PURPOSE: Late major bleeding is one of the main complications after transcatheter aortic valve replacement (TAVR). We aimed to develop a risk prediction model based on deep learning to predict major or life-threatening bleeding complications (MLBCs) after TAVR. PATIENTS AND METHODS: This was a retrospective study including TAVR patients from West China Hospital of Sichuan University Transcatheter Aortic Valve Replacement Registry (ChiCTR2000033419) between April 17, 2012 and May 27, 2020. A deep learning-based model named BLeNet was developed with 56 features covering baseline, procedural, and post-procedural characteristics. The model was validated with the bootstrap method and evaluated using Harrell's concordance index (c-index), receiver operating characteristics (ROC) curve, calibration curve, and Kaplan-Meier estimate. Captum interpretation library was applied to identify feature importance. The BLeNet model was compared with the traditional Cox proportional hazard (Cox-PH) model and the random survival forest model in the metrics mentioned above. RESULTS: The BLeNet model outperformed the Cox-PH and random survival forest models significantly in discrimination [optimism-corrected c-index of BLeNet vs Cox-PH vs random survival forest: 0.81 (95% CI: 0.79-0.92) vs 0.72 (95% CI: 0.63-0.77) vs 0.70 (95% CI: 0.61-0.74)] and calibration (integrated calibration index of BLeNet vs Cox-PH vs random survival forest: 0.007 vs 0.015 vs 0.019). In Kaplan-Meier analysis, BLeNet model had great performance in stratifying high- and low-bleeding risk patients (p < 0.0001). CONCLUSION: Deep learning is a feasible way to build prediction models concerning TAVR prognosis. A dedicated bleeding risk prediction model was developed for TAVR patients to facilitate well-informed clinical decisions.
PURPOSE: Late major bleeding is one of the main complications after transcatheter aortic valve replacement (TAVR). We aimed to develop a risk prediction model based on deep learning to predict major or life-threatening bleeding complications (MLBCs) after TAVR. PATIENTS AND METHODS: This was a retrospective study including TAVR patients from West China Hospital of Sichuan University Transcatheter Aortic Valve Replacement Registry (ChiCTR2000033419) between April 17, 2012 and May 27, 2020. A deep learning-based model named BLeNet was developed with 56 features covering baseline, procedural, and post-procedural characteristics. The model was validated with the bootstrap method and evaluated using Harrell's concordance index (c-index), receiver operating characteristics (ROC) curve, calibration curve, and Kaplan-Meier estimate. Captum interpretation library was applied to identify feature importance. The BLeNet model was compared with the traditional Cox proportional hazard (Cox-PH) model and the random survival forest model in the metrics mentioned above. RESULTS: The BLeNet model outperformed the Cox-PH and random survival forest models significantly in discrimination [optimism-corrected c-index of BLeNet vs Cox-PH vs random survival forest: 0.81 (95% CI: 0.79-0.92) vs 0.72 (95% CI: 0.63-0.77) vs 0.70 (95% CI: 0.61-0.74)] and calibration (integrated calibration index of BLeNet vs Cox-PH vs random survival forest: 0.007 vs 0.015 vs 0.019). In Kaplan-Meier analysis, BLeNet model had great performance in stratifying high- and low-bleeding risk patients (p < 0.0001). CONCLUSION: Deep learning is a feasible way to build prediction models concerning TAVR prognosis. A dedicated bleeding risk prediction model was developed for TAVR patients to facilitate well-informed clinical decisions.
Authors: Philippe Généreux; David J Cohen; Michael Mack; Josep Rodes-Cabau; Mayank Yadav; Ke Xu; Rupa Parvataneni; Rebecca Hahn; Susheel K Kodali; John G Webb; Martin B Leon Journal: J Am Coll Cardiol Date: 2014-12-23 Impact factor: 24.094
Authors: Jeffrey J Popma; G Michael Deeb; Steven J Yakubov; Mubashir Mumtaz; Hemal Gada; Daniel O'Hair; Tanvir Bajwa; John C Heiser; William Merhi; Neal S Kleiman; Judah Askew; Paul Sorajja; Joshua Rovin; Stanley J Chetcuti; David H Adams; Paul S Teirstein; George L Zorn; John K Forrest; Didier Tchétché; Jon Resar; Antony Walton; Nicolo Piazza; Basel Ramlawi; Newell Robinson; George Petrossian; Thomas G Gleason; Jae K Oh; Michael J Boulware; Hongyan Qiao; Andrew S Mugglin; Michael J Reardon Journal: N Engl J Med Date: 2019-03-16 Impact factor: 91.245
Authors: Pradyumna Agasthi; Hasan Ashraf; Sai Harika Pujari; Marlene E Girardo; Andrew Tseng; Farouk Mookadam; Nithin R Venepally; Matthew Buras; Banveet K Khetarpal; Mohamed Allam; Mackram F Eleid; Kevin L Greason; Nirat Beohar; Robert J Siegel; John Sweeney; Floyd D Fortuin; David R Holmes; Reza Arsanjani Journal: Cardiovasc Revasc Med Date: 2020-08-15
Authors: A Pieter Kappetein; Stuart J Head; Philippe Généreux; Nicolo Piazza; Nicolas M van Mieghem; Eugene H Blackstone; Thomas G Brott; David J Cohen; Donald E Cutlip; Gerrit-Anne van Es; Rebecca T Hahn; Ajay J Kirtane; Mitchell W Krucoff; Susheel Kodali; Michael J Mack; Roxana Mehran; Josep Rodés-Cabau; Pascal Vranckx; John G Webb; Stephan Windecker; Patrick W Serruys; Martin B Leon Journal: Eur Heart J Date: 2012-10 Impact factor: 29.983
Authors: Bruna Gomes; Maximilian Pilz; Christoph Reich; Florian Leuschner; Mathias Konstandin; Hugo A Katus; Benjamin Meder Journal: Clin Res Cardiol Date: 2020-06-24 Impact factor: 5.460
Authors: Raffaele Piccolo; Thomas Pilgrim; Anna Franzone; Marco Valgimigli; Alan Haynes; Masahiko Asami; Jonas Lanz; Lorenz Räber; Fabien Praz; Bettina Langhammer; Eva Roost; Stephan Windecker; Stefan Stortecky Journal: JACC Cardiovasc Interv Date: 2017-07-24 Impact factor: 11.195
Authors: Karel G M Moons; Douglas G Altman; Johannes B Reitsma; John P A Ioannidis; Petra Macaskill; Ewout W Steyerberg; Andrew J Vickers; David F Ransohoff; Gary S Collins Journal: Ann Intern Med Date: 2015-01-06 Impact factor: 25.391