Research Article

Empowering Medical Students: Harnessing Artificial Intelligence for Precision Point-of-Care Echocardiography Assessment of Left Ventricular Ejection Fraction

Table 1

Baseline demographics and clinical characteristics of those with successful AI vs. unsuccessful AI measurements.

VariableSuccessful AI measurement n = 82Unsuccessful AI measurement n = 6 value

Baseline demographic and clinical characteristics
Age (years), mean ± SD58.5 ± 16.854.7 ± 7.10.578
Male, n (%)72 (87.8)4 (66.7)0.188
BMI, mean ± SD28.2 ± 4.529.8 ± 3.60.397
Smoking, n (%)46 (56.1)4 (66.7)0.214
Ability to turn left, n (%)74 (90.2)6 (100)0.886
Effective communication, n (%)78 (95.1)6 (100)0.703
Active dyspnea, n (%)77 (93.9)6 (100)1.000
Lung disease, n (%)79 (96.3)5 (83.3)0.140

Exam quality+<0.001
Excellent, n (%)15 (18.3)0 (0.0)
High, n (%)24 (29.3)0 (0.0)
Moderate, n (%)41 (50.0)2 (33.3)
Poor, n (%)2 (2.4)4 (66.7)

Exam difficulty0.040
Easy, n (%)29 (35.4)0 (0.0)
Intermediate, n (%)26 (31.7)1 (16.7)
Difficult, n (%)27 (32.9)5 (83.3)

Admission diagnosis0.432
Heart failure, n (%)9 (11.0)2 (33.3)
Acute coronary syndrome, n (%)48 (58.5)3 (50.0)
Arrhythmia, n (%)11 (13.4)0 (0.0)
Perimyocarditis, n (%)8 (9.8)1 (16.7)
Other, n (%)6 (7.3)0 (0.0)

Exam setting
HR (bpm), mean ± SD73.9 ± 13.385.0 ± 18.50.056
Sinus rhythm, n (%)73 (89.0)6 (100)0.513
Length of study (minutes), mean ± SD6.3 ± 3.114.7 ± 3.4<0.001
Normal LVEF, n (%)++42 (51.2)2 (33.3)0.676
LVEF (%), mean ± SD++52.1 ± 11.338.9 ± 18.50.038

+As per cardiologist evaluation. As per medical student evaluation. ++As per expert echocardiographer assessment of the formal echocardiography. AI, artificial intelligence; BMI, body mass index; bpm, beats per minute; HR, heart rate; LVEF, left ventricular ejection fraction; n, number; SD, standard deviation. Bold values indicate the p value is statistically significant (less than 0.05).