Machine learning to predict futile recanalization of large vessel occlusion before and after endovascular thrombectomy

Abstract

Background and purposeFutile recanalization occurs when the endovascular thrombectomy (EVT) is a technical success but fails to achieve a favorable outcome. This study aimed to use machine learning (ML) algorithms to develop a pre-EVT model and a post-EVT model to predict the risk of futile recanalization and to provide meaningful insights to assess the prognostic factors associated with futile recanalization.MethodsConsecutive acute ischemic stroke patients with large vessel occlusion (LVO) undergoing EVT at the National Advanced Stroke Center of Nanjing First Hospital (China) between April 2017 and May 2021 were analyzed. The baseline characteristics and peri-interventional characteristics were assessed using four ML algorithms. The predictive performance was evaluated by the area under curve (AUC) of receiver operating characteristic and calibration curve. In addition, the SHapley Additive exPlanations (SHAP) approach and partial dependence plot were introduced to understand the relative importance and the influence of a single feature.ResultsA total of 312 patients were included in this study. Of the four ML models that include baseline characteristics, the “Early” XGBoost had a better performance {AUC, 0.790 [95% confidence intervals (CI), 0.677–0.903]; Brier, 0.191}. Subsequent inclusion of peri-interventional characteristics into the “Early” XGBoost showed that the “Late” XGBoost performed better [AUC, 0.910 (95% CI, 0.837–0.984); Brier, 0.123]. NIHSS after 24 h, age, groin to recanalization, and the number of passages were the critical prognostic factors associated with futile recanalization, and the SHAP approach shows that NIHSS after 24 h ranks first in relative importance.ConclusionsThe “Early” XGBoost and the “Late” XGBoost allowed us to predict futile recanalization before and after EVT accurately. Our study suggests that including peri-interventional characteristics may lead to superior predictive performance compared to a model based on baseline characteristics only. In addition, NIHSS after 24 h was the most important prognostic factor for futile recanalization.

Neuroimaging of Acute Ischemic Stroke: Multimodal Imaging Approach for Acute Endovascular Therapy

“…125 These algorithms are useful to detect LVO, delineate the core, penumbra size and target mismatch, 126 score collaterals, 127 classify stroke mechanisms, 128 and predict outcomes and risk of hemorrhagic transformation after EVT in ischemic stroke patients. 129,130 The role of machine learning is evolving and will continue to play a role in the diagnosis and management of cerebrovascular diseases in the future. Further integration of artificial intelligence and machine learning in acute stroke care is inevitable.…”

“…Commercially available machine learning algorithms have been integrated into clinical setting to support the time-sensitive decision-making for rapid diagnosis and image analysis; no significant differences have been observed between software [ 125 ]. These algorithms are useful to detect LVO, delineate the core, penumbra size and target mismatch [ 126 ], score collaterals [ 127 ], classify stroke mechanisms [ 128 ], and predict outcomes and risk of hemorrhagic transformation after EVT in ischemic stroke patients [ 129 , 130 ]. The role of machine learning is evolving and will continue to play a role in the diagnosis and management of cerebrovascular diseases in the future.…”

Machine learning model to predict 3-month nonunion(delayed union) of unstable distal clavicle fracture patients treated with open reduction and internal fixation

“…Recent research has demonstrated the growing application of ML models in the medical sector [11][12][13][14][15][16].ML models incorporate a variety of advanced algorithms to handle different data characteristics, including State-Action-Reward-State-Action , Random Forest Classi er, Deep Q Network, and Support Vector Machine [17].In comparison to traditional regression models, ML has been validated as an effective method for prognosis prediction in modeling due to its capacity to intricately analyze complex non-linear interrelations among variables [18,19], and to enhance prediction accuracy through its superior algorithms, particularly when analyzing large datasets with numerous variables [20,21]. Crucially, the widespread adoption of Electronic Patient Record systems and the extensive use of structured patient data have made sophisticated algorithmic modeling and bedside application feasible [22].…”

Introducing the Futile Recanalization Prediction Score (FRPS): A Novel Approach to Predict and Mitigate Ineffective Recanalization after Endovascular Treatment of Acute Ischemic Stroke

“…A risk prediction score to mitigate harm among subgroups of patients at risk of FR is warranted. However, minimal studies have explored this area [ 6 ].…”