Artificial Intelligence Versus Anesthesiologist Visual Assessment of Ejection Fraction by Transesophageal Echocardiography During Cardiac Surgery

NCT07841327 | Completed

• 1 other identifier: FMASU MS 82/2026
• Study Type: observational
• Target: 93
• Locations: 1 country
• Sites: 1

Brief Summary

This prospective observational study evaluated the reliability of a general-purpose artificial intelligence application in estimating left ventricular ejection fraction from intraoperative transesophageal echocardiography images during cardiac surgery. The artificial intelligence estimates were compared with visual assessment by two independent blinded professor anesthesiologists and with preoperative transthoracic echocardiography findings. Ejection fraction measured using M-mode and the time required for each assessment were also evaluated. The study included 93 adults undergoing elective coronary artery bypass grafting or valve surgery. The artificial intelligence assessments were performed using pseudonymized images and were not used to guide clinical decisions or patient management.

Conditions

Left Ventricular Function; Cardiac Surgery

Keywords

Artificial Intelligence; Transesophageal Echocardiography; Left Ventricular Ejection Fraction; Visual Estimation; M-Mode Echocardiography

Outcome Measures

Primary Outcomes (1)

• Difference Between AI and Anesthesiologist Visual Assessment of LVEF

  Left ventricular ejection fraction was assessed from the same intraoperative transesophageal echocardiography transgastric short-axis mid-papillary view at 0 degrees by a general-purpose artificial intelligence application and by two independent blinded professor anesthesiologists using visual (eyeball) assessment. The paired assessments were compared to evaluate the difference and agreement between the artificial intelligence and anesthesiologist assessments.

  During cardiac surgery, at the time of the intraoperative TEE assessment

Secondary Outcomes (3)

• Difference Between AI and Anesthesiologist M-Mode Assessment of LVEF

  During cardiac surgery, at the time of the intraoperative TEE assessment

• Time Required for AI and Anesthesiologist LVEF Assessment

  During intraoperative TEE image review, from the start of each visual (eyeball) or M-mode LVEF assessment until the corresponding estimate is completed, assessed up to 3 minutes per assessment per participant.

• Difference Between Intraoperative TEE and Preoperative TTE LVEF Assessments

  From the available preoperative TTE assessment to the intraoperative TEE assessment during cardiac surgery

Study Arms (1)

Elective Cardiac Surgery Patients

A single cohort of 93 adult patients undergoing elective coronary artery bypass grafting or valve repair or replacement surgery. Intraoperative transesophageal echocardiography images were evaluated for left ventricular ejection fraction using artificial intelligence, anesthesiologist visual assessment, and M-mode echocardiography.

Diagnostic Test: Artificial Intelligence Assessment of TEE Images

Interventions

Artificial Intelligence Assessment of TEE Images DIAGNOSTIC_TEST

Pseudonymized end-diastolic and end-systolic frames and an M-mode recording obtained from the transgastric short-axis mid-papillary view at 0 degrees were analyzed by a general-purpose artificial intelligence application to estimate left ventricular ejection fraction. The artificial intelligence results were compared with assessments by two independent blinded professor anesthesiologists and with preoperative transthoracic echocardiography. The artificial intelligence output was used only for research and did not guide clinical management.

Elective Cardiac Surgery Patients

Eligibility Criteria

• Age: 21 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Adult patients aged 21 years or older who were scheduled for elective coronary artery bypass grafting, valve repair, or valve replacement surgery at the Cardiothoracic Surgery Academy, Ain Shams University and had an available preoperative transthoracic echocardiographic assessment.

You may qualify if:

• Age 21 years or older.
• Scheduled for elective cardiac surgery involving coronary artery bypass grafting, valve repair, or valve replacement.
• Availability of a preoperative transthoracic echocardiographic assessment.
• Either sex.
• American Society of Anesthesiologists physical status III or IV.

You may not qualify if:

• Coagulopathy, defined as an international normalized ratio greater than 2 or a platelet count below 50,000/mm3.
• Previous cardiac surgery (redo procedure).
• Esophageal or upper gastrointestinal pathology preventing safe transesophageal echocardiography probe placement, including esophageal stricture, tumor, or large varices.
• Poor-quality transesophageal echocardiography images despite standard optimization, preventing reliable interpretation.
• Severe arrhythmia or hemodynamic instability before surgery, during induction, or during surgery that could compromise the accuracy of the transesophageal echocardiography assessment.
• Refusal to participate or a condition limiting valid consent or participation, including cognitive impairment or a language barrier.

Sponsors & Collaborators

• Ain Shams University: lead

Study Sites (1)

Cardiothoracic Surgery Academy, Ain Shams University Hospitals

Cairo, Cairo Governorate, Egypt

Location

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: September 14, 2026
• First Posted: September 25, 2026
• Study Start: March 28, 2026
• Primary Completion: August 22, 2026
• Study Completion: August 22, 2026
• Last Updated: September 25, 2026

Record last verified: 2026-09

Data Sharing

• IPD Sharing: Will not share

Locations

EG (1)