OSCR

Deep learning guided propofol ketamine dosing and inflammation trajectories in elderly burns.

Overview

Authors: Xiaohui Yuan1, Gang Wang1, Xiaoyang Jiang1, Wenjing Miao1
  1. Department of Anesthesiology, Wuhan Third Hospital, Wuhan, China
Institutions: Wuhan Third Hospital (China)
Journal: Frontiers in computational neuroscience, volume 20, article 1824898
Dates: received 6 March 2026; accepted 31 March 2026; published online 18 May 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.3389/fncom.2026.1824898 · PMID 42232895 · PMCID PMC13223136 · OpenAlex W7161539093
Open access: gold, a free copy (OpenAlex)
Categories: human (organism)
Methods: Statistics, Machine learning, Single-unit activity, calcium imaging, Physiology & signal measures, Connectivity
Keywords: burn injuries, clinical decision support, elderly, event-transformer, IL-6, ketamine, offline reinforcement learning, propofol
Topic: Anesthesia and Neurotoxicity Research (Developmental Neuroscience, Neuroscience), according to OpenAlex
Citations: not cited yet (Europe PMC); 41 references in the paper

Abstract

Background and objectives: Elderly patients (≥65 years) who sustain burn injuries encounter a clinically significant perioperative challenge: a dysregulated hyperinflammatory response, characterized by elevated levels of interleukin-6 (IL-6), tumor necrosis factor-alpha (TNF-α), and C-reactive protein (CRP), compounded by a markedly reduced hemodynamic reserve. Both propofol and low-dose ketamine exhibit distinct anti-inflammatory mechanisms; however, the optimization of their combined dosing within explicit safety parameters remains unestablished. Our objectives were to: (1) develop and externally validate a probabilistic machine learning (ML) model to predict dynamic 24-h trajectories of inflammatory markers; and (2) integrate these predictions with a safety-constrained offline reinforcement learning (RL) agent to formulate individualized propofol-ketamine dosing recommendations.

Study design: This study employed a retrospective multi-cohort analysis utilizing two publicly accessible intensive care databases.

Setting: The research was conducted in an academic medical center ICU (MIMIC-IV) and across 208 community and academic hospitals (eICU Collaborative Research Database).

Measurements: The study analyzed 614 perioperative episodes in patients aged ≥65 years with confirmed burn injuries who received propofol-based anesthesia for ≥30 min and had ≥2 inflammatory laboratory measurements within 6–24 h post-induction. External validation was performed on 206 independent episodes.

Main results: The proposed Event-Transformer with continuous-time Neural ODE dynamics demonstrated a 12-h IL-6 mean absolute error (MAE) of 6.82 pg/mL, representing a 70.1% improvement over linear mixed models (22.8 pg/mL). It achieved an inflammatory spike detection area under the receiver operating characteristic curve (AUROC) of 0.814 and empirical 90% prediction interval (PI) coverage of 87.2%. The Conservative Policy with Q-Learning (CPQL) dosing agent enhanced the time within the MAP target range (65–90 mmHg) from 62.3% to 71.8% (p < 0.001), decreased vasopressor initiation from 27.0% to 18.4% (p = 0.003), reduced peak predicted CRP by 21.3%, and decreased total propofol exposure by 12.1% through the introduction of adjunct ketamine (≈7.2 mcg/kg/min). The safety constraint violation rate was 0.0% under CPQL compared to 4.2% for unconstrained offline RL.

Conclusions: An integrated inflammatory forecasting and dosing optimization pipeline can facilitate individualized propofol-ketamine titration in elderly burn patients, yielding predicted clinically significant improvements in hemodynamic stability and inflammatory burden, without safety violations. Clinically, the 70.1% reduction in IL-6 forecasting error translates to a meaningful difference between correct and incorrect inflammatory spike classification in a substantial fraction of patients, supporting the potential real-world utility of this framework as a decision-support tool to inform and guide future prospective trials.

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

Code

The paper links to its data and to no code of its authors: 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

Data availability statement

The original contributions presented in the study are included in the article/supplementary material, further inquiries can be directed to the corresponding author.

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, 28 September 2026: the first record

Recorded: type, language, journal, volume, pages, dates, 4 authors, 8 keywords, 29 references.

Cite

This paper

Yuan, X., Wang, G., Jiang, X., & Miao, W. (2026). Deep learning guided propofol ketamine dosing and inflammation trajectories in elderly burns. Frontiers in computational neuroscience, 20, 1824898. https://doi.org/10.3389/fncom.2026.1824898

BibTeX

@article{yuan2026deep,
author = {Yuan, Xiaohui and Wang, Gang and Jiang, Xiaoyang and Miao, Wenjing},
title = {{Deep learning guided propofol ketamine dosing and inflammation trajectories in elderly burns}},
journal = {Frontiers in computational neuroscience},
year = {2026},
month = may,
volume = {20},
pages = {1824898},
publisher = {Frontiers Media SA},
issn = {1662-5188},
doi = {10.3389/fncom.2026.1824898},
url = {https://doi.org/10.3389/fncom.2026.1824898},
pmid = {42232895},
pmcid = {PMC13223136}
}

RIS

TY - JOUR
AU - Yuan, Xiaohui
AU - Wang, Gang
AU - Jiang, Xiaoyang
AU - Miao, Wenjing
TI - Deep learning guided propofol ketamine dosing and inflammation trajectories in elderly burns
T2 - Frontiers in computational neuroscience
J2 - Front Comput Neurosci
PY - 2026
DA - 2026/05/18
VL - 20
SP - 1824898
SN - 1662-5188
PB - Frontiers Media SA
DO - 10.3389/fncom.2026.1824898
UR - https://doi.org/10.3389/fncom.2026.1824898
LA - en
ER -

CSL-JSON

{
"id": "10.3389/fncom.2026.1824898",
"type": "article-journal",
"title": "Deep learning guided propofol ketamine dosing and inflammation trajectories in elderly burns",
"container-title": "Frontiers in computational neuroscience",
"author": [
{
"family": "Yuan",
"given": "Xiaohui"
},
{
"family": "Wang",
"given": "Gang"
},
{
"family": "Jiang",
"given": "Xiaoyang"
},
{
"family": "Miao",
"given": "Wenjing"
}
],
"container-title-short": "Front Comput Neurosci",
"volume": "20",
"page": "1824898",
"DOI": "10.3389/fncom.2026.1824898",
"PMID": "42232895",
"PMCID": "PMC13223136",
"ISSN": "1662-5188",
"publisher": "Frontiers Media SA",
"URL": "https://doi.org/10.3389/fncom.2026.1824898",
"language": "en",
"issued": {
"date-parts": [
[
2026,
5,
18
]
]
}
}

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1016/j.isci.2026.116135 [code]
Predicting ICU in-hospital mortality from text-encoded structured EHR data using adaptive transformer layer fusion.
Journal: iScience
In common: physionet.org/content/eicu-crd, physionet.org/content/mimiciv, 1 reference
[2] doi:10.3389/fneur.2026.1848730
Early prediction of incident delirium in traumatic brain injury: a multicenter validated and interpretable machine learning approach.
Journal: Frontiers in neurology
In common: physionet.org/content/eicu-crd, physionet.org/content/mimiciv, 1 reference
[3] doi:10.1002/cns.70735
Four Distinct Dynamic Intracranial Pressure Trajectories and Their Prognostic Implications in Acute Brain Injury: A Multicenter Cohort Study.
Journal: CNS neuroscience & therapeutics
In common: physionet.org/content/eicu-crd, physionet.org/content/mimiciv
[4] doi:10.1186/s40001-025-03587-z [code]
Influence of early temperature trajectories on clinical outcomes in traumatic brain injury: a multicenter validation study using machine learning.
Journal: European journal of medical research
In common: physionet.org/content/eicu-crd, physionet.org/content/mimiciv
[5] doi:10.1038/s41598-024-69143-7
End-tidal carbon dioxide and arterial to end-tidal carbon dioxide gradient are associated with mortality in patients with neurological injuries.
Journal: Scientific reports
In common: physionet.org/content/mimiciv, 2 references
[6] doi:10.3389/fmed.2025.1621441 [code]
The impact of autoimmune diseases on delirium risk in critically ill patients: a propensity score matching multicenter analysis.
Journal: Frontiers in medicine
In common: physionet.org/content/eicu-crd, 1 reference
[7] doi:10.3389/fneur.2024.1439318 [code]
Trajectories of systemic immune inflammation index and mortality risk in patients with moderate-to-severe traumatic brain injury: a retrospective cohort study.
Journal: Frontiers in neurology
In common: physionet.org/content/eicu-crd, 1 reference
[8] doi:10.1093/jamiaopen/ooac048 [code]
Delirium prediction in the ICU: designing a screening tool for preventive interventions.
Journal: JAMIA open
In common: physionet.org/content/eicu-crd, 1 reference
[9] doi:10.1111/cns.13854
Group-based trajectory modeling of intracranial pressure in patients with acute brain injury: Results from multi-center ICUs, 2008-2019.
Journal: CNS neuroscience & therapeutics
In common: physionet.org/content/eicu-crd, 1 reference
[10] doi:10.7189/jogh.16.04108
Association between serum glucose/potassium ratio and acute kidney injury in patients with traumatic brain injury: based on MIMIC-IV database.
Journal: Journal of global health
In common: physionet.org/content/mimiciv, 1 reference

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: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.

Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.

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