---
title: "ePWV and delirium risk in ICU sepsis patients: retrospective MIMIC-IV analysis and predictive model"
id: "pubmed-42700537"
canonical_url: "https://medichelpline.com/clinical-feed/pubmed-42700537"
content_type: "clinical_feed_article"
specialty: "Critical Care"
source_name: "PubMed / NCBI"
source_url: "https://pubmed.ncbi.nlm.nih.gov/42700537/"
doi: "10.1016/j.clinsp.2026.101106"
published_at: "2026-09-05T00:00:00.000Z"
evidence_level: "Journal Article"
license: "CC-BY-NC-4.0 / Informational Use"
---
# ePWV and delirium risk in ICU sepsis patients: retrospective MIMIC-IV analysis and predictive model
## Provenance & Clinical Metadata
- **Canonical URL:** https://medichelpline.com/clinical-feed/pubmed-42700537
- **Specialty:** [Critical Care](https://medichelpline.com/clinical-feed/critical-care.md)
- **Primary Source:** PubMed / NCBI
- **Source URL:** [Original Journal Publication](https://pubmed.ncbi.nlm.nih.gov/42700537/)
- **DOI:** [10.1016/j.clinsp.2026.101106](https://doi.org/10.1016%2Fj.clinsp.2026.101106)
- **Published At:** 2026-09-05T00:00:00.000Z
- **Evidence Rating:** Journal Article
## Executive GIST (TL;DR)
- This retrospective cohort study used the **MIMIC-IV** (v3.1) database to examine the association between estimated pulse wave velocity (**ePWV**) and delirium in ICU patients meeting Sepsis-3.0 criteria. The exposure was ePWV calculated from age and blood pressure, and the outcome was delirium defined by the **CAM-ICU**. - The analysis included 24,889 sepsis patients; overall delirium incidence was 44.4% in the cohort. - Patients were randomly split 70:30 into training and validation sets for model development. Feature selection combined the Boruta algorithm and **LASSO** regression. - Time-to-event analyses used Kaplan–Meier curves and Cox proportional hazards models. Kaplan–Meier demonstrated significant differences in delirium risk across ePWV strata (p < 0.0001). - In multivariable Cox regression, higher **ePWV** was independently associated with greater delirium risk (HR per unit = 1.018, 95% CI 1.008–1.027); the highest ePWV quartile had a 19% higher risk versus the lowest (HR = 1.193). - Restricted cubic spline (RCS) analyses indicated a nonlinear relationship between ePWV and delirium (RCS p = 0.019). - Subgroup analyses showed consistent associations across subgroups except in patients with cerebral infarction, where significance was not observed. - Five machine learning classifiers were trained and compared; **K-Nearest Neighbor** achieved the best discrimination in the validation cohort with AUC = 0.736. - SHAP (SHapley Additive exPlanations) interpretation identified **respiratory failure**, **acute renal failure (ARF)** and **ACE inhibitor (ACEI)** use among the most important predictive features. - The authors conclude that **ePWV** is independently associated with delirium risk in ICU sepsis patients and that the ML model may assist in early identification of high-risk patients. Conflict of interest: none reported.
## Clinical Analysis & Structured Key Points
Clipboard, Search History, and several other advanced features are temporarily unavailable. [ Skip to main page content ](https://pubmed.ncbi.nlm.nih.gov/42700537/#article-details) ![U.S. flag](https://cdn.ncbi.nlm.nih.gov/coreutils/uswds/img/favicons/favicon-57.png) An official website of the United States government Here's how you know ![Dot gov](https://cdn.ncbi.nlm.nih.gov/coreutils/uswds/img/icon-dot-gov.svg) **The .gov means it’s official.** Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site. ![Https](https://cdn.ncbi.nlm.nih.gov/coreutils/uswds/img/icon-https.svg) **The site is secure.** The **https://** ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely. [ ![NIH NLM Logo](https://cdn.ncbi.nlm.nih.gov/coreutils/nwds/img/logos/AgencyLogo.svg) ](https://www.ncbi.nlm.nih.gov/) [Log in](https://account.ncbi.nlm.nih.gov/?back_url=https%3A%2F%2Fpubmed.ncbi.nlm.nih.gov%2F42700537%2F) Show account info Close #### Account Logged in as: **username** * [Dashboard](https://www.ncbi.nlm.nih.gov/myncbi/) * [Publications](https://www.ncbi.nlm.nih.gov/myncbi/collections/bibliography/) * [Account settings](https://www.ncbi.nlm.nih.gov/account/settings/) * [Log out](https://www.ncbi.nlm.nih.gov/account/signout/?back_url=https%3A//pubmed.ncbi.nlm.nih.gov/42700537/) [Access keys](https://www.ncbi.nlm.nih.gov/guide/browsers/#ncbi_accesskeys) [NCBI Homepage](https://www.ncbi.nlm.nih.gov) [MyNCBI Homepage](https://pubmed.ncbi.nlm.nih.gov/myncbi/) [Main Content](https://pubmed.ncbi.nlm.nih.gov/42700537/#maincontent) [Main Navigation](https://pubmed.ncbi.nlm.nih.gov/42700537/) [ ![pubmed logo](https://cdn.ncbi.nlm.nih.gov/pubmed/c24ab723-7c80-48cd-9c68-022ded852586/core/images/pubmed-logo-blue.svg) ](https://pubmed.ncbi.nlm.nih.gov/) [ ](https://pubmed.ncbi.nlm.nih.gov/42700537/ "Show search bar") Search: [](https://pubmed.ncbi.nlm.nih.gov/42700537/ "Clear search input")Search [Advanced](https://pubmed.ncbi.nlm.nih.gov/advanced/) [ Clipboard ](https://pubmed.ncbi.nlm.nih.gov/clipboard/) [ User Guide ](https://pubmed.ncbi.nlm.nih.gov/help/) Save Email Send to * [ Clipboard ](https://pubmed.ncbi.nlm.nih.gov/42700537/) * [My Bibliography](https://account.ncbi.nlm.nih.gov/?back_url=https%3A%2F%2Fpubmed.ncbi.nlm.nih.gov%2F42700537%2F%23open-bibliography-panel) * [Collections](https://account.ncbi.nlm.nih.gov/?back_url=https%3A%2F%2Fpubmed.ncbi.nlm.nih.gov%2F42700537%2F%23open-collections-panel) * [Citation manager](https://pubmed.ncbi.nlm.nih.gov/42700537/) Display options Display options Format Abstract PubMed PMID ## Save citation to file Format: Summary (text) PubMed PMID Abstract (text) CSV Create file Cancel ## Email citation Email address has not been verified. Go to [ My NCBI account settings ](https://account.ncbi.nlm.nih.gov/settings/) to confirm your email and then refresh this page. To: Subject: Body: Format: Summary Summary (text) Abstract Abstract (text) MeSH and other data Send email Cancel ### Add to Collections * Create a new collection * Add to an existing collection Name your collection: Name must be less than 100 characters Choose a collection: Unable to load your collection due to an error [Please try again](https://pubmed.ncbi.nlm.nih.gov/42700537/) Add Cancel ### Add to My Bibliography * My Bibliography Unable to load your delegates due to an error [Please try again](https://pubmed.ncbi.nlm.nih.gov/42700537/) Add Cancel ## Your saved search Name of saved search: Search terms: [Test search terms](https://pubmed.ncbi.nlm.nih.gov/42700537/) Would you like email updates of new search results? Saved Search Alert Radio Buttons * Yes * No Email: ([change](https://www.ncbi.nlm.nih.gov/account/settings/)) Frequency: Monthly Weekly Daily Which day? The first Sunday The first Monday The first Tuesday The first Wednesday The first Thursday The first Friday The first Saturday The first day The first weekday Which day? Sunday Monday Tuesday Wednesday Thursday Friday Saturday Report format: Summary Summary (text) Abstract Abstract (text) PubMed Send at most: 1 item 5 items 10 items 20 items 50 items 100 items 200 items Send even when there aren't any new results Optional text in email: Save Cancel ## Create a file for external citation management software Create file Cancel ## Your RSS Feed Name of RSS Feed: Number of items displayed: 5 10 15 20 50 100 Create RSS Cancel RSS Link Copy ### Actions Cite Collections Add to Collections * Create a new collection * Add to an existing collection Name your collection: Name must be less than 100 characters Choose a collection: Unable to load your collection due to an error [Please try again](https://pubmed.ncbi.nlm.nih.gov/42700537/) Add Cancel Permalink Permalink Copy Display options Display options Format Abstract PubMed PMID ### Page navigation * [ Title & authors ](https://pubmed.ncbi.nlm.nih.gov/42700537/#heading) * [ Abstract ](https://pubmed.ncbi.nlm.nih.gov/42700537/#abstract) * [ Conflict of interest statement ](https://pubmed.ncbi.nlm.nih.gov/42700537/#conflict-of-interest) Title & authors Abstract Conflict of interest statement Clinics (Sao Paulo) Actions * [ Search in PubMed ](https://pubmed.ncbi.nlm.nih.gov/?term=%22Clinics+%28Sao+Paulo%29%22%5Bjour%5D&sort=date&sort_order=desc) * [ Search in NLM Catalog ](https://www.ncbi.nlm.nih.gov/nlmcatalog?term=%22Clinics+%28Sao+Paulo%29%22%5BTitle+Abbreviation%5D) * [ Add to Search ](https://pubmed.ncbi.nlm.nih.gov/42700537/) . 2026 Sep 5:81:101106. doi: 10.1016/j.clinsp.2026.101106. Online ahead of print. # Association between ePWV and delirium risk in icu sepsis patients: a retrospective analysis based on the MIMIC database and development of a predictive model [Lihong Dong](https://pubmed.ncbi.nlm.nih.gov/?term=Dong+L&cauthor_id=42700537)[ 1 ](https://pubmed.ncbi.nlm.nih.gov/42700537/#full-view-affiliation-1 "Department of Critical Care Medicine, The First Affiliated Hospital of Kunming Medical University, Kunming Yunnan, China."), [Xixiang Yang](https://pubmed.ncbi.nlm.nih.gov/?term=Yang+X&cauthor_id=42700537)[ 2 ](https://pubmed.ncbi.nlm.nih.gov/42700537/#full-view-affiliation-2 "Ningxia Medical University, Yinchuan Ningxia, China."), [Xiaolin Zhu](https://pubmed.ncbi.nlm.nih.gov/?term=Zhu+X&cauthor_id=42700537)[ 1 ](https://pubmed.ncbi.nlm.nih.gov/42700537/#full-view-affiliation-1 "Department of Critical Care Medicine, The First Affiliated Hospital of Kunming Medical University, Kunming Yunnan, China."), [Hong Wang](https://pubmed.ncbi.nlm.nih.gov/?term=Wang+H&cauthor_id=42700537)[ 3 ](https://pubmed.ncbi.nlm.nih.gov/42700537/#full-view-affiliation-3 "Department of Critical Care Medicine, The Sixth Affiliated Hospital of Kunming Medical University, Yuxi Yunnan, China."), [Xiaoyan Wang](https://pubmed.ncbi.nlm.nih.gov/?term=Wang+X&cauthor_id=42700537)[ 4 ](https://pubmed.ncbi.nlm.nih.gov/42700537/#full-view-affiliation-4 "Department of Critical Care Medicine, The First Affiliated Hospital of Kunming Medical University, Kunming Yunnan, China. Electronic address: 119571925@qq.com.") Affiliations Expand ### Affiliations * 1 Department of Critical Care Medicine, The First Affiliated Hospital of Kunming Medical University, Kunming Yunnan, China. * 2 Ningxia Medical University, Yinchuan Ningxia, China. * 3 Department of Critical Care Medicine, The Sixth Affiliated Hospital of Kunming Medical University, Yuxi Yunnan, China. * 4 Department of Critical Care Medicine, The First Affiliated Hospital of Kunming Medical University, Kunming Yunnan, China. Electronic address: 119571925@qq.com. * PMID: **42700537** * DOI: [ 10.1016/j.clinsp.2026.101106 ](https://doi.org/10.1016/j.clinsp.2026.101106) Item in Clipboard # Association between ePWV and delirium risk in icu sepsis patients: a retrospective analysis based on the MIMIC database and development of a predictive model Lihong Dong et al. Clinics (Sao Paulo). 2026. Show details Display options Display options Format Abstract PubMed PMID Clinics (Sao Paulo) Actions * [ Search in PubMed ](https://pubmed.ncbi.nlm.nih.gov/?term=%22Clinics+%28Sao+Paulo%29%22%5Bjour%5D&sort=date&sort_order=desc) * [ Search in NLM Catalog ](https://www.ncbi.nlm.nih.gov/nlmcatalog?term=%22Clinics+%28Sao+Paulo%29%22%5BTitle+Abbreviation%5D) * [ Add to Search ](https://pubmed.ncbi.nlm.nih.gov/42700537/) . 2026 Sep 5:81:101106. doi: 10.1016/j.clinsp.2026.101106. Online ahead of print. ### Authors [Lihong Dong](https://pubmed.ncbi.nlm.nih.gov/?term=Dong+L&cauthor_id=42700537)[ 1 ](https://pubmed.ncbi.nlm.nih.gov/42700537/#short-view-affiliation-1 "Department of Critical Care Medicine, The First Affiliated Hospital of Kunming Medical University, Kunming Yunnan, China."), [Xixiang Yang](https://pubmed.ncbi.nlm.nih.gov/?term=Yang+X&cauthor_id=42700537)[ 2 ](https://pubmed.ncbi.nlm.nih.gov/42700537/#short-view-affiliation-2 "Ningxia Medical University, Yinchuan Ningxia, China."), [Xiaolin Zhu](https://pubmed.ncbi.nlm.nih.gov/?term=Zhu+X&cauthor_id=42700537)[ 1 ](https://pubmed.ncbi.nlm.nih.gov/42700537/#short-view-affiliation-1 "Department of Critical Care Medicine, The First Affiliated Hospital of Kunming Medical University, Kunming Yunnan, China."), [Hong Wang](https://pubmed.ncbi.nlm.nih.gov/?term=Wang+H&cauthor_id=42700537)[ 3 ](https://pubmed.ncbi.nlm.nih.gov/42700537/#short-view-affiliation-3 "Department of Critical Care Medicine, The Sixth Affiliated Hospital of Kunming Medical University, Yuxi Yunnan, China."), [Xiaoyan Wang](https://pubmed.ncbi.nlm.nih.gov/?term=Wang+X&cauthor_id=42700537)[ 4 ](https://pubmed.ncbi.nlm.nih.gov/42700537/#short-view-affiliation-4 "Department of Critical Care Medicine, The First Affiliated Hospital of Kunming Medical University, Kunming Yunnan, China. Electronic address: 119571925@qq.com.") ### Affiliations * 1 Department of Critical Care Medicine, The First Affiliated Hospital of Kunming Medical University, Kunming Yunnan, China. * 2 Ningxia Medical University, Yinchuan Ningxia, China. * 3 Department of Critical Care Medicine, The Sixth Affiliated Hospital of Kunming Medical University, Yuxi Yunnan, China. * 4 Department of Critical Care Medicine, The First Affiliated Hospital of Kunming Medical University, Kunming Yunnan, China. Electronic address: 119571925@qq.com. * PMID: **42700537** * DOI: [ 10.1016/j.clinsp.2026.101106 ](https://doi.org/10.1016/j.clinsp.2026.101106) Item in Clipboard Cite Display options Display options Format Abstract PubMed PMID ## Abstract **Background:** Sepsis, frequently complicated by delirium with poor prognosis, is common in the Intensive Care Unit (ICU). Estimated Pulse Wave Velocity (ePWV), a non-invasive arterial stiffness marker, remains unexplored regarding delirium risk in ICU sepsis patients. This study investigated ePWV's association with sepsis-linked delirium and developed a predictive model. **Methods:** This retrospective cohort study utilized MIMIC-IV 3.1 data. ICU patients with sepsis meeting the Sepsis-3.0 criteria were randomly allocated in a 7:3 to the training and validation cohorts.The exposure was ePWV derived using age and blood pressure. The outcome was delirium, defined by the Confusion Assessment Method for the Intensive Care Unit (CAM-ICU). Features were selected via Boruta and LASSO.Associations were examined using Cox models, Kaplan-Meier curves, restricted cubic splines, and subgroup analyses. Five machine learning models were evaluated. **Results:** Among 24,889 patients (delirium incidence 44.4%), Kaplan-Meier analysis showed significant differences in delirium risk across ePWV levels (p < 0.0001). Cox regression indicated ePWV was positively associated with delirium (HR = 1.018, 95% CI: 1.008‒1.027), with the highest quartile showing 19% elevated risk versus the lowest (HR = 1.193). RCS analysis revealed a nonlinear relationship (p = 0.019). Subgroup analyses were significant except for cerebral infarction. K-Nearest Neighbor performed best with AUC = 0.736 in validation. SHAP analysis demonstrated respiratory failure, ARFand ACEI as key features. **Conclusion:** ePWV was independently associated with delirium risk in ICU sepsis patients. The machine learning model demonstrated good discriminative ability, facilitating early identification of high-risk patients. **Keywords:** Delirium; MIMIC-IV; Machine learning; Sepsis; ePWV. Copyright © 2026 HCFMUSP. Published by Elsevier España, S.L.U. All rights reserved. [PubMed Disclaimer](https://pubmed.ncbi.nlm.nih.gov/disclaimer/) ## Conflict of interest statement Conflicts of interest The authors declare no conflicts of interest. [x] Cite Copy Download .nbib .nbib Format: AMA APA MLA NLM **Send To** * [Clipboard](https://pubmed.ncbi.nlm.nih.gov/42700537/) * [Email](https://account.ncbi.nlm.nih.gov/?back_url=https%3A%2F%2Fpubmed.ncbi.nlm.nih.gov%2F42700537%2F%23open-email-panel) * [Save](https://pubmed.ncbi.nlm.nih.gov/42700537/) * [My Bibliography](https://account.ncbi.nlm.nih.gov/?back_url=https%3A%2F%2Fpubmed.ncbi.nlm.nih.gov%2F42700537%2F%23open-bibliography-panel) * [Collections](https://account.ncbi.nlm.nih.gov/?back_url=https%3A%2F%2Fpubmed.ncbi.nlm.nih.gov%2F42700537%2F%23open-collections-panel) * [Citation Manager](https://pubmed.ncbi.nlm.nih.gov/42700537/) [x] NCBI Literature Resources [MeSH](https://www.ncbi.nlm.nih.gov/mesh/) [PMC](https://www.ncbi.nlm.nih.gov/pmc/) [Bookshelf](https://www.ncbi.nlm.nih.gov/books) [Disclaimer](https://pubmed.ncbi.nlm.nih.gov/disclaimer/) The PubMed wordmark and PubMed logo are registered trademarks of the U.S. Department of Health and Human Services (HHS). Unauthorized use of these marks is strictly prohibited. Follow NCBI [ Twitter ](https://twitter.com/ncbi) [ Facebook ](https://www.facebook.com/ncbi.nlm) [ LinkedIn ](https://www.linkedin.com/company/ncbinlm) [ GitHub ](https://github.com/ncbi) [ ](https://ncbiinsights.ncbi.nlm.nih.gov/) [Connect with NLM](https://www.nlm.nih.gov/socialmedia/index.html) * [ Twitter ](https://twitter.com/NLM_NIH) * [ SM-Facebook ](https://www.facebook.com/nationallibraryofmedicine) * [ SM-Youtube ](https://www.youtube.com/user/NLMNIH) National Library of Medicine [8600 Rockville Pike Bethesda, MD 20894](https://www.google.com/maps/place/8600+Rockville+Pike,+Bethesda,+MD+20894/@38.9959508,-77.101021,17z/data=!3m1!4b1!4m5!3m4!1s0x89b7c95e25765ddb:0x19156f88b27635b8!8m2!3d38.9959508!4d-77.0988323) [Web Policies](https://www.nlm.nih.gov/web_policies.html) [FOIA](https://www.nih.gov/institutes-nih/nih-office-director/office-communications-public-liaison/freedom-information-act-office) [HHS Vulnerability Disclosure](https://www.hhs.gov/vulnerability-disclosure-policy/index.html) [Help](https://support.nlm.nih.gov/?pagename=pubmed%3Apubmed%3Aabstract%3ANONE) [Accessibility](https://www.nlm.nih.gov/accessibility.html) [Careers](https://www.nlm.nih.gov/careers/careers.html) * [NLM](https://www.nlm.nih.gov/) * [NIH](https://www.nih.gov/) * [HHS](https://www.hhs.gov/) * [USA.gov](https://www.usa.gov/)
## Related Clinical Research

- [Therapeutic coma in non‑convulsive status epilepticus: higher complications, longer ICU stay, and](https://medichelpline.com/clinical-feed/pubmed-42701136.md) (DOI: 10.1007/s00415-026-14090-8)
- [NLRP3-linked ASTRA transcriptomic score associates with lower 28-day mortality in ICU sepsis cohor](https://medichelpline.com/clinical-feed/pubmed-42700257.md) (DOI: 10.1007/s00011-026-02352-0)
- [Entropy-Based Framework to Quantify Dynamic Epistemic Uncertainty in Clinical LLM Reasoning](https://medichelpline.com/clinical-feed/medrxiv-1-novel-entropy-based-framework-for-quantifying-dynamic-epistemic-uncertainty-in.md)
- [Low‑Dose Epirubicin in Sepsis and Septic Shock: Phase IIa EPOS‑1 Safety and Dose‑Escalation Results](https://medichelpline.com/clinical-feed/medrxiv-1-epirubicin-for-the-treatment-of-sepsis-and-septic-shock-epos-1-a-randomized.md)
- [High AUROC can hide threshold failure in sepsis transcriptomic classifiers: preprocessing stabilit](https://medichelpline.com/clinical-feed/plos-one-13-high-auroc-can-mask-decision-failure-in-sepsis-transcriptomic-classifiers.md)

## Navigation
- [← Back to Critical Care Feed](https://medichelpline.com/clinical-feed/critical-care.md)
- [← All Clinical Specialties](https://medichelpline.com/clinical-feed.md)
## Medical & Regulatory Disclaimer

> [!CAUTION]
> MedicHelpline content is structured for research, educational, and professional discovery purposes. It does not constitute individual medical advice, clinical diagnosis, or treatment recommendations.
> Always verify dosing, contraindications, and regulatory alerts against official product labeling and primary regulatory sources before clinical decision-making.