Multi-Center Registry Cohort Study on Prognostic Factors and Prediction Model Construction in Aneurysmal SAH

Official title

Multi-Center Registry Cohort Study on Prognostic Factors and Prediction Model Construction in Aneurysmal Subarachnoid Hemorrhage

Overview

PROSAH-MPC, a collaborative research project among neurosurgical centers in China, focuses on aneurysmal subarachnoid hemorrhage (aSAH). Its aim is to identify prognostic factors and develop robust prediction models for complications, disability, and mortality in aSAH patients. By leveraging a large, multi-center, prospective cohort design, PROSAH-MPC aims to overcome limitations of past studies and provide a more comprehensive understanding of the disease.

Detailed description

PROSAH-MPC (Prognostic Factors and Prediction Models in Aneurysmal Subarachnoid Hemorrhage Multi-Center Prospective Cohort) is an ambitious research endeavor that brings together a consortium of neurosurgical centers across various regions to comprehensively investigate the complexities of aneurysmal subarachnoid hemorrhage (aSAH). This multi-faceted study aims to unlock the prognostic factors that underpin the outcomes of patients afflicted with this severe and often life-threatening cerebrovascular disorder.

The primary objective of PROSAH-MPC is to construct and validate robust prediction models that can accurately forecast the risks of complications, disability, and mortality in aSAH patients. By leveraging the strengths of a large, multi-center, prospective cohort design, the study aims to overcome the limitations of previous single-center, limited sample size, or retrospective studies, enabling a more holistic and generalizable understanding of the disease.

Central to the study is the collection of extensive clinical and radiological data from enrolled patients, including demographics, medical histories, treatment regimens, radiological features, and follow-up outcomes. Radiomic analysis of imaging data, such as CT and MRI scans, will be employed to extract subtle but crucial features that may predict patient outcomes by deep learning. This data-rich approach ensures that the prediction models are built on a solid foundation of evidence-based knowledge.

PROSAH-MPC's ultimate goal is to transform the way we approach aSAH management by providing clinicians with reliable tools to assess individual patient risks and tailor treatment plans accordingly. The validated prediction models have the potential to enhance early recognition of high-risk patients, facilitate timely interventions, and ultimately improve patient outcomes and quality of life.

Interventions

• Diagnostic test Machine Leaning Models
  Area Under the Curve (ROC): Measures the overall performance of the model across all classification thresholds. A higher AUC value indicates better performance. Accuracy: The proportion of correctly predicted outcomes (both positive and negative) out of all predictions made. Precision (Positive Predictive Value, PPV): The proportion of correctly predicted positive outcomes out of all predicted positive outcomes. Sensitivity (True Positive Rate, TPR): The proportion of actual positive outcomes

Primary outcome measures

• modified Rankin Scale (mRS) for evaluating the prognosis [Time frame: 12 months post-event]
• Delayed cerebral ischemia (DCI) [Time frame: 30 days post-event]

Secondary outcome measures (4)

• Rebleeding [Time frame: 30 days post-event]
• Intracranial Aneurysm Re-Rupture [Time frame: 30 days post-event]
• Hydrocephalus [Time frame: 30 days post-event]
• Clearing Rate of Subarachnoid Hemorrhage [Time frame: 14 days post-admission CT scan]

Eligibility criteria

Inclusion criteria

• Subarachnoid hemorrhage confirmed by computed tomography (CT);
• Cerebral angiography (CTA) and digital subtraction angiography (DSA) examination confirming intracranial aneurysm rupture as the cause of the subarachnoid hemorrhage;
• Blood routine, biochemical function, blood coagulation function, and craniocerebral CT performed within 24 hours of symptom onset;
• Underwent aneurysm clipping by surgery or endovascular embolization within 72 hours after-onset.

Exclusion criteria

• Aneurysm rupture bleeding time exceeding 24 hours before hospital admission;
• Incomplete image data or blood test information;
• Long-term use of anticoagulant medications such as aspirin or warfarin;
• Admitted to hospital with active infectious diseases;
• long-term anticoagulant drugs such as aspirin, wave dimensions;
• Presence of other intracranial vascular malformations.

Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.

Healthy volunteers: No

Study design

Observational model

Cohort

Study locations

China · 1 center

• The Second Affiliated Hospital of Nanchang University — Nanchang

Publications

• Du S, Wu Y, Tao J, Shu L, Yan T, Xiao B, Lv S, Ye M, Gong Y, Zhu X, Hu P, Wu M. Development and Validation of Machine Learning Models for Outcome Prediction in Patients with Poor-Grade Aneurysmal Subarachnoid Hemorrhage Following Endovascular Treatment. Ther Clin Risk Manag. 2025 Mar 7;21:293-307. doi: 10.2147/TCRM.S504745. eCollection 2025. PMID 40071129
• Shu L, Xiao B, Jiang Y, Tang S, Yan T, Wu Y, Wu M, Lv S, Lai X, Zhu X, Hu P, Ye M. Comparison of LVIS and Enterprise stent-assisted coiling embolization for ruptured intracranial aneurysms: a propensity score-matched cohort study. Neurosurg Rev. 2024 Sep 7;47(1):560. doi: 10.1007/s10143-024-02756-8. PMID 39242449
• Hu P, Wu Y, Yan T, Shu L, Liu F, Xiao B, Ye M, Wu M, Lv S, Zhu X. Deep learning-based quantification of total bleeding volume and its association with complications, disability, and death in patients with aneurysmal subarachnoid hemorrhage. J Neurosurg. 2024 Mar 29;141(2):343-354. doi: 10.3171/2024.1.JNS232280. Print 2024 Aug 1. PMID 38552240

Identifiers

NCT: NCT05738083 · IIT-O-2023-011

Primary sources (government registries)

• ClinicalTrials.gov (US NIH)

View this study on ClinicalTrials.gov ↗