Senlin Du,1– 4,* Yanze Wu,1– 4,* Jiarong Tao,1 Lei Shu,1– 4 Tengfeng Yan,1– 4 Bing Xiao,1 Shigang Lv,1 Minhua Ye,1 Yanyan Gong,1 Xingen Zhu,1– 4 Ping Hu,1,5 Miaojing Wu1 

1Department of Neurosurgery, The second Affiliated Hospital, Jiangxi Medical College of Nanchang University, Nanchang, 330006, People’s Republic of China; 2Jiangxi Key Laboratory of Neurological Tumors and Cerebrovascular Diseases, Nanchang, 330006, People’s Republic of China; 3Jiangxi Health Commission Key Laboratory of Neurological Medicine, Nanchang, 330006, People’s Republic of China; 4Institute of Neuroscience, Nanchang University, Nanchang, 330006, People’s Republic of China; 5Department of Neurosurgery, Panzhihua Central Hospital, The second Clinical Medical College of Panzhihua University, Panzhihua, 617067, People’s Republic of China

*These authors contributed equally to this work

Correspondence: Miaojing Wu, Department of Neurosurgery, The second Affiliated Hospital, Jiangxi Medical College of Nanchang University, Nanchang, 330006, People’s Republic of China, Email wmj1987@163.com

Background: Endovascular treatment (EVT) has been recommended as a superior modality for the treatment of intracranial aneurysm. However, there still exists a worse percentage of poor functional outcome in patients with poor-grade aneurysmal subarachnoid hemorrhage (aSAH) undergoing EVT. Therefore, it is urgently needed to investigate the risk factors and develop a critical decision model in the subtype of such patients.
Methods: We extracted the target variables from an ongoing registry cohort study, PROSAH-MPC, which was conducted in multiple centers in China. We randomly assigned these patients to training and validation cohorts with a ratio of 7:3. Univariate and multivariate logistic regressions were performed to find the potential factors, and then nine machine learning models and a stack ensemble model were developed with optimized variables. The performance of these models was evaluated through several indicators, including area under the receiver operating characteristic curve (AUC-ROC). We further use Shapley Additive Explanations (SHAP) methods for the distribution of feature visualization based on the optimal models.
Results: A total of 226 eligible patients with poor-grade aSAH undergoing EVT were enrolled, while 89 (39.4%) has a poor 12-month outcome. Age (Adjusted OR [aOR], 1.08; 95% CI: 1.03– 1.13; p = 0.002), subarachnoid hemorrhage volume (aOR, 1.02; 95% CI: 1.00– 1.05; p = 0.033), World Federation of Neurosurgical Societies grade (WFNS) (aOR, 2.03; 95% CI: 1.05– 3.93; p = 0.035), and Hunt-Hess grade (aOR, 2.36; 95% CI: 1.13– 4.93; p = 0.022) were identified as the independent risk factors of the poor outcome. Then, the prediction models developed have revealed that LightGBM algorithm has a superior performance with an AUC-ROC value of 0.842 in the validation cohort, while the SHAP results showed that age is the most important risk factor affecting functional outcomes.
Conclusion: The LightGBM model holds immense potential in facilitating risk stratification for poor-grade aSAH patients undergoing endovascular treatment who are at risk of adverse outcomes, thereby enhancing clinical decision-making processes.
Trial Registration: PROSAH-MPC. NCT05738083. Registered 16 November 2022 – Retrospectively registered, http://clinicaltrials.gov/study/NCT05738083.

Keywords: intracranial aneurysm, subarachnoid hemorrhage, endovascular procedures, machine learning, prognosis