Pre-treatment re-bleeding following aneurysmal subarachnoid hemorrhage: A systematic review of published prediction models with risk of bias and clinical applicability assessment.

Background: Pre-treatment rebleeding following aneurysmal subarachnoid hemorrhage (aSAH) increases the risk of death and a poor neurological outcome. Current guidelines recommend aneurysm treatment "as early as feasible after presentation, preferably within 24 h of onset" to mitigate this risk, a practice termed ultra-early treatment. However, ongoing debate regarding whether ultra-early treatment is independently associated with reduced re-bleeding risk, together with the recognition that re-bleeding occurs even in centres practicing ultra-early treatment due to the presence of other risk-factors has resulted in a renewed need for patient-specific re-bleed risk prediction. Here, we systematically review models which seek to provide patient specific predictions of pre-treatment rebleeding risk.

Methods: Following registration on the International prospective register of systematic reviews (PROSPERO) CRD 42023421235; Ovid Medline (Pubmed), Embase and Googlescholar were searched for English language studies between 1st May 2002 and 1st June 2023 describing pre-treatment rebleed prediction models following aSAH in adults ≥18 years. Of 763 unique records, 17 full texts were scrutinised with 5 publications describing 4 models reviewed. We used the semi-automated template of Fernandez-Felix et al. incorporating the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS) checklist and the Prediction model Risk Of Bias ASsessment Tool (PROBAST) for data extraction, risk of bias and clinical applicability assessment. To further standardize risk of bias and clinical applicability assessment, we also used the published explanatory notes for the PROBAST tool and compared the aneurysm treatment practices each prediction model's formulation cohort experienced to a prespecified benchmark representative of contemporary aneurysm treatment practices as outlined in recent evidence-based guidelines and published practice pattern reports from four developed countries.

Results: Reported model discriminative performance varied between 0.77 and 0.939, however, no single model demonstrated a consistently low risk of bias and low concern for clinical applicability in all domains. Only the score of Darkwah Oppong et al. was formulated using a patient cohort in which the majority of patients were managed in accordance with contemporary, evidence-based aneurysm treatment practices defined by ultra-early and predominantly endovascular treatment. However, this model did not undergo calibration or clinical utility analysis and when applied to an external cohort, its discriminative performance was substantially lower that reported at formulation.

Conclusions: No existing prediction model can be recommended for clinical use in centers practicing contemporary, evidence-based aneurysm treatment. There is a pressing need for improved prediction models to estimate and minimize pre-treatment re-bleeding risk.