Back to 2025 Abstracts
Diagnosis Of Submassive Pulmonary Embolism (SMPE): CT Angiography (CTA), Echocardiography, And The Role Of Artificial Intelligence (AI)
Lauren A. Huntress, MD1, Matthew Sayegh, MD
2, Joseph Savarese, MD
1, John Ricotta, MD, FACS, DFSVS
1, Joseph J. Ricotta, MD, FACS
1.
1Delray Medical Center, Delray Beach, FL, USA,
2Florida Atlantic University Schmidt College of Medicine, Delray Beach, FL, USA.
OBJECTIVES: Early intervention in SMPE has been shown to improve long-term cardiopulmonary outcomes compared to anticoagulation alone. SMPE is diagnosed by documentation of RV/LV ratio > 0.9, indicative of right heart strain (RHS), and is associated with adverse clinical outcomes. Although often used interchangeably to guide treatment of SMPE, limited data exists comparing measurement of RV/LV ratio by CT Angiography (CTA) and Transthoracic Echocardiography (TTE). We also examined the role of AI in early detection of SMPE.
METHODS: A single-institution retrospective review of artificial intelligence-detected pulmonary embolism (Viz.ai) on CTA chest was performed over one year. Detection of PE on CTA by AI (CTA/AI) activated the pulmonary embolism response team (PERT). SMPE was defined by RV/LV ratio of >0.9. A TTE was performed in all patients with SMPE on CTA confirmed by radiology (CTA/RAD). In addition, some patients had TTE based on their clinical condition despite RV/LV <0.9 by CTA. Using Chi-squared analysis, we compared ability to detect SMPE by CTA/RAD with TTE.
RESULTS: Over one year, 201 Viz.ai activations for suspected PE on CTA chest were reviewed (n=112 male (56%), n=89 female (44%), mean age = 72 +/- 17 years). PE was detected in 121 patients on CTA/RAD, and 105 patients had RV/LV ratio calculated on both CTA/RAD and TTE during evaluation for SMPE. 47 of 105 patients (45%) had RHS on CTA/RAD, but no RHS on TTE. When comparing CTA/RAD to TTE, the average RV/LV ratio was 0.32 +/- 0.34 (p>0.0001) higher than on CTA/RAD. When compared to CTA/RAD, CTA/AI had a PPV of 0.6 for detection of any PE. Using TTE as the standard, CTA/RAD had a PPV of 0.44, NPV of 0.9 for detection of SMPE.
CONCLUSIONS: Our study suggests the need for further improvements in CTA/AI PE detection and that CTA/RAD is suboptimal in the evaluation of SMPE in isolation. We also noted that CTA/RAD significantly overestimates the RV/LV ratio and thereby RHS compared to TTE. Basing the need for intervention solely on CTA/RAD may subject patients unnecessarily to the risks associated with intervention for SMPE. Our data suggests the importance of including both CTA and TTE in the PERT algorithm, and that these imaging modalities should not be used interchangeably, but synergistically to guide treatment for SMPE.
Back to 2025 Abstracts
