Artificial Intelligence Versus Anesthesiologist Visual Assessment of Ejection Fraction by Transesophageal Echocardiography During Cardiac Surgery
Reliability of Artificial Intelligent General Application in Assessing Ejection Fraction in Comparison to Anesthesiologist Eye Ball by Trans Oesophageal Echo During Cardiac Surgery
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.
Aperçu de l'étude
Statut
Les conditions
Intervention / Traitement
Description détaillée
This was a prospective, single-cohort observational study conducted at the Cardiothoracic Surgery Academy, Ain Shams University. Adults aged 21 years or older undergoing elective coronary artery bypass grafting or valve repair or replacement surgery were enrolled consecutively after providing written informed consent.
After induction of anesthesia and hemodynamic stabilization, transesophageal echocardiography images were obtained using a transgastric short-axis view at the mid-papillary level and an angle of 0 degrees. End-diastolic and end-systolic frames and an M-mode recording were collected for assessment of left ventricular ejection fraction.
Pseudonymized echocardiographic images were assessed using a general-purpose artificial intelligence application. The same images were independently assessed by two blinded professor anesthesiologists who had no access to the artificial intelligence output or the other assessments. Visual estimation of ejection fraction, M-mode-derived ejection fraction, and interpretation time were recorded. These findings were also compared with the preoperative transthoracic echocardiography assessment.
The artificial intelligence output was used exclusively for research and was not used to make or modify any clinical decision. A total of 93 eligible participants were included in the final analysis.
Type d'étude
Inscription (Réel)
Contacts et emplacements
Lieux d'étude
-
-
Cairo Governorate
-
Cairo, Cairo Governorate, Egypte
- Cardiothoracic Surgery Academy, Ain Shams University Hospitals
-
-
Critères de participation
Critère d'éligibilité
Âges éligibles pour étudier
Accepte les volontaires sains
Sexes éligibles pour l'étude
Méthode d'échantillonnage
Population étudiée
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.
La description
Inclusion Criteria:
- 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.
Exclusion Criteria:
- 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.
Plan d'étude
Comment l'étude est-elle conçue ?
Détails de conception
- Modèles d'observation: COHORT
- Perspectives temporelles: PROSPECTIVE
Cohortes et interventions
Groupe / Cohorte |
Intervention / Traitement |
|---|---|
|
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. |
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. |
Que mesure l'étude ?
Principaux critères de jugement
Mesure des résultats |
Description de la mesure |
Délai |
|---|---|---|
|
Difference Between AI and Anesthesiologist Visual Assessment of LVEF
Délai: During cardiac surgery, at the time of the intraoperative TEE assessment
|
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
|
Mesures de résultats secondaires
Mesure des résultats |
Description de la mesure |
Délai |
|---|---|---|
|
Difference Between AI and Anesthesiologist M-Mode Assessment of LVEF
Délai: During cardiac surgery, at the time of the intraoperative TEE assessment
|
Left ventricular ejection fraction was assessed using M-mode in the 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. The paired M-mode ejection fraction assessments were compared to evaluate the difference and agreement between methods. |
During cardiac surgery, at the time of the intraoperative TEE assessment
|
|
Time Required for AI and Anesthesiologist LVEF Assessment
Délai: 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.
|
The time required for the general-purpose artificial intelligence application and the anesthesiologist assessors to complete the visual (eyeball) and M-mode left ventricular ejection fraction assessments was recorded separately using a timer and reported in seconds. Assessment times were compared between the artificial intelligence and anesthesiologist methods. |
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
Délai: From the available preoperative TTE assessment to the intraoperative TEE assessment during cardiac surgery
|
Left ventricular ejection fraction estimates obtained from intraoperative transesophageal echocardiography by the general-purpose artificial intelligence application and the blinded anesthesiologist assessors were compared with the available preoperative transthoracic echocardiography ejection fraction for the same participant. The difference between each intraoperative assessment and the preoperative transthoracic echocardiography value was evaluated. |
From the available preoperative TTE assessment to the intraoperative TEE assessment during cardiac surgery
|
Collaborateurs et enquêteurs
Parrainer
Dates d'enregistrement des études
Dates principales de l'étude
Début de l'étude (Réel)
Achèvement primaire (Réel)
Achèvement de l'étude (Réel)
Dates d'inscription aux études
Première soumission
Première soumission répondant aux critères de contrôle qualité
Première publication (Réel)
Mises à jour des dossiers d'étude
Dernière mise à jour publiée (Réel)
Dernière mise à jour soumise répondant aux critères de contrôle qualité
Dernière vérification
Plus d'information
Termes liés à cette étude
Mots clés
Autres numéros d'identification d'étude
- FMASU MS 82/2026
Plan pour les données individuelles des participants (IPD)
Prévoyez-vous de partager les données individuelles des participants (DPI) ?
Description du régime IPD
Individual participant data will not be shared because external sharing of participant-level data was not included in the approved study protocol, ethics approval, or informed consent. Only aggregate study results will be reported.
Informations sur les médicaments et les dispositifs, documents d'étude
Étudie un produit pharmaceutique réglementé par la FDA américaine
Étudie un produit d'appareil réglementé par la FDA américaine
Ces informations ont été extraites directement du site Web clinicaltrials.gov sans aucune modification. Si vous avez des demandes de modification, de suppression ou de mise à jour des détails de votre étude, veuillez contacter register@clinicaltrials.gov. Dès qu'un changement est mis en œuvre sur clinicaltrials.gov, il sera également mis à jour automatiquement sur notre site Web .