# Publications using hctsa Articles are labeled as follows: * πŸ“— = Journal publication. * πŸ“™ = Preprint. * :computer: = Link to GitHub code repository available. If you have used *hctsa* in your published work, or we have missed any publications, feel free to reach out by [email](mailto:ben.d.fulcher@gmail.com) and we'll add it this growing list! *** ## Our Research πŸ“• ### 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.

πŸ“— Data Mining and Knowledge Discovery 33, 1821 (2019).

πŸ’» catch22 Code.

10618_2019_647_Fig5_HTML.png.webphttps://link.springer.com/article/10.1007/s10618-019-00647-x

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).

πŸ“— Cell Systems 5, 527 (2017).

πŸ’» Code (fly).

πŸ’» Code (worm).

Screenshot 2024-05-11 at 6.27.14β€―am.pnghttps://www.cell.com/cell-systems/fulltext/S2405-4712(17)30438-6

Introduced the feature-based time-series analysis methodology.

πŸ“— Feature Engineering for Machine Learning and Data Analytics, CRC Press (2018).

πŸ“™ Preprint.

Screenshot 2024-05-11 at 6.32.02β€―am.pnghttps://www.crcpress.com/Feature-Engineering-for-Machine-Learning-and-Data-Analytics/Dong-Liu/p/book/9781138744387

Showed that the behaviour of thousands of time-series methods on thousands of different time series can be used to organise the interdisciplinary time-series analysis literature.

πŸ“— J. Roy. Soc. Interface (2013).

rsif20130048f05.jpghttps://royalsocietypublishing.org/doi/full/10.1098/rsif.2013.0048
*** ### Applications Papers We have used *hctsa* to:

Find dynamical signatures of psychiatric disorders from resting-state fMRI data.

πŸ“— PLoS Comp. Biol. (2024).

Screenshot 2024-05-10 at 2.05.57β€―pm.pnghttps://www.biorxiv.org/content/10.1101/2024.01.10.573372v1

Predict individual response to rTMS depression treatment from EEG data.

πŸ“™ medRxiv (2023).

Screenshot 2024-05-10 at 2.08.30β€―pm.pnghttps://www.medrxiv.org/content/10.1101/2023.10.24.23297492v1

Distinguish meditators from non-meditators from 30s of resting-state EEG data.

πŸ“— Neural Networks (2023).

1-s2.0-S0893608023007013-gr1.jpghttps://www.sciencedirect.com/science/article/pii/S0893608023007013?via%3Dihub

Identify neurophysiological signatures of cortical micro-architecture.

πŸ“— Nature Comms. (2023).

41467_2023_41689_Fig1_HTML.png.webphttps://www.nature.com/articles/s41467-023-41689-6

Classify stars from NASA's Kepler Mission.

πŸ“— Monthly Notices of the Royal Astronomical Society (2022).

stac1515fig2.jpeghttps://academic.oup.com/HTTPHandlers/Sigma/LoginHandler.ashx?error=login_required&state=3b05040c-72f2-4071-a0fa-043c19da7236redirecturl%3Dhttpszazjzjacademiczwoupzwcomzjmnraszjarticlezj514zj2zj2793zj6598817

Determine how striatal neuromodulation affects brain dynamics in thalamus and cortex.

πŸ“— eLife (2023).

Screenshot 2024-05-10 at 2.22.19β€―pm.pnghttps://elifesciences.org/articles/78620

Uncover the dynamical structure of sleep EEG.

πŸ“— Sleep Medicine (2022).

1-s2.0-S1389945722010516-ga1_lrg.jpghttps://www.sciencedirect.com/science/article/pii/S1389945722010516?via%3Dihub

Show how gradients of variation in time-series properties of BOLD dynamics vary with physiological variation and structural connectivity in the human neocortex.

πŸ“— eLife (2020).

lax_62116_elife-62116-fig1-v2.tif.pnghttps://elifesciences.org/articles/62116

Distinguish targeted perturbations to mouse fMRI dynamics.

πŸ“— Cerebral Cortex (2020).

πŸ’» Code.

F4.large.jpghttps://academic.oup.com/cercor/article/30/9/4922/5823074?login=false
*as well as:* * Distinguish wake from anesthetized flies. * [πŸ“— Leung et al. *PLoS Biology* (2025).](https://doi.org/10.1371/journal.pbio.3003217) * Connect structural brain connectivity to fMRI dynamics (mouse). * [πŸ“— *Chaos* (2017)](http://aip.scitation.org/doi/10.1063/1.4979281). * Connect structural brain connectivity to fMRI dynamics (human). * [πŸ“— *Network Neuroscience* (2020)](https://doi.org/10.1162/netn_a_00151). * Distinguish time-series patterns for data-mining applications. * [πŸ“— *IEEE Trans. Knowl. Data Eng.* (2014)](http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6786425). * Classify babies with low blood pH from fetal heart rate time series. * [πŸ“— *34th Ann. Int. Conf. IEEE EMBC* (2012)](http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6346629). *** ## Others' Research πŸ“• ### 🧬 Biology

Extract acoustic features from social vocal accommodation in adult marmoset monkeys.

πŸ“™ bioRxiv (2023).

Screenshot 2024-05-10 at 3.15.52β€―pm.pnghttps://www.biorxiv.org/content/10.1101/2023.09.22.559020v1

Track Drosophila in real time for high-throughput behavioural phenotyping.

πŸ“— eLife (2023).

Screenshot 2024-05-10 at 3.20.27β€―pm.pnghttps://elifesciences.org/articles/86695

Detect anger from photoplethysmography (PPG) sensors.

πŸ“— Journal of NeuroEngineering and Rehabilitation (2023).

12984_2023_1217_Fig5_HTML.pnghttps://jneuroengrehab.biomedcentral.com/articles/10.1186/s12984-023-01217-5

Identify and distinguish marmoset vocalisations from audio, using Adaboost feature selection from hctsa features.

πŸ“— J. Roy. Soc. Interface (2023).

Screenshot 2024-05-10 at 3.22.07β€―pm.pnghttps://royalsocietypublishing.org/doi/10.1098/rsif.2023.0399

Discriminate zebra finch songs in different social contexts.

πŸ“— PLoS Computational Biology (2021).

journal.pcbi.1008820.g003.tif.pnghttps://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1008820

Distinguish electromagnetic field exposure from zebrafish locomotion time series.

πŸ“— Sensors (2020).

sensors-20-04818-g005.pnghttps://www.mdpi.com/1424-8220/20/17/4818
*** ### 🧫 Cellular Neuroscience

Confirm the role of Β΅ORs in VTA and NAc in acute fentanyl-induced behaviour (positive reinforcement).

πŸ“— Chaudun et al., Nature (2024).

https://www.nature.com/articles/s41586-024-07440-xScreenshot 2024-05-28 at 10.30.28.png

Assess stress-induced changes in astrocyte calcium dynamics.

πŸ“— Nature Comms. (2020).

https://www.nature.com/articles/s41467-020-15778-9Screenshot 2024-05-10 at 2.56.37β€―pm.png

Assess the stress controllability of neurons from their activity time series.

πŸ“— Nature Neuroscience (2020).

https://www.nature.com/articles/s41593-020-0591-0Screenshot 2024-05-10 at 3.03.50β€―pm.png
*** ### 🧠 Neuroimaging *Here are some highlights:*

Understand changes in fMRI brain dynamics in patients with epilepsy.

πŸ“— Communications Biology (2024).

Screenshot 2024-05-10 at 4.57.19β€―pm.pnghttps://www.nature.com/articles/s42003-024-05819-0

Extract EEG markers of cognitive decline.

πŸ“— npj Aging (2024).

raoul5-3099459-large.gif.png

Detect EEG markers of seizure disorders.

πŸ“— Brain Communications (2023).

Screenshot 2024-05-10 at 5.03.42β€―pm.pnghttps://academic.oup.com/braincomms/article/5/6/fcad330/7456007?login=false

Capture a distinctive fingerprint of an individual's resting-state fMRI data.

πŸ“™ ResearchSquare (2023).

Screenshot 2024-05-10 at 5.10.29β€―pm.pnghttps://www.researchsquare.com/article/rs-3344208/v1

Identify methamphetamine users from EEG time series.

πŸ“™ ResearchSquare (2023).

aaf69048deda0f2db74b0bf9.jpghttps://www.researchsquare.com/article/rs-3052453/v1

Compute temporal profile similarity for individual fingerprinting from human fMRI data.

πŸ“— Network Neuroscience (2023).

netn_a_00320_f001.pnghttps://direct.mit.edu/netn/article/7/3/1206/115891/Functional-connectome-fingerprinting-across-the

Characterise subnetworks of the frontoparietal control network from fMRI recordings.

πŸ“™ bioRxiv (2023).

Screenshot 2024-05-10 at 5.22.39β€―pm.pnghttps://www.biorxiv.org/content/10.1101/2023.09.06.556465v1

Find time-series properties of motor-evoked potentials that predict multiple sclerosis progression after two years.

πŸ“— BMC Neurology (2020).

12883_2020_1672_Fig7_HTML.png.webphttps://bmcneurol.biomedcentral.com/articles/10.1186/s12883-020-01672-w

Detect mild cognitive impairment using single-channel EEG to measure speech-evoked brain responses.

πŸ“— IEEE Transactions on Neural Systems and Rehabilitation Engineering (2019).

Screenshot 2024-05-10 at 5.30.01β€―pm.pnghttps://ieeexplore.ieee.org/abstract/document/8693868
*In addition to:* * Predict depth of anesthesia from heart-rate dynamics. * [Qian et al., Br J Anaesth (2025).](https://doi.org/10.1016/j.bja.2025.09.053) * Detect associations between brain region dynamics and traits like cognitive ability and substance use. * [οΏ½ Tian et al., *Nature Human Behavior* (2025).](https://www.nature.com/articles/s41562-025-02332-0) * Predict age from resting-state MEG from individual brain regions. * [οΏ½](https://ieeexplore.ieee.org/abstract/document/10340663)[ ](#user-content-fn-1)[^1][*Stier et* ](#user-content-fn-1)[^1][*al., PNAS* (2025).](https://www.pnas.org/doi/10.1073/pnas.2411098122) * Estimate brain age in children from EEG. * [πŸ“— *45th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)* (2023)](https://ieeexplore.ieee.org/abstract/document/10340663). * Extract gradients from fMRI *hctsa* time-series features to understand the relationship between schizophrenia and nicotine dependence. * [πŸ“— *Cerebral Cortex* (2023)](https://doi.org/10.1093/cercor/bhad030). * 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). * [πŸ“™ *SciTePress* (2023)](https://www.scitepress.org/Papers/2023/116256/). * Distinguish motor-evoked potentials corresponding to multiple sclerosis. * [πŸ“— *Frontiers in Neuroinformatics* (2020)](https://doi.org/10.3389/fninf.2020.00028). *** ### πŸ”¬ Medicine**β€”**General *Here are some highlights:*

Differentiate tremor disorders using massive feature extraction, outperforming the best traditional tremor statistic.

πŸ“™ MedRxiv (2024).

Screenshot 2024-05-11 at 6.13.35β€―am.pnghttps://www.medrxiv.org/content/10.1101/2024.03.14.24303988v1

Identify physiological features predictive of respiratory outcomes in extremely pre-term infants from bedside monitor data.

πŸ“™ MedRxiv (2024)

Screenshot 2024-05-11 at 5.38.04β€―am.pnghttps://www.medrxiv.org/content/10.1101/2024.01.24.24301724v1

Discover signatures of fatal neonatal illness from vital signs.

πŸ“— npj Digital Medicine (2022).

Screenshot 2024-05-11 at 6.19.09β€―am.pnghttps://www.nature.com/articles/s41746-021-00551-z

Detect falls in elderly people from accelerometer data.

πŸ“— IEEE International Conference on Information and Communication Technology for Sustainable Development (2021).

Screenshot 2024-05-11 at 5.52.46β€―am.pnghttps://www.researchgate.net/publication/350835794_Social_Group_Optimized_Machine-Learning_Based_Elderly_Fall_detection_Approach_Using_Interdisciplinary_Time-Series_Features

Prediction of post-cardiac arrest outcomes at discharge from physiological time series recorded on the first day of intensive care.

πŸ“— Anaesthesia Critical Care & Pain Medicine (2021).

Screenshot 2024-05-11 at 5.55.26β€―am.pnghttps://www.sciencedirect.com/science/article/pii/S2352556821002228?via%3Dihub

Detect falls of elderly people using wearable sensors.

πŸ“— IEEE Access (2021).

Screenshot 2024-05-11 at 6.00.45β€―am.pnghttps://ieeexplore.ieee.org/document/9344695

Demonstrate that the suppression of essential tremor is due to a disruption of oscillations in the olivocerebellar loop.

πŸ“— Nature Comms. (2021).

Screenshot 2024-05-11 at 6.03.04β€―am.pnghttps://www.nature.com/articles/s41467-020-20581-7

Classify heartbeats measured using single-lead ECG.

πŸ“— IEEE 42nd International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO) (2019).

Screenshot 2024-05-11 at 6.05.55β€―am.pnghttps://ieeexplore.ieee.org/abstract/document/8757135

Assess muscles for clinical rehabilitation.

πŸ“— 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (2017).

Screenshot 2024-05-11 at 6.09.07β€―am.pnghttps://ieeexplore.ieee.org/abstract/document/8037372/
*in addition to:* * Predicting hospital length of stay from vital signs * Juez–Garcia et al. [Continuous vital sign monitoring for predicting hospital length of stay: a feasibility study in chronic obstructive pulmonary disease and chronic heart failure patients](https://sjtrem.biomedcentral.com/articles/10.1186/s13049-025-01458-4) (2025). * Differentiate essential tremor (ET) and tremor-dominant Parkinson's disease (PD) * [ HΓ€ring et al. Phenotypical Differentiation of Tremor Using Time Series Feature Extraction and Machine Learning, *Movement Disorders* (2025)](https://movementdisorders.onlinelibrary.wiley.com/doi/10.1002/mds.70032) * Predict MS disability progression using time-series features of evoked potential signals * :green\_book: [Fonteyn et al. International Conference on Machine Learning and Applications (ICMLA). (2025)](https://doi.org/10.1109/ICMLA61862.2024.00171). * Identify sepsis in very low birth weight (<1.5kg) infants from heart rate signals, identifying heart rate characteristics of reduced variability and transient decelerations. * [πŸ“™ *MedRxiv* (2024)](https://www.medrxiv.org/content/10.1101/2024.02.03.24302230v1) * Identify novel heart-rate variability metrics, including `RobustSD`, to create a parsimonious model for cerebral palsy prediction in preterm neonatal intensive care unit patients. * [πŸ“— *Pediatric Research* (2023)](https://www.nature.com/articles/s41390-023-02853-2). * Predicting post cardiac arrest outcomes. * [πŸ“— *Anaesthesia Critical Care & Pain Medicine* (2022)](https://doi.org/10.1016/j.accpm.2021.101015). * Detect falls from wearable sensor data. * [πŸ“— *Scientific Reports* (2021)](https://doi.org/10.1038/s41598-021-02537-z). * Detect falls from wearable sensor data. * [πŸ“— *Biosensors* (2021)](https://doi.org/10.3390/bios11080284). * Select features for fetal heart rate analysis using genetic algorithms. * [πŸ“— *Physiological Measurement* (2014)](http://iopscience.iop.org/article/10.1088/0967-3334/35/7/1357/meta). *** ### 🦠 **Medicineβ€”Pathology**

Screen for COVID-19 using digital holographic microscopy.

πŸ“— Biomedical Optics Express (2022).

getimagev2.cfm.jpeg.pnghttps://opg.optica.org/boe/abstract.cfm?uri=boe-13-10-5377

Detect COVID-19 from red blood cells using digital holographic microscopy.

πŸ“— Optics Express (2022).

getimagev2.cfm-4.jpeghttps://opg.optica.org/oe/fulltext.cfm?uri=oe-30-2-1723&id=467318

Identify the biogeographic heterogeneity of mucus, lumen, and feces.

πŸ“— PNAS (2021).

Screenshot 2024-05-10 at 3.56.32β€―pm.pnghttps://www.pnas.org/doi/full/10.1073/pnas.2019336118
*** ### πŸ— Engineering *Here are some highlights:*

Detect keyhole porosity formation during laser irradiation of Ti-6Al-4V substrates.

πŸ“— Additive Manufacturing (2023).

1-s2.0-S2214860423004232-gr3_lrg.jpghttps://www.sciencedirect.com/science/article/pii/S2214860423004232?via%3Dihub

Identify keyhole pores in a laser powder-bed fusion process using acoustic and inline pyrometry time series.

πŸ“— Journal of Materials Processing Technology (2022).

Screenshot 2024-05-10 at 4.28.01β€―pm.pnghttps://www.sciencedirect.com/science/article/pii/S0924013622001686?via%3Dihub

Detect false data injection attacks into smart meters.

πŸ“— IEEE Access (2021).

Screenshot 2024-05-10 at 4.53.06β€―pm.pnghttps://www.researchgate.net/publication/355700005_Big_Data-Driven_Detection_of_False_Data_Injection_Attacks_in_Smart_Meters

Predict pending loss of power stability from generator response signals.

πŸ“— IEEE Access (2021).

raoul5-3099459-large.gif.pnghttps://ieeexplore.ieee.org/document/9494352/

Detect seeded bearing faults on a wind turbine subjected to non-stationary wind speed.

πŸ“— Proceedings of the Seventeenth International Conference on Condition Monitoring and Asset Management (2021).

Screenshot 2024-05-10 at 4.37.17β€―pm.pnghttps://ris.uni-paderborn.de/record/22507

Recognise hand gestures.

πŸ“— PLoS ONE (2020).

pone.0227039.g005.PNG_L.pnghttps://journals.plos.org/plosone/article?id=10.1371/journal.pone.0227039

Distinguish energy use behaviours from smart meter data.

πŸ“— Energy and Buildings (2019).

1-s2.0-S0378778819311260-gr5.jpghttps://doi.org/10.1016/j.enbuild.2019.07.019

Non-intrusively monitor load for appliance detection and electrical power saving in buildings.

πŸ“— Energy and Buildings (2019).

1-s2.0-S0378778819305614-gr6.jpghttps://www.sciencedirect.com/science/article/pii/S0378778819305614?via%3Dihub

Evaluate asphalt irregularity from smartphone sensors.

πŸ“— International Symposium on Intelligent Data Analysis (2018).

453857_1_En_27_Fig3_HTML.gif.webphttps://link.springer.com/chapter/10.1007/978-3-319-68765-0_27
*in addition to:* * 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. * [πŸ“— *Proceedings of the Asia Pacific Conference of the PHM Society* (2023)](https://doi.org/10.36001/phmap.2023.v4i1.3596). * Identify faults in a large-scale industrial process. * [*PhD Thesis*](https://hdl.handle.net/1721.1/139296). *** ### ⛰️ Geoscience

Detecting earthquakes from seismic recordings.

πŸ“— Geophysical Prospecting (2023).

gpr13386-fig-0001-m.jpghttps://onlinelibrary.wiley.com/doi/10.1111/1365-2478.13386

Find temporal patterns for reconstructing surface soil moisture time series.

πŸ“— Journal of Hydrology (2023).

1-s2.0-S0022169423005218-gr13.jpghttps://www.sciencedirect.com/science/article/pii/S0022169423005218?via%3Dihub

Predict earthquakes (in the following month) from seismic indicators in Bangladesh.

πŸ“— IEEE Access (2021).

ander11-3071400-large.gifhttps://ieeexplore.ieee.org/document/9395582

Detect earthquakes in Groningen, The Netherlands.

πŸ“— 82nd EAGE Annual Conference & Exhibition Workshop Programme (2020).

Screenshot 2024-05-10 at 4.08.43β€―pm.pnghttps://www.earthdoc.org/content/papers/10.3997/2214-4609.202011128
*** [^1]: