Background and purpose The ever-growing availability of imaging led to increasing incidentally discovered unruptured intracranial aneurysms (UIAs). We leveraged machine-learning techniques and advanced statistical methods to provide new insights into rupture intracranial aneurysm (RIA) risks.
Methods We analysed the characteristics of 2505 patients with intracranial aneurysms (IA) discovered between 2016 and 2019. Baseline characteristics, familial history of IA, tobacco and alcohol consumption, pharmacological treatments before the IA diagnosis, cardiovascular risk factors and comorbidities, headaches, allergy and atopy, IA location, absolute IA size and adjusted size ratio (aSR) were analysed with a multivariable logistic regression (MLR) model. A random forest (RF) method globally assessed the risk factors and evaluated the predictive capacity of a multivariate model.
Results Among 994 patients with RIA (39.7%) and 1511 patients with UIA (60.3 %), the MLR showed that IA location appeared to be the most significant factor associated with RIA (OR, 95% CI: internal carotid artery, reference; middle cerebral artery, 2.72, 2.02–3.58; anterior cerebral artery, 4.99, 3.61–6.92; posterior circulation arteries, 6.05, 4.41–8.33). Size and aSR were not significant factors associated with RIA in the MLR model and antiplatelet-treatment intake patients were less likely to have RIA (OR: 0.74; 95% CI: 0.55–0.98). IA location, age, following by aSR were the best predictors of RIA using the RF model.
Conclusions The location of IA is the most consistent parameter associated with RIA. The use of ‘artificial intelligence’ RF helps to re-evaluate the contribution and selection of each risk factor in the multivariate model.
- intracranial aneurysm
- machine learning
- decision trees
Statistics from Altmetric.com
If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.
Collaborators The ICAN Investigators are: Hubert Desal, Romain Bourcier, Richard Redon, Gervaise Loirand, Jean-Jacques Schott, Stéphanie Chatel, Emmanuelle Bourcereau, Christian Dina, Floriane Simonet, Eric Charpentier, Estelle Baron, Stéphanie Bonnaud, Benjamin Daumas-Duport, Bertrand Isidor, Jérôme Connault, Pierre Lebranchu, Antoine Rimbert, Thierry Le Tourneau, Chrisanthi Papagiannaki, Michel Piotin, Hocine Redjem, Mikael Mazighi, Jean Philippe Desilles, Olivier Naggara, Denis Trystram, Myriam Edjlali-Goujon, Grégoire Boulouis, Christine Rodriguez, Waghi Ben Hassen, Suzanna Saleme, Charbel Mounayer, Aymeric Rouchaud, Olivier Levrier, Pierre Aguettaz, Xavier Combaz, Anne Pasco, Vincent l’Allinec, Marc Bintner, Marc Molho, Pascale Gauthier, Cyril Chivot, Vincent Costalat, Cyril Darganzil, Alain Bonafé, Anne Christine Januel, Caterina Michelozzi, Christophe Cognard, Fabrice Bonneville, Philippe Tall, Jean Darcourt, Alessandra Biondi, Cristina Iosif, Jean Christophe Ferre, Jean Yves Gauvrit, François Eugene, Hélène Raoult, Jean Christophe Gentric, Julien Ognard, René Anxionnat, Benjamin Gory, Serge Bracard, Anne Laure Derelle, Romain Tonnelet, Laurent Spelle, Léon Ikka, Augustin Ozanne, Sophie Gallas, Jildaz Caroff, Nidal Ben Achour, Jacques Moret, Emmanuel Chabert, Jérôme Berge, Gaultier Marnat, Xavier Barreau, Florent Gariel, Frédéric Clarencon, Eimad Shotar, Mohammed Aggour, Frédéric Ricolfi, Adrien Chavent, Pierre Thouant, Pablo Lebidinsky, Brivael Lemogne, Denis Herbreteau, Richard Bibi, Kevin Janot, Laurent Pierot, Sébastien Soize, Marc Antoine Labeyrie, Christophe Vandendries, Emmanuel Houdart, Appoline Kazemi, Xavier Leclerc, Jean Pierre Pruvo, Nicolas Bricout, Stéphane Velasco, Samy Boucebci.
Contributors OR, MK and PAG have performed the statistical analysis and have written the manuscript. AG, LB, PB, PCDB, VL’A, OL, PA, J-PD, CM, GM, A-CV, GL, HD and RR have acquired the data and made a critical review of the manuscript. RB has conceived the study and written the manuscript.
Funding This study was supported by a grant from the National Research Agency and the French Ministry of Health (ANR-DGOS 2015), Agence Nationale de la Recherche, 50, avenue Daumesnil, 75012 PARIS, 01.78.09.80.00— DGOS 14 Avenue Duquesne, 75 007 Paris, France, 01 40 56 60 00, The French Regional Council of Pays de la Loire (RFI VaCaRMe), Hôtel de la région 1, rue de la Loire 44 966 Nantes Cedex 9, 02 28 20 50 00, and The Fondation GENAVIE 8 Quai Moncousu, 44 000 Nantes, France, 02 28 08 01 13.
Competing interests None declared.
Patient consent for publication Not required.
Ethics approval The ICAN project is a non-interventional clinical research, approved by the Institutional Review Boards (Comité consultatif sur le traitement de l’information en matière de recherche dans le domaine de la santé, Commission Nationale de l’Informatique et des Libertés) and Ethics Committees of Nantes. Informed written consent has been obtained from all patients and the biobank called Génétique et biomarqueurs des pathologies cardiovasculaires, respiratoires et leur facteur de risques is approved by the French Ministry of Research (n◦ DC-2011-1399) and by the Comité de Protection des Personnes. (Clinical Trial) RC15_0304.
Provenance and peer review Not commissioned; externally peer reviewed.
Data availability statement Data are available upon reasonable request. we made both the analysis code and simulated data publicly available in order to favor transparency, promote reproducibility and facilitate mega-analysis.
Supplemental material This content has been supplied by the author(s). It has not been vetted by BMJ Publishing Group Limited (BMJ) and may not have been peer-reviewed. Any opinions or recommendations discussed are solely those of the author(s) and are not endorsed by BMJ. BMJ disclaims all liability and responsibility arising from any reliance placed on the content. Where the content includes any translated material, BMJ does not warrant the accuracy and reliability of the translations (including but not limited to local regulations, clinical guidelines, terminology, drug names and drug dosages), and is not responsible for any error and/or omissions arising from translation and adaptation or otherwise.