Machine Learning Framework for Thrombosis Risk Prediction in Rotary Blood Pumps

TL;DR

This paper presents an interpretable machine learning framework that predicts thrombosis risk in rotary blood pumps using CFD-derived flow features, enabling rapid, transparent risk assessment and device optimization.

Contribution

It introduces a novel, physically interpretable ML approach combining logistic regression with feature selection for thrombosis risk prediction based on CFD data.

Findings

The model accurately reproduces risk distributions in validation scenarios.

It identifies key flow features associated with thrombosis risk.

The framework enables rapid thrombogenicity screening with low computational cost.

Abstract

Thrombosis in rotary blood pumps arises from complex flow conditions that remain difficult to translate into reliable and interpretable risk predictions using existing computational models. This limitation reflects an incomplete understanding of how specific flow features contribute to thrombus initiation and growth. This study introduces an interpretable machine learning framework for spatial thrombosis assessment based directly on computational fluid dynamics-derived flow features. A logistic regression (LR) model combined with a structured feature-selection pipeline is used to derive a compact and physically interpretable feature set, including nonlinear feature combinations. The framework is trained using spatial risk patterns from a validated, macro-scale thrombosis model for two representative scenarios. The model reproduces the labeled risk distributions and identifies distinct sets of flow features associated with increased thrombosis risk. When applied to a centrifugal pump, despite training on a single axial pump operating point, the model predicts plausible thrombosis-prone regions. These results show that interpretable machine learning can link local flow features to thrombosis risk while remaining computationally efficient and mechanistically transparent. The low computational cost enables rapid thrombogenicity screening without repeated or costly simulations. The proposed framework complements physics-based thrombosis modeling and provides a methodological basis for integrating interpretable machine learning into CFD-driven thrombosis analysis and device design workflows.