Portal de Periódicos da CAPES

Machine learning algorithms performed no better than regression models for prognostication in traumatic brain injury

2020; Elsevier BV; Volume: 122; Linguagem: Inglês

10.1016/j.jclinepi.2020.03.005

1878-5921

Benjamin Gravesteijn, Daan Nieboer, Ari Ercole, Hester F. Lingsma, David Nelson, Ben Van Calster, Ewout W. Steyerberg, Cecilia Åkerlund, Krisztina Amrein, Nada Anđelić, Lasse Andreassen, Audny Anke, Anna Antoni, Gérard Audibert, Philippe Azouvi, Maria Luisa Azzolini, Ronald Bartels, Pál Barzó, Romuald Beauvais, Ronny Beer, Bo‐Michael Bellander, Antonio Belli, Habib Benali, Maurizio Berardino, Luigi Beretta, Morten Blaabjerg, Peter Bragge, Alexandra Bražinová, Vibeke Brinck, Joanne Brooker, Caroline Brorsson, András Büki, Monika Bullinger, Manuel Cabeleira, Alessio Caccioppola, Emiliana Calappi, Maria Rosa Calvi, Peter Cameron, Guillermo Carbayo Lozano, Marco Carbonara, Giorgio Chevallard, Arturo Chieregato, Giuseppe Citerio, Maryse C. Cnossen, Mark Coburn, Jonathan Coles, D. James Cooper, Marta Correia, Amra Čović, Nicola Curry, Endre Czeiter, Marek Czosnyka, Claire Dahyot‐Fizelier, Helen Dawes, Véronique De Keyser, Vincent Degos, Françesco Della Corte, Hugo den Boogert, Bart Depreitere, Đula Đilvesi, Abhishek Dixit, Emma Donoghue, Jens Dreier Guy-Loup Dulière, Ari Ercole, Patrick Esser, Martin Fabricius, Kelly Foks Valery L. Feigin, Shirin Frisvold, Alex Furmanov, Pablo Gagliardo, Damien Galanaud, Dashiell Gantner, Guoyi Gao, Pradeep George, Alexandre Ghuysen, Lelde Giga, Ben Glocker, Jagoš Golubović, Pedro A. Gómez, Johannes Gratz, Benjamin Gravesteijn, Francesca Grossi, Russell L. Gruen, Deepak Gupta, Juanita A. Haagsma, Iain Haitsma, Raimund Helbok, Eirik Helseth, Lindsay Horton, Jilske Huijben, Peter J. Hutchinson, Bram Jacobs, Stefan Jankowski, Mike Jarrett Ji-yao Jiang, Kelly Jones, Mladen Karan, Angelos G. Kolias, Erwin J. O. Kompanje, Daniel Kondziella, Evgenios Koraropoulos, Lars‐Owe Koskinen, Noémi Kovács, Alfonso Lagares, Linda Lanyon, Steven Laureys, Fiona Lecky, Rolf Lefering, Valérie Legrand, Aurélie Lejeune, Leon Levi, Roger Lightfoot, Hester F. Lingsma, Andrew I.R. Maas, Ana M. Castaño‐León, Marc Maegele, Marek Majdán, Alex Manara, Geoffrey A. Manley, Costanza Martino, Hugues Maréchal, Julia Mattern, Catherine McMahon, Béla Melegh, David Menon, Tomas Menovsky, Davide Mulazzi, Visakh Muraleedharan, Lynnette Murray, Nandesh Nair, Ancuța Negru, David Nelson, Virginia Newcombe, Daan Nieboer, Quentin Noirhomme, József Nyirádi, Otesile Olubukola, Matej Orešič, Fabrizio Ortolano, Aarno Palotie, Paul M. Parizel, Jean‐François Payen, Natascha Perera, Vincent Perlbarg, Paolo Persona, Wilco C. Peul, Anna Piippo-Karjalainen, Matti Pirinen, Horia Pleș, Suzanne Polinder, Iñigo Pomposo, Jussi P. Posti, Louis Puybasset, Andreea Rădoi, Arminas Ragauskas, Rahul Raj, Malinka Rambadagalla, Ruben Real, Jonathan R. Rhodes, Sylvia Richardson, Sophie Richter, Samuli Ripatti, Saulius Ročka, Cecilie Røe, Olav Røise, Jonathan Rosand, Jeffrey V. Rosenfeld, Christina Rosenlund, Guy Rosenthal, Rolf Rossaint, Sandra Rossi, Daniel Rueckert, Martin Rusňák, Juan Sahuquillo, Oliver Sakowitz, Renán Sánchez-Porras, János Sándor, Nadine Schäfer, Silke Schmidt, Herbert Schöechl, Guus Schoonman, Rico Frederik Schou, Elisabeth Schwendenwein, Charlie Sewalt, Toril Skandsen, Peter Smielewski, Abayomi Sorinola, Emmanuel A. Stamatakis, Simon Stanworth, Ana Kowark, Robert D. Stevens, William Stewart, Ewout W. Steyerberg, Nino Stocchetti, Nina Sundström, Anneliese Synnot, Riikka Takala, Viktória Tamás, Tomas Tamošuitis, Mark Taylor, Braden Te Ao, Olli Tenovuo, Alice Theadom, Matt Thomas, Dick Tibboel, Marjolein Timmers, Christos Tolias, Tony Trapani, Cristina Maria Tudora, Peter Vajkoczy, Shirley Vallance, Egils Valeinis, Zoltán Vámos, Gregory Van der Steen, Joukje van der Naalt, Jeroen T.J.M. van Dijck, Thomas A. van Essen, Wim Van Hecke, Caroline van Heugten, Dominique Van Praag, Thijs Vande Vyvere, Audrey Vanhaudenhuyse, Roel P. J. van Wijk, Alessia Vargiolu, Emmanuel Vega, Kimberley Velt, Jan Verheyden, Paul Vespa, Anne Vik, Rimantas Vilcinis, Victor Volovici, Nicole von Steinbüchel, Daphne Voormolen, Petar Vuleković, Kevin Wang, Eveline Wiegers, Guy Williams, Lindsay Wilson, Stefan Winzeck, Stefan Wolf, Zhihui Yang, Peter Ylén, Alexander Younsi, Frederick A. Zeiler, Veronika Zelinkova, Agate Ziverte, Tommaso Zoerle,

Autopsy Techniques and Outcomes

ObjectiveWe aimed to explore the added value of common machine learning (ML) algorithms for prediction of outcome for moderate and severe traumatic brain injury.Study Design and SettingWe performed logistic regression (LR), lasso regression, and ridge regression with key baseline predictors in the IMPACT-II database (15 studies, n = 11,022). ML algorithms included support vector machines, random forests, gradient boosting machines, and artificial neural networks and were trained using the same predictors. To assess generalizability of predictions, we performed internal, internal-external, and external validation on the recent CENTER-TBI study (patients with Glasgow Coma Scale <13, n = 1,554). Both calibration (calibration slope/intercept) and discrimination (area under the curve) was quantified.ResultsIn the IMPACT-II database, 3,332/11,022 (30%) died and 5,233(48%) had unfavorable outcome (Glasgow Outcome Scale less than 4). In the CENTER-TBI study, 348/1,554(29%) died and 651(54%) had unfavorable outcome. Discrimination and calibration varied widely between the studies and less so between the studied algorithms. The mean area under the curve was 0.82 for mortality and 0.77 for unfavorable outcomes in the CENTER-TBI study.ConclusionML algorithms may not outperform traditional regression approaches in a low-dimensional setting for outcome prediction after moderate or severe traumatic brain injury. Similar to regression-based prediction models, ML algorithms should be rigorously validated to ensure applicability to new populations.