Development and internal validation of an interpretable machine learning model to predict coagulopathy following extracorporeal membrane oxygenation: a retrospective multicenter study

TL;DR

Researchers developed and validated a machine learning model to predict coagulopathy in ECMO patients, identifying key factors like platelet levels and lactate for better clinical management.

Contribution

An optimized, interpretable machine learning model (ECMO-IC index) was developed and internally validated for predicting ECMO-induced coagulopathy.

Findings

The ECMO-IC index achieved strong diagnostic performance with an AUC of 0.815 in derivation and validation cohorts.

SHAP analysis highlighted the importance of platelet count, lactate, potassium, and APACHE II in predicting ECMO-IC.

Nonlinear relationships and threshold effects were identified for key variables using RCS regression and threshold analysis.

Abstract

Extracorporeal membrane oxygenation-induced coagulopathy (ECMO-IC) represents a frequent and severe complication, contributing to oxygenator replacement and unfavorable outcomes. Currently, no reliable machine learning (ML) model exists for early identification. This study comprehensively assesses routine clinical characteristics to develop a reliable, accurate, and explainable ML model for estimating ECMO-IC risk and to identify modifiable factors.

This study included two center cohorts with 266 patients undergoing ECMO from 2015 to 2024. Feature selection utilized the Boruta algorithm, followed by the implementation of a distinctive ML framework incorporating 12 ML algorithms to establish a consensus prediction model (ECMO-IC index). Model and feature variable assessment employed multiple analytical methods: Bootstrapping and fivefold cross-validation, subgroup and interaction analysis, restricted cubic spline (RCS) regression, and threshold effect analysis. Model interpretation and feature quantification relied on the Shapley Additive Explanations (SHAP) methodology for visualization purposes.

Through Boruta algorithm selection, 17 characteristics were identified and incorporated into 12 ML methodologies, generating 105 permutations and an optimal algorithm for identifying ECMO-IC. The ECMO-IC index comprising 9 modifiable or nonmodifiable variables, namely platelet (PLT), lactate, systemic immune-inflammation index (SII), K, total protein (TP), shock index (SI), red blood cell volume distribution width (RDWCV), acute physiology and chronic health evaluation II (APACHE II), and Ca, demonstrated strong diagnostic capabilities, achieving a mean area under the curve (AUC) of 0.815 across derivation (AUC = 0.817) and validation (AUC = 0.813) cohorts, along with notable discriminatory power, model fit, and clinical utility. SHAP elucidates the importance of ranking features (PLT, lactate, K, Ca and APACHE II) and visualises global and individual ECMO-IC risk prediction. RCS regression and threshold effect analysis suggested a nonlinear link between model features (PLT: P for nonlinearity = 0.002, SII: P for nonlinearity = 0.001, K: P for nonlinearity = 0.006, Ca: P for nonlinearity = 0.008, and lactate: P for nonlinearity = 0.004) and ECMO-IC, and generated an inflection point for features (PLT = 95 × 109/L, lactate = 5.7 mmol/L, SII = 200, K = 4.4 mmol/L, TP = 45.6 g/L, SI = 0.8, RDWCV = 14%, APACHE II = 15, Ca = 1.03 mmol/L). To provide a more flexible predictive tool, the ECMO-IC model was constructed using a free, publicly available web-based calculator (https://genglongliu.shinyapps.io/DynNomapp/).

An optimised explainable ML model (ECMO-IC index) incorporating several modifiable parameters was established and internally validated to deliver an readily available and accurate diagnostic tool for ECMO-IC, with potential applications in ECMO clinical management.

The online version contains supplementary material available at 10.1186/s13049-026-01564-x.

Figures