Predicting functional results of percutaneous coronary intervention using machine learning modelling

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Root mean square error 0.036 (95% CI: 0.033-0.040)

• Primary Outcome: Continuous post-PCI μFR prediction accuracy

• Nnt Or Sensitivity: Sensitivity 0.90 (95% CI: 0.88-0.93), Specificity 0.29 (95% CI: 0.23-0.34), AUC 0.72 (95% CI: 0.69-0.74)

• Confidence Interval: Mean absolute error 0.030 (95% CI: 0.027-0.032)

Clinical Application

Requires sophisticated data infrastructure and validated implementation protocols before clinical deployment Would need validation in Australian PCI populations and integration with existing cardiac catheterisation laboratory workflows. TGA approval likely required for clinical decision support software. Patients undergoing elective PCI where pre-procedural physiological assessment is feasible

Abstract

BACKGROUND: Post-percutaneous coronary intervention (PCI) Murray's law-based quantitative flow ratio (μFR) is associated with long-term clinical outcomes. A tool capable of accurately predicting post-PCI μFR before intervention could support procedural planning, reduce the risk of suboptimal physiological results, and improve prognosis. OBJECTIVES: To develop and validate machine-learning models that predict continuous post-PCI μFR using only pre-procedural angiographic, physiological and clinical data, and to assess their ability to classify PCI outcomes as optimal (μFR ≥ 0.91) or sub-optimal (μFR < 0.91). METHODS: Four machine learning models were trained using pre-PCI variables. Internal bootstrap validation (1000 iterations) identified the best-performing model based on lowest root mean square error (RMSE) for continuous prediction. Predicted μFR values were subsequently used to classify PCI outcomes. RESULTS: In 343 vessels (291 patients), machine learning achieved high accuracy for continuous post-PCI μFR prediction (RMSE 0.036; 95% CI: 0.033-0.040; mean absolute error 0.030; 95% CI: 0.027-0.032; mean absolute percentage error 3.2%; 95% CI: 2.9-3.5), indicating reliable estimation of post-PCI μFR using only pre-procedural data. When the predicted μFR was used to classify PCI outcomes, performance remained clinically meaningful, with accuracy 0.72 (95% CI: 0.70-0.75), area under the curve 0.72 (95% CI: 0.69-0.74), sensitivity 0.90 (95% CI: 0.88-0.93), and specificity 0.29 (95% CI: 0.23-0.34). The high sensitivity ensures reliable upfront identification of vessels likely to achieve optimal physiology. CONCLUSIONS: Machine-learning models accurately predict post-PCI μFR and reliably distinguish optimal from sub-optimal outcomes before intervention. This approach supports personalized PCI planning and improves strategy selection.

References

1. 1.Fezzi, S., Zhu, Y., Bargary, N., Ding, D., Scarsini, R., Lunardi, M., Leone, A. M., Mammone, C., Wagener, M., McInerney, A., Toth, G. G., Pesarini, G., Connolly, D., Trani, C., Tu, S., Burzotta, F., Ribichini, F., Simpkin, A. J., & Wijns, W. (2026). Predicting functional results of percutaneous coronary intervention using machine learning modelling. International Journal of Cardiology, 134183. https://doi.org/10.1016/j.ijcard.2026.134183