Predicting depth of anaesthesia from single-channel EEG using a deep TCN-BiLSTM-attention model with EWMA.

Overview

Authors: Sukriti¹, Chirag Kriplani¹, Suman Kumar¹, Abhishek Singh¹

School of Electronics Engineering, Vellore Institute of Technology, Chennai, India

Institutions: Vellore Institute of Technology University (India)

Journal: Scientific reports, volume 16, issue 1, article 25470

Dates: received 5 January 2026; accepted 20 May 2026; published online 4 June 2026

Type: Research article · Language: English

License: CC BY

Identifiers: DOI 10.1038/s41598-026-54608-8 · PMID 42243301 · PMCID PMC13473519 · OpenAlex W7163516490

Open access: gold, a free copy (OpenAlex)

Status: data only

Categories: EEG (modality), human (organism), cognitive (subfield)

Methods: Spectral & time-frequency, Preprocessing, Statistics, Connectivity, Machine learning, Smoothing, state filtering, decompositions, Physiology & signal measures

Keywords: Depth of Anaesthesia, EEG, Bispectral Index Regression, Temporal Convolutional Network, Bidirectional LSTM, Exponentially Weighted Moving Average, Computational biology and bioinformatics, Engineering, Health care, Mathematics and computing, Medical research, Neuroscience

MeSH: Anesthesia*, Electroencephalography*, Algorithms, Consciousness Monitors, Convolutional Neural Networks, Humans, Long Short Term Memory (* major topic)

Topic: EEG and Brain-Computer Interfaces (Cognitive Neuroscience, Neuroscience), according to OpenAlex

Funding: Vellore Institute of Technology, Chennai

Citations: not cited yet (Europe PMC); 45 references in the paper

Abstract

Accurately determining the depth of anaesthesia (DoA) is crucial for ensuring patient safety and providing individualised anaesthetic management. Widely used monitors, such as the Bispectral Index (BIS), rely on proprietary multichannel EEG algorithms, which limit transparency and accessibility. This study presents a single-lead EEG framework for continuous BIS estimation that is window-level causal, end-to-end, and suitable for near–real-time deployment. The approach integrates a Temporal Convolutional Network (TCN) with power-of-two dilations, a compact bidirectional LSTM for temporal refinement, and additive attention pooling, followed by an exponentially weighted moving average (EWMA) to stabilize predictions over time. This design captures multi-scale temporal dependencies directly from raw EEG while preserving interpretability and low latency. Using a random segment-level split on a public perioperative EEG–BIS dataset, the proposed model achieved a mean absolute error (MAE) of 4.499, root mean square error (RMSE) of 7.499, Pearson’s correlation coefficient (r) of 0.903, and Lin’s concordance correlation coefficient (CCC) of 0.897 relative to reference BIS values. Under a stricter subject-independent 5-fold GroupKFold evaluation, performance decreased as expected. Still, it remained stable across folds, with the best configuration achieving an MAE of 6.03 ± 0.38 and a CCC of 0.819 ± 0.050 after EWMA smoothing. With approximately 1.07 million parameters and a throughput of about 430 segments per second, the proposed framework offers an efficient and transparent solution for single-sensor DoA monitoring. Overall, this work advances data-driven BIS estimation beyond feature-based methods while explicitly addressing both within-dataset performance and generalization to unseen subjects.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data, not to its authors' code: see the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

figshare:1, at figshare; found in the references
figshare:5589841, at figshare; found in “Data availability”

Data availability

The dataset analysed during the current study is publicly available on figshare: Ma, Li (2017). *EEG and BIS raw data*. figshare. Dataset. [https://doi.org/10.6084/m9.figshare.5589841.v1](cited in this paper).

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 4 authors, 12 keywords, 7 MeSH terms, 1 funder, 42 references.

Cite

This paper

Sukriti, Kriplani, C., Kumar, S., & Singh, A. (2026). Predicting depth of anaesthesia from single-channel EEG using a deep TCN-BiLSTM-attention model with EWMA. Scientific reports, 16(1), 25470. https://doi.org/10.1038/s41598-026-54608-8

BibTeX

@article{sukriti2026predicting, author = {Sukriti and Kriplani, Chirag and Kumar, Suman and Singh, Abhishek}, title = {{Predicting depth of anaesthesia from single-channel EEG using a deep TCN-BiLSTM-attention model with EWMA}}, journal = {Scientific reports}, year = {2026}, month = jun, volume = {16}, number = {1}, pages = {25470}, publisher = {Nature Publishing Group}, issn = {2045-2322}, doi = {10.1038/s41598-026-54608-8}, url = {https://doi.org/10.1038/s41598-026-54608-8}, pmid = {42243301}, pmcid = {PMC13473519} }

RIS

TY - JOUR AU - Sukriti AU - Kriplani, Chirag AU - Kumar, Suman AU - Singh, Abhishek TI - Predicting depth of anaesthesia from single-channel EEG using a deep TCN-BiLSTM-attention model with EWMA T2 - Scientific reports J2 - Sci Rep PY - 2026 DA - 2026/06/04 VL - 16 IS - 1 SP - 25470 SN - 2045-2322 PB - Nature Publishing Group DO - 10.1038/s41598-026-54608-8 UR - https://doi.org/10.1038/s41598-026-54608-8 LA - en ER -

CSL-JSON

{ "id": "10.1038/s41598-026-54608-8", "type": "article-journal", "title": "Predicting depth of anaesthesia from single-channel EEG using a deep TCN-BiLSTM-attention model with EWMA", "container-title": "Scientific reports", "author": [ { "family": "Sukriti" }, { "family": "Kriplani", "given": "Chirag" }, { "family": "Kumar", "given": "Suman" }, { "family": "Singh", "given": "Abhishek" } ], "container-title-short": "Sci Rep", "volume": "16", "issue": "1", "page": "25470", "DOI": "10.1038/s41598-026-54608-8", "PMID": "42243301", "PMCID": "PMC13473519", "ISSN": "2045-2322", "publisher": "Nature Publishing Group", "URL": "https://doi.org/10.1038/s41598-026-54608-8", "language": "en", "issued": { "date-parts": [ [ 2026, 6, 4 ] ] } }

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.