Prediction of All-Cause Mortality Following Percutaneous Coronary Intervention in Bifurcation Lesions Using Machine Learning Algorithms
Stratifying prognosis following coronary bifurcation percutaneous coronary intervention (PCI) is an unmet clinical need that may be fulfilled through the adoption of machine learning (ML) algorithms to refine outcome predictions. We sought to develop an ML-based risk stratification model built on cl...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Journal of Personalized Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4426/12/6/990 |
| _version_ | 1797485511147782144 |
|---|---|
| author | Jacopo Burrello Guglielmo Gallone Alessio Burrello Daniele Jahier Pagliari Eline H. Ploumen Mario Iannaccone Leonardo De Luca Paolo Zocca Giuseppe Patti Enrico Cerrato Wojciech Wojakowski Giuseppe Venuti Ovidio De Filippo Alessio Mattesini Nicola Ryan Gérard Helft Saverio Muscoli Jing Kan Imad Sheiban Radoslaw Parma Daniela Trabattoni Massimo Giammaria Alessandra Truffa Francesco Piroli Yoichi Imori Bernardo Cortese Pierluigi Omedè Federico Conrotto Shao-Liang Chen Javier Escaned Rosaly A. Buiten Clemens Von Birgelen Paolo Mulatero Gaetano Maria De Ferrari Silvia Monticone Fabrizio D’Ascenzo |
| author_facet | Jacopo Burrello Guglielmo Gallone Alessio Burrello Daniele Jahier Pagliari Eline H. Ploumen Mario Iannaccone Leonardo De Luca Paolo Zocca Giuseppe Patti Enrico Cerrato Wojciech Wojakowski Giuseppe Venuti Ovidio De Filippo Alessio Mattesini Nicola Ryan Gérard Helft Saverio Muscoli Jing Kan Imad Sheiban Radoslaw Parma Daniela Trabattoni Massimo Giammaria Alessandra Truffa Francesco Piroli Yoichi Imori Bernardo Cortese Pierluigi Omedè Federico Conrotto Shao-Liang Chen Javier Escaned Rosaly A. Buiten Clemens Von Birgelen Paolo Mulatero Gaetano Maria De Ferrari Silvia Monticone Fabrizio D’Ascenzo |
| author_sort | Jacopo Burrello |
| collection | DOAJ |
| description | Stratifying prognosis following coronary bifurcation percutaneous coronary intervention (PCI) is an unmet clinical need that may be fulfilled through the adoption of machine learning (ML) algorithms to refine outcome predictions. We sought to develop an ML-based risk stratification model built on clinical, anatomical, and procedural features to predict all-cause mortality following contemporary bifurcation PCI. Multiple ML models to predict all-cause mortality were tested on a cohort of 2393 patients (training, n = 1795; internal validation, n = 598) undergoing bifurcation PCI with contemporary stents from the real-world RAIN registry. Twenty-five commonly available patient-/lesion-related features were selected to train ML models. The best model was validated in an external cohort of 1701 patients undergoing bifurcation PCI from the DUTCH PEERS and BIO-RESORT trial cohorts. At ROC curves, the AUC for the prediction of 2-year mortality was 0.79 (0.74–0.83) in the overall population, 0.74 (0.62–0.85) at internal validation and 0.71 (0.62–0.79) at external validation. Performance at risk ranking analysis, k-center cross-validation, and continual learning confirmed the generalizability of the models, also available as an online interface. The RAIN-ML prediction model represents the first tool combining clinical, anatomical, and procedural features to predict all-cause mortality among patients undergoing contemporary bifurcation PCI with reliable performance. |
| first_indexed | 2024-03-09T23:19:51Z |
| format | Article |
| id | doaj.art-c75d97b8c6b644adbd339f65a0ca436f |
| institution | Directory Open Access Journal |
| issn | 2075-4426 |
| language | English |
| last_indexed | 2024-03-09T23:19:51Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Personalized Medicine |
| spelling | doaj.art-c75d97b8c6b644adbd339f65a0ca436f2023-11-23T17:28:56ZengMDPI AGJournal of Personalized Medicine2075-44262022-06-0112699010.3390/jpm12060990Prediction of All-Cause Mortality Following Percutaneous Coronary Intervention in Bifurcation Lesions Using Machine Learning AlgorithmsJacopo Burrello0Guglielmo Gallone1Alessio Burrello2Daniele Jahier Pagliari3Eline H. Ploumen4Mario Iannaccone5Leonardo De Luca6Paolo Zocca7Giuseppe Patti8Enrico Cerrato9Wojciech Wojakowski10Giuseppe Venuti11Ovidio De Filippo12Alessio Mattesini13Nicola Ryan14Gérard Helft15Saverio Muscoli16Jing Kan17Imad Sheiban18Radoslaw Parma19Daniela Trabattoni20Massimo Giammaria21Alessandra Truffa22Francesco Piroli23Yoichi Imori24Bernardo Cortese25Pierluigi Omedè26Federico Conrotto27Shao-Liang Chen28Javier Escaned29Rosaly A. Buiten30Clemens Von Birgelen31Paolo Mulatero32Gaetano Maria De Ferrari33Silvia Monticone34Fabrizio D’Ascenzo35Division of Internal Medicine and Hypertension, Department of Medical Sciences, University of Turin, 10126 Turin, ItalyDivision of Cardiology, Department of Medical Sciences, University of Turin, 10126 Turin, ItalyDepartment of Electrical, Electronic and Information Engineering, University of Bologna, 40126 Bologna, ItalyDepartment of Control and Computer Engineering, Polytechnic University of Turin, 10129 Turin, ItalyCardiology Department, Medisch Spectrum Twente, Thoraxcentrum Twente, 7412 Enschede, The NetherlandsCardiology Department, San Giovanni Bosco Hospital, 10154 Turin, ItalyDivision of Cardiology, S. Giovanni Evangelista Hospital, Tivoli, 00019 Rome, ItalyCardiology Department, Medisch Spectrum Twente, Thoraxcentrum Twente, 7412 Enschede, The NetherlandsCoronary Care Unit and Catheterization Laboratory, A.O.U. Maggiore della Carità, 28100 Novara, ItalyDepartment of Cardiology, San Luigi Gonzaga Hospital, 10043 Orbassano, ItalyDepartment of Cardiology, Medical University of Silesia, 40-752 Katowice, PolandDivision of Cardiology, A.O.U. “Policlinico-Vittorio Emanuele”, 95123 Catania, ItalyDivision of Cardiology, Department of Medical Sciences, University of Turin, 10126 Turin, ItalyStructural Interventional Cardiology, Careggi University Hospital, 50134 Florence, ItalyDepartment of Cardiology, Aberdeen Royal Infirmary, Aberdeen AB25 2ZN, UKDepartment of Cardiology, Pierre and Marie Curie University, 75005 Paris, FranceDepartment of Medicine, Università degli Studi di Roma Tor Vergata, 00133 Rome, ItalyDivision of Cardiology, Nanjing First Hospital, Nanjing Medical University, Nanjing 210029, ChinaDivision of Cardiology, Pederzoli Hospital, 37019 Peschiera del Garda, ItalyDepartment of Cardiology, University Clinical Hospital, 02-091 Warsaw, PolandDepartment of Cardiovascular Sciences, IRCCS Centro Cardiologico Monzino, 20138 Milan, ItalyDivision of Cardiology, Ospedale Maria Vittoria, 10144 Turin, ItalyDivision of Cardiology, ASL Cardinal Massaia Hospital, 14100 Asti, ItalyDivision of Cardiology, Department of Medical Sciences, University of Turin, 10126 Turin, ItalyDepartment of Cardiovascular Medicine, Nippon Medical School, Sendagi, Bunkyo-ku, Tokyo 113-8602, JapanDivision of Cardiology, San Carlo Clinic, 20037 Milan, ItalyDivision of Cardiology, Department of Medical Sciences, University of Turin, 10126 Turin, ItalyDivision of Cardiology, Department of Medical Sciences, University of Turin, 10126 Turin, ItalyDivision of Cardiology, Nanjing First Hospital, Nanjing Medical University, Nanjing 210029, ChinaDivision of Cardiology, Hospital San Carlos, Complutense University, 28040 Madrid, SpainCardiology Department, Medisch Spectrum Twente, Thoraxcentrum Twente, 7412 Enschede, The NetherlandsCardiology Department, Medisch Spectrum Twente, Thoraxcentrum Twente, 7412 Enschede, The NetherlandsDivision of Internal Medicine and Hypertension, Department of Medical Sciences, University of Turin, 10126 Turin, ItalyDivision of Cardiology, Department of Medical Sciences, University of Turin, 10126 Turin, ItalyDivision of Internal Medicine and Hypertension, Department of Medical Sciences, University of Turin, 10126 Turin, ItalyDivision of Cardiology, Department of Medical Sciences, University of Turin, 10126 Turin, ItalyStratifying prognosis following coronary bifurcation percutaneous coronary intervention (PCI) is an unmet clinical need that may be fulfilled through the adoption of machine learning (ML) algorithms to refine outcome predictions. We sought to develop an ML-based risk stratification model built on clinical, anatomical, and procedural features to predict all-cause mortality following contemporary bifurcation PCI. Multiple ML models to predict all-cause mortality were tested on a cohort of 2393 patients (training, n = 1795; internal validation, n = 598) undergoing bifurcation PCI with contemporary stents from the real-world RAIN registry. Twenty-five commonly available patient-/lesion-related features were selected to train ML models. The best model was validated in an external cohort of 1701 patients undergoing bifurcation PCI from the DUTCH PEERS and BIO-RESORT trial cohorts. At ROC curves, the AUC for the prediction of 2-year mortality was 0.79 (0.74–0.83) in the overall population, 0.74 (0.62–0.85) at internal validation and 0.71 (0.62–0.79) at external validation. Performance at risk ranking analysis, k-center cross-validation, and continual learning confirmed the generalizability of the models, also available as an online interface. The RAIN-ML prediction model represents the first tool combining clinical, anatomical, and procedural features to predict all-cause mortality among patients undergoing contemporary bifurcation PCI with reliable performance.https://www.mdpi.com/2075-4426/12/6/990percutaneous coronary interventioncoronary bifurcationmachine learningprognosis |
| spellingShingle | Jacopo Burrello Guglielmo Gallone Alessio Burrello Daniele Jahier Pagliari Eline H. Ploumen Mario Iannaccone Leonardo De Luca Paolo Zocca Giuseppe Patti Enrico Cerrato Wojciech Wojakowski Giuseppe Venuti Ovidio De Filippo Alessio Mattesini Nicola Ryan Gérard Helft Saverio Muscoli Jing Kan Imad Sheiban Radoslaw Parma Daniela Trabattoni Massimo Giammaria Alessandra Truffa Francesco Piroli Yoichi Imori Bernardo Cortese Pierluigi Omedè Federico Conrotto Shao-Liang Chen Javier Escaned Rosaly A. Buiten Clemens Von Birgelen Paolo Mulatero Gaetano Maria De Ferrari Silvia Monticone Fabrizio D’Ascenzo Prediction of All-Cause Mortality Following Percutaneous Coronary Intervention in Bifurcation Lesions Using Machine Learning Algorithms Journal of Personalized Medicine percutaneous coronary intervention coronary bifurcation machine learning prognosis |
| title | Prediction of All-Cause Mortality Following Percutaneous Coronary Intervention in Bifurcation Lesions Using Machine Learning Algorithms |
| title_full | Prediction of All-Cause Mortality Following Percutaneous Coronary Intervention in Bifurcation Lesions Using Machine Learning Algorithms |
| title_fullStr | Prediction of All-Cause Mortality Following Percutaneous Coronary Intervention in Bifurcation Lesions Using Machine Learning Algorithms |
| title_full_unstemmed | Prediction of All-Cause Mortality Following Percutaneous Coronary Intervention in Bifurcation Lesions Using Machine Learning Algorithms |
| title_short | Prediction of All-Cause Mortality Following Percutaneous Coronary Intervention in Bifurcation Lesions Using Machine Learning Algorithms |
| title_sort | prediction of all cause mortality following percutaneous coronary intervention in bifurcation lesions using machine learning algorithms |
| topic | percutaneous coronary intervention coronary bifurcation machine learning prognosis |
| url | https://www.mdpi.com/2075-4426/12/6/990 |
| work_keys_str_mv | AT jacopoburrello predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT guglielmogallone predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT alessioburrello predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT danielejahierpagliari predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT elinehploumen predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT marioiannaccone predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT leonardodeluca predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT paolozocca predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT giuseppepatti predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT enricocerrato predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT wojciechwojakowski predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT giuseppevenuti predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT ovidiodefilippo predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT alessiomattesini predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT nicolaryan predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT gerardhelft predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT saveriomuscoli predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT jingkan predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT imadsheiban predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT radoslawparma predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT danielatrabattoni predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT massimogiammaria predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT alessandratruffa predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT francescopiroli predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT yoichiimori predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT bernardocortese predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT pierluigiomede predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT federicoconrotto predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT shaoliangchen predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT javierescaned predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT rosalyabuiten predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT clemensvonbirgelen predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT paolomulatero predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT gaetanomariadeferrari predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT silviamonticone predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms AT fabriziodascenzo predictionofallcausemortalityfollowingpercutaneouscoronaryinterventioninbifurcationlesionsusingmachinelearningalgorithms |