Does AI-driven longitudinal quantification of Tc-PYP uptake correlate with multimodality imaging and predict outcomes in patients with cardiac amyloidosis?
AI-driven longitudinal quantification of Tc-PYP uptake correlates with other imaging measures and predicts the risk of cardiovascular death or heart failure hospitalization in patients with cardiac amyloidosis.
BACKGROUND: Tc-PYP) deep learning measurements with changes in other imaging parameters and clinical outcomes. METHODS: Tc-PYP images were quantified using our previously developed deep learning methodology including assessment of cardiac pyrophosphate activity (CPA) and volume of involvement (VOI). RESULTS: In total, 85 patients were included, with a median population age of 79 years (interquartile range IQR: 72 - 84) and 76 (89%) male patients. In patients on therapy, there was a reduction in VOI (median: 100 to 51, P < 0.001), CPA (median: 165 to 81, P < 0.001), native T1 (median: 1400 to 1387, P = 0.005), and extracellular volume (median: 50 to 49, P = 0.035) during a median time of 369 days (IQR: 365-516) between scans. There was a modest correlation between change in CPA and change in native T1 (ρ = 0.376, P = 0.009). After adjusting for age, treatment, and CPA at follow-up, an increase in CPA during follow-up was also associated with an increased risk (adjusted hazard ratio: 2.31 per standard deviation increase, 95% confidence interval: 1.28-4.17, P = 0.005). CONCLUSIONS: Tc-PYP quantitation has modest correlations with other measures of disease burden including native T1. Changes in these measures were associated with risk of cardiovascular death or HF hospitalization, suggesting that the serial measurements may be clinically meaningful surrogate endpoints.
Miller et al. (Thu,) studied this question.