Publications using hctsa

This page lists scientific research publications that have used hctsa

Where journal articles (📗) are not open access, we also provide a link to the preprint (📙). Links to Github code repositories (:octocat:) are provided where possible.

Our Research 📕

Methods papers

The following publications for details of how the highly-comparative approach to time-series analysis has developed since our initial publication in 2013. We:

• Reduced the hctsa feature library down to a reduced set of 22 efficiently coded features: catch22.
  • 📗 CAnonical Time-series CHaracteristics. Data Mining and Knowledge Discovery 33, 1821 (2019).
  • catch22 Code.
• Developed a software package for highly-comparative time-series analysis, hctsa (includes applications to high throughput phenotyping of C. Elegans and Drosophila movement time series).
  • 📗 hctsa: A Computational Framework for Automated Time-Series Phenotyping Using Massive Feature Extraction. Cell Systems 5, 527 (2017).
  • Code (fly) & Code (worm).
• Introduced the feature-based time-series analysis methodology
  • 📗 Feature-based time-series analysis. Feature Engineering for Machine Learning and Data Analytics, CRC Press (2018). 📙 Preprint.
• Showed that the behavior of thousands of time-series methods on thousands of different time series can be used to organize the interdisciplinary time-series analysis literature
  • 📗 Highly comparative time-series analysis: the empirical structure of time series and their methods. J. Roy. Soc. Interface (2013).

Applications papers

We have used hctsa to:

• (in combination with pyspi) to find dynamical signatures of psychiatric disorders from resting-state fMRI data.
  • 📙 bioRxiv (2023).
• Predict individual response to rTMS depression treatment from EEG data.
  • 📙 medRxiv (2023).
• Distinguish meditators from non-meditators from 30s of resting-state EEG data.
  • 📗 Neural Networks (2023).
• Identify neurophysiological signatures of cortical micro-architecture.
  • 📗 Nature Communications (2023).
• Classify stars from NASA's Kepler Mission.
  • 📗 Monthly Notices of the Royal Astronomical Society (2022).
• Determine how striatal neuromodulation affect brain dynamics in thalamus and cortex.
  • 📗 eLife (2023).
• Uncover the dynamical structure of sleep EEG.
  • 📗 Sleep Medicine (2022).
• Show how gradients of variation in time-series properties of BOLD dynamics vary with physiological variation and structural connectivity in the human neocortex.
  • 📗 eLife (2020).
• Distinguish targeted perturbations to mouse fMRI dynamics
  • 📗 Cerebral Cortex (2020).
  • Code.
• Connect structural brain connectivity to fMRI dynamics (mouse)
  • 📗 Chaos (2017).
• Connect structural brain connectivity to fMRI dynamics (human)
  • 📗 Network Neuroscience (2020).
• Distinguish time-series patterns for data-mining applications
  • 📗 IEEE Trans. Knowl. Data Eng. (2014).
• Classify babies with low blood pH from fetal heart rate time series
  • 📗 34th Ann. Int. Conf. IEEE EMBC (2012).

Others' Research 📕

(Let me know if I've missed any!)

hctsa has also been used to:

Biology

• Extract acoustic features from social vocal accommodation in adult marmoset monkeys. 📙 bioRxiv (2023).
• Track Drosophila in real time for high-throughput behavioral phenotyping. 📗 eLife (2023).
• Detect anger from photoplethysmography (PPG) sensors 📗 Journal of NeuroEngineering and Rehabilitation (2023).
• Identify and distinguish marmoset vocalisations from audio, using Adaboost feature selection from hctsa features 📗 J. Roy. Soc. Interface (2023).
• Discriminate zebra finch songs in different social contexts. 📗 PLoS Computational Biology (2021).
• Distinguish electromagnetic field exposure from zebrafish locomotion time series. 📗 Sensors (2020).

Cellular Neuroscience

• Assess stress-induced changes in astrocyte calcium dynamics. 📗 Nature Communications (2020).
• Assess the stress controllability of neurons from their activity time series. 📗 Nature Neuroscience (2020).

Neuroimaging

• Understand changes in fMRI brain dynamics in patients with epilepsy 📗 Communications Biology (2024).
• Extract EEG markers of cognitive decline. 📗 npj Aging (2024).
• Detect EEG markers of seizure disorders. 📗 Brain Communications (2023).
• Estimate brain age in children from EEG. 📗 45th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (2023)
• Capture a distinctive fingerprint of a individual's resting-state fMRI data. 📙 ResearchSquare (2023).
• As a partial source of features for building a cognitive assessment model from resting-state EEG 📙 ResearchSquare (2023).
• Identify methamphetamine users from EEG time series 📙 ResearchSquare (2023).
• Compute temporal profile similarity for individual fingerprinting from human fMRI data. 📗 Network Neuroscience (2023).
• Extract gradients from fMRI hctsa time-series features to understand the relationship between schizophrenia and nicotine dependence. 📗 Cerebral Cortex (2023).
• Classify endogenous (preictal), interictal, and seizure-like (ictal) activity from local field potentials (LFPs) from layers II/III of the primary somatosensory cortex of young mice (using feature selection methods from an initial pool of hctsa features). 📙 SciTePress (2023).
• Characterize subnetworks of the frontoparietal control network from fMRI recordings. 📙 bioRxiv (2023).
• Distinguish motor-evoked potentials corresponding to multiple sclerosis. 📗 Front. Neuroinform. (2020).
• Find time-series properties of motor-evoked potentials that predict multiple sclerosis progression after two years. 📗 BMC Neurology (2020).
• Detect mild cognitive impairment using single-channel EEG to measure speech-evoked brain responses. 📗 IEEE Transactions on Neural Systems and Rehabilitation Engineering (2019).

Medicine—General

• Differentiate tremor disorders using massive feature extraction, outperforming the best traditional tremor statistic. 📙 MedRxiv (2024).
• Identify sepsis in very low birth weight (<1.5kg) infants from heart rate signals, identifying heart rate characteristics of reduced variability and transient decelerations. 📙 MedRxiv (2024)
• Identify physiological features predictive of respiratory outcomes in extremely pre-term infants from bedside monitor data. 📙 MedRxiv (2024)
• Identify novel heart-rate variability metrics, including RobustSD, to create a parsimonious model for cerebral palsy prediction in preterm neonatal intensive care unit patients. 📗 Pediatric Research (2023).
• Predicting post cardiac arrest outcomes. 📗 Anaesthesia Critical Care & Pain Medicine (2022).
• Discover signatures of fatal neonatal illness from vital signs. 📗 npj Digital Medicine (2022).
• Prediction of post-cardiac arrest outcomes at discharge from physiological time series recorded on the first day of intensive care. 📗 Anaesthesia Critical Care & Pain Medicine (2021).
• Detect falls from wearable sensor data. 📗 Scientific Reports (2021).
• Detect falls from wearable sensor data. 📗 Biosensors (2021).
• Detect falls in elderly people from accelerometer data. 📗 IEEE International Conference on Information and Communication Technology for Sustainable Development (2021).
• Detect falls of elderly people using wearable sensors. 📗 IEEE Access (2021).
• Demonstrate that the suppression of essential tremor is due to a disruption of oscillations in the olivocerebellar loop. 📗 Nature Communications (2021).
• Classify heartbeats measured using single-lead ECG. 📗 IEEE 42nd International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO) (2019).
• Assess muscles for clinical rehabilitation. 📗 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (2017).
• Select features for fetal heart rate analysis using genetic algorithms. 📗 Physiological Measurement (2014).

Medicine—Pathology

• Screen for COVID-19 using digital holographic microscopy. 📗 Biomedical Optics Express (2022).
• Detect COVID-19 from red blood cells using digital holographic microscopy. 📗 Optics Express (2022).
• Identify the biogeographic heterogeneity of mucus, lumen, and feces. 📗 PNAS (2021).

Engineering

• Detect keyhole porosity formation during laser irradiation of Ti-6Al-4V substrates. 📗 Additive Manufacturing (2023).
• Diagnose a spacecraft propulsion system utilizing data provided by the Prognostics and Health Management (PHM) society, as part of the Asia-Pacific PHM conference’s data challenge, 2023. 📗 Proceedings of the Asia Pacific Conference of the PHM Society (2023).
• Identify keyhole pores in a laser powder-bed fusion process using acoustic and inline pyrometry time series. 📗 Journal of Materials Processing Technology (2022).
• Identify faults in a large-scale industrial process. PhD Thesis.
• Detect false data injection attacks into smart meters. 📗 IEEE Access (2021).
• Predict pending loss of power stability from generator response signals. 📗 IEEE Access (2021).
• Detect seeded bearing faults on a wind turbine subjected to non-stationary wind speed 📗 Proceedings of the Seventeenth International Conference on Condition Monitoring and Asset Management (2021).
• Recognize hand gestures. 📗 PLoS ONE (2020).
• Distinguish energy use behaviors from smart meter data. 📗 Energy and Buildings (2019).
• Non-intrusively monitor load for appliance detection and electrical power saving in buildings. 📗 Energy and Buildings (2019).
• Evaluate asphalt irregularity from smartphone sensors. 📗 International Symposium on Intelligent Data Analysis (2018).

Geoscience

• Detecting earthquakes from seismic recordings 📗 Geophysical Prospecting (2023).
• Find temporal patterns for reconstructing surface soil moisture time series 📗 Journal of Hydrology (2023).
• Predict earthquakes (in the following month) from seismic indicators in Bangladesh. 📗 IEEE Access (2021).
• Detect earthquakes in Groningen, The Netherlands. 📗 82nd EAGE Annual Conference & Exhibition Workshop Programme (2020).