Portal de Periódicos da CAPES

Development and testing of an artificial intelligence tool for predicting end-stage kidney disease in patients with immunoglobulin A nephropathy

2020; Elsevier BV; Volume: 99; Issue: 5 Linguagem: Inglês

10.1016/j.kint.2020.07.046

1523-1755

Francesco Paolo Schena, Vito Walter Anelli, Joseph Trotta, Tommaso Di Noia, Carlo Manno, Giovanni Tripepi, Graziella D’Arrigo, Nicholas C. Chesnaye, María Luisa Russo, Μaria Stangou, Αikaterini Papagianni, Carmine Zoccali, Vladimı́r Tesař, Rosanna Coppo, Vladimı́r Tesař, Dita Maixnerová, Sigrid Lundberg, Loreto Gesualdo, Francesco Emma, Laura Fuiano, G. Beltrame, Cristiana Rollino, Rosanna Coppo, Alessandro Amore, Roberta Camilla, Licia Peruzzi, Manuel Praga, Sandro Feriozzi, Rosaria Polci, Giuseppe Segoloni, Loredana Colla, Antonello Pani, Andrea Angioi, Lisa Adele Piras, John Feehally, Giovanni Cancarini, S. Ravera, Magdalena Durlik, Elisabetta Moggia, José Ballarín, S. Di Giulio, Francesco Pugliese, I. Serriello, Yaşar Çalışkan, Mehmet Şükrü Sever, İşın Kiliçaslan, Francesco Locatelli, Lucia Del Vecchio, J F M Wetzels, Harm Peters, U. Berg, Fernanda Carvalho, A.C. da Costa Ferreira, M. Maggio, Andrzej Więcek, Mai Ots-Rosenberg, Riccardo Magistroni, Rezan Topaloğlu, Yelda Bilginer, Marco DʼAmico, Μaria Stangou, F Giacchino, Dimitrios Goumenos, Marios Papasotiriou, Kres̆imir Gales̃ić, Luka Torić, Colin Geddes, Kostas C. Siamopoulos, Olga Balafa, Marco Galliani, Piero Stratta, Marco Quaglia, R Bergia, Raffaella Cravero, Maurizio Salvadori, Lino Cirami, Bengt Fellström, Hilde Kloster Smerud, Franco Ferrario, T. Stellato, Jesús Egido, Carina Aguilar Martín, Jürgen Floege, Frank Eitner, Thomas Rauen, Antonio Lupo, Patrizia Bernich, Paolo Menè, Massimo Morosetti, Cees van Kooten, Ton J. Rabelink, Marlies E. J. Reinders, J.M. Boria Grinyo, Stefano Cusinato, Luisa Benozzi, Silvana Savoldi, C. Licata, Małgorzata Mizerska-Wasiak, Maria Roszkowska–Blaim, G Martina, A Messuerotti, Antonio Dal Canton, Ciro Esposito, C. Migotto, G Triolo, Filippo Mariano, Claudio Pozzi, R Boero, Mazzucco, C. Giannakakis, Eva Honsová, B. Sundelin, Anna Maria Di Palma, Franco Ferrario, Ester Gutiérrez, A.M. Asunis, Jonathan Barratt, Regina Tardanico, Agnieszka Perkowska‐Ptasińska, J. Arce Terroba, M. Fortunato, Afroditi Pantzaki, Yasemin Özlük, E. J. Steenbergen, Magnus Söderberg, Živile Riispere, Luciana Furci, Dıclehan Orhan, David Kipgen, Donatella Casartelli, Danica Galešić Ljubanović, Hariklia Gakiopoulou, E. Bertoni, Pablo Cannata Ortiz, Henryk Karkoszka, Hermann-Josef Groene, Antonella Stoppacciaro, Ingeborg M. Bajema, Jan A. Bruijn, X. FulladosaOliveras, Jadwiga Małdyk, E. Ioachim, Daniela Isabel Abbrescia, Nikoleta M. Kouri, Μaria Stangou, Αikaterini Papagianni, Francesco Scolari, Elisa Delbarba, Mario Bonomini, Luca Piscitani, Giovanni Stallone, Barbara Infante, Giulia Godeas, Desirèe Madio, Luigi Biancone, Marco Campagna, Gianluigi Zaza, Isabella Squarzoni, Concetta Cangemi,

Platelet Disorders and Treatments

We have developed an artificial neural network prediction model for end-stage kidney disease (ESKD) in patients with primary immunoglobulin A nephropathy (IgAN) using a retrospective cohort of 948 patients with IgAN. Our tool is based on a two-step procedure of a classifier model that predicts ESKD, and a regression model that predicts development of ESKD over time. The classifier model showed a performance value of 0.82 (area under the receiver operating characteristic curve) in patients with a follow-up of five years, which improved to 0.89 at the ten-year follow-up. Both models had a higher recall rate, which indicated the practicality of the tool. The regression model showed a mean absolute error of 1.78 years and a root mean square error of 2.15 years. Testing in an independent cohort of 167patients with IgAN found successful results for 91% of the patients. Comparison of our system with other mathematical models showed the highest discriminant Harrell C index at five- and ten-years follow-up (81% and 86%, respectively), paralleling the lowest Akaike information criterion values (355.01 and 269.56, respectively). Moreover, our system was the best calibrated model indicating that the predicted and observed outcome probabilities did not significantly differ. Finally, the dynamic discrimination indexes of our artificial neural network, expressed as the weighted average of time-dependent areas under the curve calculated at one and two years, were 0.80 and 0.79, respectively. Similar results were observed over a 25-year follow-up period. Thus, our tool identified individuals who were at a high risk of developing ESKD due to IgAN and predicted the time-to-event endpoint. Accurate prediction is an important step toward introduction of a therapeutic strategy for improving clinical outcomes.