Efficacy of AI EF Screening by Using Smartphone Application Recorded PLAX View Cardiac Ultrasound Video Clips

Rayong Hospital

Status: Completed

Conditions: Cardiac Failure; Artificial Intelligence; Echocardiography; Heart Failure With Reduced Ejection Fraction; Heart Failure

Treatments: Other: Easy EF

Study type: Interventional

Funder types: Other

Identifiers

NCT06330103

RayongH

Details and patient eligibility

About

Assessing the Efficacy of Artificial Intelligence in Left Ventricular Function Screening Using Parasternal Long Axis View Cardiac Ultrasound Video Clips

ABSTRACT BACKGROUND: Echocardiography serves as a fundamental diagnostic procedure for managing heart failure patients. Data from Thailand's Ministry of Public Health reveals that there is a substantial patient population, with over 100,000 admissions annually due to this condition. Nevertheless, the widespread implementation of echocardiography in this patient group remains challenging, primarily due to limitations in specialist resources, particularly in rural community hospitals. Although modern community hospitals are equipped with ultrasound machines capable of basic cardiac assessment (e.g., parasternal long axis view), the demand for expert cardiologists remains a formidable obstacle to achieving comprehensive diagnostic capabilities. Leveraging the capabilities of Artificial Intelligence (AI) technology, proficient in the accurate prediction and processing of diverse healthcare data types, offers a promising for addressing this prevailing issue. This study is designed to assess the effectiveness of AI in evaluating cardiac performance from parasternal long axis view ultrasound video clips obtained via the smartphone application.

OBJECTIVES: To evaluate the effectiveness of artificial intelligence in screening cardiac function from parasternal long axis view cardiac ultrasound video clips obtained through the smartphone application.

Full description

METHODS: The investigators built the smartphone application to collect parasternal long axis view video clips and used artificial intelligence "Easy EF" to evaluate cardiac function. All samples that were evaluated for LVEF by certified cardiologists, 70% of all clips were used to train AI, while the remaining 30% of clips were used to test if AI could process the results correctly. Artificial intelligence aims to classify cardiac function into three groups: Reduced EF, Mildly Reduced EF, and Preserved LV.

Enrollment: 923 patients

Sex: All

Volunteers: Accepts Healthy Volunteers

Inclusion criteria

• Shot 5 second VDO clip of Parasternal long axis heart ultrasound recorded by smartphone Application "Easy EF" without patient identification with result of Ejection fraction that performed by certify cardiologist approved result

Exclusion criteria

• Incomplete VDO clip (too much shaking, too shot recording)
• Lighting was inappropriate
• Inappropriate ultrasound framing
• arrhythmia (atrial fibrillation)

Trial design

Primary purpose: Diagnostic

Allocation: Non-Randomized

Interventional model: Parallel Assignment

Masking: Single Blind

---

923 participants in 2 patient groups

LV function from cardiologist

Active Comparator group

Description:

Certified Cardiologist will access and interpreted LV function by used traditional Echocardiography then separate result into three group Preserved LV ejection fraction(EF\>50%), mildly reduce ejection fraction(EF40-49%), reduced LV ejection fraction(EF\<40%)

Treatment:

Other: Easy EF

LV function By artificial intelligence

Experimental group

Description:

AI will access VDO clips in only parasternal long axis view and separate into three group Preserved LV ejection fraction(EF\>50%), mildly reduce ejection fraction(EF40-49%), reduced LV ejection fraction(EF\<40%)

Treatment:

Other: Easy EF