Antithrombotic medication and bleeding risk in patients with cerebral cavernous malformations: a cohort study

Identifying potential (re)hemorrhage among sporadic cerebral cavernous malformations using machine learning

The (re)hemorrhage in patients with sporadic cerebral cavernous malformations (CCM) was the primary aim for CCM management. However, accurately identifying the potential (re)hemorrhage among sporadic CCM patients in advance remains a challenge. This study aims to develop machine learning models to detect potential (re)hemorrhage in sporadic CCM patients. This study was based on a dataset of 731 sporadic CCM patients in open data platform Dryad. Sporadic CCM patients were followed up 5 years from January 2003 to December 2018. Support vector machine (SVM), stacked generalization, and extreme gradient boosting (XGBoost) were used to construct models. The performance of models was evaluated by area under receiver operating characteristic curves (AUROC), area under the precision-recall curve (PR-AUC) and other metrics. A total of 517 patients with sporadic CCM were included (330 female [63.8%], mean [SD] age at diagnosis, 42.1 [15.5] years). 76 (re)hemorrhage (14.7%) occurred during follow-up. Among 3 machine learning models, XGBoost model yielded the highest mean (SD) AUROC (0.87 [0.06]) in cross-validation. The top 4 features of XGBoost model were ranked with SHAP (SHapley Additive exPlanations). All-Elements XGBoost model achieved an AUROCs of 0.84 and PR-AUC of 0.49 in testing set, with a sensitivity of 0.86 and a specificity of 0.76. Importantly, 4-Elements XGBoost model developed using top 4 features got a AUROCs of 0.83 and PR-AUC of 0.40, a sensitivity of 0.79, and a specificity of 0.72 in testing set. Two machine learning-based models achieved accurate performance in identifying potential (re)hemorrhages within 5 years in sporadic CCM patients. These models may provide insights for clinical decision-making.

Antithrombotic Therapy in Cerebral Cavernous Malformations: A Systematic Review, Meta-Analysis, and Network Meta-Analysis

BACKGROUND

Cerebral cavernous malformations are complex vascular anomalies in the central nervous system associated with a risk of intracranial hemorrhage. Traditional guidelines have been cautious about the use of antithrombotic therapy in this patient group, citing concerns about potential bleeding risk. However, recent research posits that antithrombotic therapy may actually be beneficial. This study aims to clarify the association between antithrombotic therapy, including antiplatelet and anticoagulant medications, and the risk of intracranial hemorrhage in patients with cerebral cavernous malformations.

METHODS AND RESULTS

A comprehensive literature search was conducted in PubMed, Web of Science, and Scopus databases, following Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Nine single-center, nonrandomized cohort studies involving 2709 patients were included. Outcomes were analyzed using random-effects model, and a network meta-analysis was conducted for further insight. Of the 2709 patients studied, 388 were on antithrombotic therapy. Patients on antithrombotic therapy had a lower risk of presenting with intracranial hemorrhage (odds ratio [OR], 0.56 [95% CI, 0.45-0.7]; P<0.0001). In addition, the use of antithrombotic therapy was associated with lower risk of intracranial hemorrhage from a cerebral cavernous malformation on follow-up (OR, 0.21 [95% CI, 0.13-0.35]; P<0.0001). A network meta-analysis revealed a nonsignificant OR of 0.73 (95% CI, 0.23-2.56) when antiplatelet therapy was compared with anticoagulant therapy.

CONCLUSIONS

Our study explores the potential benefits of antithrombotic therapy in cerebral cavernous malformations. Although the analysis suggests a possible role for antithrombotic agents, it is critical to note that the evidence remains preliminary. Fundamental biases in study design, such as ascertainment and assignment bias, limit the weight of our conclusions. Therefore, our findings should be considered hypothesis-generating and not definitive for clinical practice change.

Cavernous malformations of the central nervous system: An international consensus statement

Introduction

Cavernous malformations (CM) of the central nervous system constitute rare vascular lesions. They are usually asymptomatic, which has allowed their management to become quite debatable. Even when they become symptomatic their optimal mode and timing of treatment remains controversial.

Research question

A consensus may navigate neurosurgeons through the decision-making process of selecting the optimal treatment for asymptomatic and symptomatic CMs.

Material and methods

A 17-item questionnaire was developed to address controversial issues in relation to aspects of the treatment, surgical planning, optimal surgical strategy for specific age groups, the role of stereotactic radiosurgery, as well as a follow-up pattern. Consequently, a three-stage Delphi process was ran through 19 invited experts with the goal of reaching a consensus. The agreement rate for reaching a consensus was set at 70%.

Results

A consensus for surgical intervention was reached on the importance of the patient's age, symptomatology, and hemorrhagic recurrence; and the CM's location and size. The employment of advanced MRI techniques is considered of value for surgical planning. Observation for asymptomatic eloquent or deep-seated CMs represents the commonest practice among our panel. Surgical resection is considered when a deep-seated CM becomes symptomatic or after a second bleeding episode. Asymptomatic, image-proven hemorrhages constituted no indication for surgical resection for our panelists. Consensus was also reached on not resecting any developmental venous anomalies, and on resecting the associated hemosiderin rim only in epilepsy cases.

Discussion and conclusion

Our Delphi consensus provides an expert common practice for specific controversial issues of CM patient management.

Bleeding Risk of Cerebral Cavernous Malformations in Patients on Statin and Antiplatelet Medication: A Cohort Study

BACKGROUND

Statin medication has been identified as a potential therapeutic target for stabilizing cerebral cavernous malformations (CCMs). Although increasing evidence suggests that antiplatelet medication decreases the risk of CCM hemorrhage, data on statin medication in clinical studies are scarce.

OBJECTIVE

To assess the risk of symptomatic CCM-related hemorrhage at presentation and during follow-up in patients on statin and antiplatelet medication.

METHODS

A single-center database containing patients harboring CCMs was retrospectively analyzed over 41 years and interrogated for symptomatic hemorrhage at diagnosis, during follow-up, and statin and antiplatelet medication.

RESULTS

In total, 212 of 933 CCMs (22.7%), harbored by 688 patients, presented with hemorrhage at diagnosis. Statin medication was not associated with a decreased risk of hemorrhage at diagnosis (odds ratio [OR] 0.63, CI 0.23-1.69, P = .355); antiplatelet medication (OR 0.26, CI 0.08-0.86, P = .028) and combined statin and antiplatelet medication (OR 0.19, CI 0.05-0.66; P = .009) showed a decreased risk. In the antiplatelet-only group, 2 (4.7%) of 43 CCMs developed follow-up hemorrhage during 137.1 lesion-years compared with 67 (9.5%) of 703 CCMs during 3228.1 lesion-years in the nonmedication group. No follow-up hemorrhages occurred in the statin and the combined statin and antiplatelet medication group. Antiplatelet medication was not associated with follow-up hemorrhage (hazard ratio [HR] 0.7, CI 0.16-3.05; P = .634).

CONCLUSION

Antiplatelet medication alone and its combination with statins were associated with a lower risk of hemorrhage at CCM diagnosis. The risk reduction of combined statin and antiplatelet medication was greater than in patients receiving antiplatelet medication alone, indicating a possible synergistic effect. Antiplatelet medication alone was not associated with follow-up hemorrhage.

Long-term antithrombotic therapy and risk of intracranial haemorrhage from cerebral cavernous malformations: a population-based cohort study, systematic review, and meta-analysis

BACKGROUND

Antithrombotic (anticoagulant or antiplatelet) therapy is withheld from some patients with cerebral cavernous malformations, because of uncertainty around the safety of these drugs in such patients. We aimed to establish whether antithrombotic therapy is associated with an increased risk of intracranial haemorrhage in adults with cerebral cavernous malformations.

METHODS

In this population-based, cohort study, we used data from the Scottish Audit of Intracranial Vascular Malformations, which prospectively identified individuals aged 16 years and older living in Scotland who were first diagnosed with a cerebral cavernous malformation during 1999-2003 or 2006-10. We compared the association between use of antithrombotic therapy after first presentation and the occurrence of intracranial haemorrhage or persistent or progressive focal neurological deficit due to the cerebral cavernous malformations during up to 15 years of prospective follow-up with multivariable Cox proportional hazards regression assessed in all individuals identified in the database. We also did a systematic review and meta-analysis, in which we searched Ovid MEDLINE and Embase from database inception to Feb 1, 2019, to identify comparative studies to calculate the intracranial haemorrhage incidence rate ratio according to antithrombotic therapy use. We then generated a pooled estimate using the inverse variance method and a random effects model.

FINDINGS

We assessed 300 of 306 individuals with a cerebral cavernous malformation who were eligible for study. 61 used antithrombotic therapy (ten [16%] of 61 used anticoagulation) for a mean duration of 7·4 years (SD 5·4) during follow-up. Antithrombotic therapy use was associated with a lower risk of subsequent intracranial haemorrhage or focal neurological deficit (one [2%] of 61 vs 29 [12%] of 239, adjusted hazard ratio [HR] 0·12, 95% CI 0·02-0·88; p=0·037). In a meta-analysis of six cohort studies including 1342 patients, antithrombotic therapy use was associated with a lower risk of intracranial haemorrhage (eight [3%] of 253 vs 152 [14%] of 1089; incidence rate ratio 0·25, 95% CI 0·13-0·51; p<0·0001; I2=0%).

INTERPRETATION

Antithrombotic therapy use is associated with a lower risk of intracranial haemorrhage or focal neurological deficit from cerebral cavernous malformations than avoidance of antithrombotic therapy. These findings provide reassurance about safety for clinical practice and require further investigation in a randomised controlled trial.

FUNDING

UK Medical Research Council, Chief Scientist Office of the Scottish Government, The Stroke Association, Cavernoma Alliance UK, and the Remmert Adriaan Laan Foundation.