA) classifier was shown to be the recommended classification method.

Forecast evaluation for data scientists: common pitfalls and best practices

Recent trends in the Machine Learning (ML) and in particular Deep Learning (DL) domains have demonstrated that with the availability of massive amounts of time series, ML and DL techniques are competitive in time series forecasting. Nevertheless, the different forms of non-stationarities associated with time series challenge the capabilities of data-driven ML models. Furthermore, due to the domain of forecasting being fostered mainly by statisticians and econometricians over the years, the concepts related to forecast evaluation are not the mainstream knowledge among ML researchers. We demonstrate in our work that as a consequence, ML researchers oftentimes adopt flawed evaluation practices which results in spurious conclusions suggesting methods that are not competitive in reality to be seemingly competitive. Therefore, in this work we provide a tutorial-like compilation of the details associated with forecast evaluation. This way, we intend to impart the information associated with forecast evaluation to fit the context of ML, as means of bridging the knowledge gap between traditional methods of forecasting and adopting current state-of-the-art ML techniques.We elaborate the details of the different problematic characteristics of time series such as non-normality and non-stationarities and how they are associated with common pitfalls in forecast evaluation. Best practices in forecast evaluation are outlined with respect to the different steps such as data partitioning, error calculation, statistical testing, and others. Further guidelines are also provided along selecting valid and suitable error measures depending on the specific characteristics of the dataset at hand.

When less is more powerful: Shapley value attributed ablation with augmented learning for practical time series sensor data classification

Time series sensor data classification tasks often suffer from training data scarcity issue due to the expenses associated with the expert-intervened annotation efforts. For example, Electrocardiogram (ECG) data classification for cardio-vascular disease (CVD) detection requires expensive labeling procedures with the help of cardiologists. Current state-of-the-art algorithms like deep learning models have shown outstanding performance under the general requirement of availability of large set of training examples. In this paper, we propose Shapley Attributed Ablation with Augmented Learning: ShapAAL, which demonstrates that deep learning algorithm with suitably selected subset of the seen examples or ablating the unimportant ones from the given limited training dataset can ensure consistently better classification performance under augmented training. In ShapAAL, additive perturbed training augments the input space to compensate the scarcity in training examples using Residual Network (ResNet) architecture through perturbation-induced inputs, while Shapley attribution seeks the subset from the augmented training space for better learnability with the goal of better general predictive performance, thanks to the "efficiency" and "null player" axioms of transferable utility games upon which Shapley value game is formulated. In ShapAAL, the subset of training examples that contribute positively to a supervised learning setup is derived from the notion of coalition games using Shapley values associated with each of the given inputs' contribution into the model prediction. ShapAAL is a novel push-pull deep architecture where the subset selection through Shapley value attribution pushes the model to lower dimension while augmented training augments the learning capability of the model over unseen data. We perform ablation study to provide the empirical evidence of our claim and we show that proposed ShapAAL method consistently outperforms the current baselines and state-of-the-art algorithms for time series sensor data classification tasks from publicly available UCR time series archive that includes different practical important problems like detection of CVDs from ECG data.

Voltage imaging reveals the dynamic electrical signatures of human breast cancer cells

Cancer cells feature a resting membrane potential (Vm) that is depolarized compared to normal cells, and express active ionic conductances, which factor directly in their pathophysiological behavior. Despite similarities to ‘excitable’ tissues, relatively little is known about cancer cell Vm dynamics. Here high-throughput, cellular-resolution Vm imaging reveals that Vm fluctuates dynamically in several breast cancer cell lines compared to non-cancerous MCF-10A cells. We characterize Vm fluctuations of hundreds of human triple-negative breast cancer MDA-MB-231 cells. By quantifying their Dynamic Electrical Signatures (DESs) through an unsupervised machine-learning protocol, we identify four classes ranging from "noisy” to “blinking/waving“. The Vm of MDA-MB-231 cells exhibits spontaneous, transient hyperpolarizations inhibited by the voltage-gated sodium channel blocker tetrodotoxin, and by calcium-activated potassium channel inhibitors apamin and iberiotoxin. The Vm of MCF-10A cells is comparatively static, but fluctuations increase following treatment with transforming growth factor-β1, a canonical inducer of the epithelial-to-mesenchymal transition. These data suggest that the ability to generate Vm fluctuations may be a property of hybrid epithelial-mesenchymal cells or those originated from luminal progenitors.

COVID-19 screening with digital holographic microscopy using intra-patient probability functions of spatio-temporal bio-optical attributes

We present an automated method for COVID-19 screening using the intra-patient population distributions of bio-optical attributes extracted from digital holographic microscopy reconstructed red blood cells. Whereas previous approaches have aimed to identify infection by classifying individual cells, here, we propose an approach to incorporate the attribute distribution information from the population of a given human subjects' cells into our classification scheme and directly classify subjects at the patient level. To capture the intra-patient distribution information in a generalized way, we propose an approach based on the Bag-of-Features (BoF) methodology to transform histograms of bio-optical attribute distributions into feature vectors for classification via a linear support vector machine. We compare our approach with simpler classifiers directly using summary statistics such as mean, standard deviation, skewness, and kurtosis of the distributions. We also compare to a k-nearest neighbor classifier using the Kolmogorov-Smirnov distance as a distance metric between the attribute distributions of each subject. We lastly compare our approach to previously published methods for classification of individual red blood cells. In each case, the methodology proposed in this paper provides the highest patient classification performance, correctly classifying 22 out of 24 individuals and achieving 91.67% classification accuracy with 90.00% sensitivity and 92.86% specificity. The incorporation of distribution information for classification additionally led to the identification of a singular temporal-based bio-optical attribute capable of highly accurate patient classification. To the best of our knowledge, this is the first report of a machine learning approach using the intra-patient probability distribution information of bio-optical attributes obtained from digital holographic microscopy for disease screening.

High-Resolution Digital Phenotypes From Consumer Wearables and Their Applications in Machine Learning of Cardiometabolic Risk Markers: Cohort Study

BACKGROUND

Consumer-grade wearable devices enable detailed recordings of heart rate and step counts in free-living conditions. Recent studies have shown that summary statistics from these wearable recordings have potential uses for longitudinal monitoring of health and disease states. However, the relationship between higher resolution physiological dynamics from wearables and known markers of health and disease remains largely uncharacterized.

OBJECTIVE

We aimed to derive high-resolution digital phenotypes from observational wearable recordings and to examine their associations with modifiable and inherent markers of cardiometabolic disease risk.

METHODS

We introduced a principled framework to extract interpretable high-resolution phenotypes from wearable data recorded in free-living conditions. The proposed framework standardizes the handling of data irregularities; encodes contextual information regarding the underlying physiological state at any given time; and generates a set of 66 minimally redundant features across active, sedentary, and sleep states. We applied our approach to a multimodal data set, from the SingHEART study (NCT02791152), which comprises heart rate and step count time series from wearables, clinical screening profiles, and whole genome sequences from 692 healthy volunteers. We used machine learning to model nonlinear relationships between the high-resolution phenotypes on the one hand and clinical or genomic risk markers for blood pressure, lipid, weight and sugar abnormalities on the other. For each risk type, we performed model comparisons based on Brier scores to assess the predictive value of high-resolution features over and beyond typical baselines. We also qualitatively characterized the wearable phenotypes for participants who had actualized clinical events.

RESULTS

We found that the high-resolution features have higher predictive value than typical baselines for clinical markers of cardiometabolic disease risk: the best models based on high-resolution features had 17.9% and 7.36% improvement in Brier score over baselines based on age and gender and resting heart rate, respectively (P<.001 in each case). Furthermore, heart rate dynamics from different activity states contain distinct information (maximum absolute correlation coefficient of 0.15). Heart rate dynamics in sedentary states are most predictive of lipid abnormalities and obesity, whereas patterns in active states are most predictive of blood pressure abnormalities (P<.001). Moreover, in comparison with standard measures, higher resolution patterns in wearable heart rate recordings are better able to represent subtle physiological dynamics related to genomic risk for cardiometabolic disease (improvement of 11.9%-22.0% in Brier scores; P<.001). Finally, illustrative case studies reveal connections between these high-resolution phenotypes and actualized clinical events, even for borderline profiles lacking apparent cardiometabolic risk markers.

CONCLUSIONS

High-resolution digital phenotypes recorded by consumer wearables in free-living states have the potential to enhance the prediction of cardiometabolic disease risk and could enable more proactive and personalized health management.

Enhanced motor cortex output and disinhibition in asymptomatic female mice with C9orf72 genetic expansion

Information and action coding by cortical circuits relies on a balanced dialogue between excitation and inhibition. Circuit hyperexcitability is considered a potential pathophysiological mechanism in various brain disorders, but the underlying deficits, especially at early disease stages, remain largely unknown. We report that asymptomatic female mice carrying the chromosome 9 open reading frame 72 (C9orf72) repeat expansion, which represents a high-prevalence genetic abnormality for human amyotrophic lateral sclerosis (ALS) and frontotemporal lobar degeneration (FTLD) spectrum disorder, exhibit abnormal motor cortex output. The number of primary motor cortex (M1) layer 5 pyramidal neurons is reduced in asymptomatic mice, with the surviving neurons receiving a decreased inhibitory drive that results in a higher M1 output, specifically during high-speed animal locomotion. Importantly, using deep-learning algorithms revealed that speed-dependent M1 output predicts the likelihood of C9orf72 genetic expansion. Our data link early circuit abnormalities with a gene mutation in asymptomatic ALS/FTLD carriers.

MultiRocket: multiple pooling operators and transformations for fast and effective time series classification

We propose MultiRocket, a fast time series classification (TSC) algorithm that achieves state-of-the-art accuracy with a tiny fraction of the time and without the complex ensembling structure of many state-of-the-art methods. MultiRocket improves on MiniRocket, one of the fastest TSC algorithms to date, by adding multiple pooling operators and transformations to improve the diversity of the features generated. In addition to processing the raw input series, MultiRocket also applies first order differences to transform the original series. Convolutions are applied to both representations, and four pooling operators are applied to the convolution outputs. When benchmarked using the University of California Riverside TSC benchmark datasets, MultiRocket is significantly more accurate than MiniRocket, and competitive with the best ranked current method in terms of accuracy, HIVE-COTE 2.0, while being orders of magnitude faster.

Behavioral Change Prediction from Physiological Signals Using Deep Learned Features

Predicting change from multivariate time series has relevant applications ranging from the medical to engineering fields. Multisensory stimulation therapy in patients with dementia aims to change the patient's behavioral state. For example, patients who exhibit a baseline of agitation may be paced to change their behavioral state to relaxed. This study aimed to predict changes in one's behavioral state from the analysis of the physiological and neurovegetative parameters to support the therapist during the stimulation session. In order to extract valuable indicators for predicting changes, both handcrafted and learned features were evaluated and compared. The handcrafted features were defined starting from the CATCH22 feature collection, while the learned ones were extracted using a temporal convolutional network, and the behavioral state was predicted through bidirectional long short-term memory auto-encoder, operating jointly. From the comparison with the state of the art, the learned features-based approach exhibits superior performance with accuracy rates of up to 99.42% with a time window of 70 seconds and up to 98.44% with a time window of 10 seconds.

Novel features for time series analysis: a complex networks approach

Being able to capture the characteristics of a time series with a feature vector is a very important task with a multitude of applications, such as classification, clustering or forecasting. Usually, the features are obtained from linear and nonlinear time series measures, that may present several data related drawbacks. In this work we introduce NetF as an alternative set of features, incorporating several representative topological measures of different complex networks mappings of the time series. Our approach does not require data preprocessing and is applicable regardless of any data characteristics. Exploring our novel feature vector, we are able to connect mapped network features to properties inherent in diversified time series models, showing that NetF can be useful to characterize time data. Furthermore, we also demonstrate the applicability of our methodology in clustering synthetic and benchmark time series sets, comparing its performance with more conventional features, showcasing how NetF can achieve high-accuracy clusters. Our results are very promising, with network features from different mapping methods capturing different properties of the time series, adding a different and rich feature set to the literature.

Discovery of signatures of fatal neonatal illness in vital signs using highly comparative time-series analysis

To seek new signatures of illness in heart rate and oxygen saturation vital signs from Neonatal Intensive Care Unit (NICU) patients, we implemented highly comparative time-series analysis to discover features of all-cause mortality in the next 7 days. We collected 0.5 Hz heart rate and oxygen saturation vital signs of infants in the University of Virginia NICU from 2009 to 2019. We applied 4998 algorithmic operations from 11 mathematical families to random daily 10 min segments from 5957 NICU infants, 205 of whom died. We clustered the results and selected a representative from each, and examined multivariable logistic regression models. 3555 operations were usable; 20 cluster medoids held more than 81% of the information, and a multivariable model had AUC 0.83. New algorithms outperformed others: moving threshold, successive increases, surprise, and random walk. We computed provenance of the computations and constructed a software library with links to the data. We conclude that highly comparative time-series analysis revealed new vital sign measures to identify NICU patients at the highest risk of death in the next week.