Abstract

This scholarly project examines the role of artificial intelligence (AI)–guided hemodynamic management in reducing intraoperative hypotension during non-emergent cardiac surgery. Intraoperative hypotension, defined as mean arterial pressure (MAP) below 65 mmHg, is a well-established risk factor for myocardial injury, acute kidney injury, and increased postoperative morbidity and mortality. Despite vigilant monitoring, traditional clinician-directed management remains largely reactive, intervening only after hypotension has occurred.

The project centers on a clinical case involving a 67-year-old male undergoing elective on-pump coronary artery bypass grafting, during which several transient hypotensive episodes occurred despite standard anesthetic care. These events served as a catalyst for an evidence-based exploration of AI-driven technologies, including predictive analytics such as the Hypotension Prediction Index (HPI) and closed-loop vasopressor infusion systems. A synthesis of current randomized and prospective studies demonstrates that AI-guided systems can predict hypotension minutes before onset with high sensitivity and specificity and significantly reduce both the incidence and duration of hypotensive episodes. Reported outcomes include reductions in time-weighted hypotension by more than 60 percent, improved precision in vasopressor administration, and shorter intensive care unit stays without increased adverse effects.

This project emphasizes the critical role of Certified Registered Nurse Anesthetists in integrating AI tools into clinical practice. Rather than replacing clinical judgment, AI-guided monitoring enhances decision-making through earlier warning and structured response algorithms. Translation to practice includes provider education, simulation-based training, and pilot implementation within elective cardiac surgery pathways, with quality metrics focused on hypotension exposure and postoperative organ function.

Overall, this work highlights AI-guided hemodynamic management as a feasible, evidence-based strategy to advance precision anesthesia care and improve patient safety in cardiac surgery.

Author Details

James P. Warren, DNP(c), BSN, SRNA; Maria Ledbetter, DNAP, CRNA

Sigma Membership

Non-member

Type

DNP Capstone Project

Format Type

Text-based Document

Study Design/Type

Case Study/Series

Research Approach

Translational Research/Evidence-based Practice

Keywords:

Artificial Intelligence, Intraoperative Hypotension, Cardiac Surgery, Surgical Complications, Hemodynamic

Advisor

Maria Ledbetter

Degree

DNP

Degree Grantor

Samford University

Degree Year

2026

Rights Holder

All rights reserved by the author(s) and/or publisher(s) listed in this item record unless relinquished in whole or part by a rights notation or a Creative Commons License present in this item record. All permission requests should be directed accordingly and not to the Sigma Repository. All submitting authors or publishers have affirmed that when using material in their work where they do not own copyright, they have obtained permission of the copyright holder prior to submission and the rights holder has been acknowledged as necessary.

Review Type

None: Degree-based Submission

Acquisition

Proxy-submission

Date of Issue

2026-02-03

Full Text of Presentation

wf_yes

Download

Additional Files

Abstract.pdf (72 kB)

Share

COinS