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.
Development and testing of an artificial intelligence tool for predicting end-stage kidney disease in patients with immunoglobulin A nephropathy / Schena, F. P.; Anelli, V. W.; Trotta, J.; Di Noia, T.; Manno, C.; Tripepi, G.; D'Arrigo, G.; Chesnaye, N. C.; Russo, M. L.; Stangou, M.; Papagianni, A.; Zoccali, C.; Tesar, V.; Coppo, R.; Tesar, V.; Maixnerova, D.; Lundberg, S.; Gesualdo, L.; Emma, F.; Fuiano, L.; Beltrame, G.; Rollino, C.; Coppo, R.; Amore, A.; Camilla, R.; Peruzzi, L.; Praga, M.; Feriozzi, S.; Polci, R.; Segoloni, G.; Colla, L.; Pani, A.; Angioi, A.; Piras, L.; Feehally, J.; Cancarini, G.; Ravera, S.; Durlik, M.; Moggia, E.; Ballarin, J.; Di Giulio, S.; Pugliese, F.; Serriello, I.; Caliskan, Y.; Sever, M.; Kilicaslan, I.; Locatelli, F.; Del Vecchio, L.; Wetzels, J. F. M.; Peters, H.; Berg, U.; Carvalho, F.; da Costa Ferreira, A. C.; Maggio, M.; Wiecek, A.; Ots-Rosenberg, M.; Magistroni, R.; Topaloglu, R.; Bilginer, Y.; D'Amico, M.; Stangou, M.; Giacchino, F.; Goumenos, D.; Papasotiriou, M.; Galesic, K.; Toric, L.; Geddes, C.; Siamopoulos, K.; Balafa, O.; Galliani, M.; Stratta, P.; Quaglia, M.; Bergia, R.; Cravero, R.; Salvadori, M.; Cirami, L.; Fellstrom, B.; Smerud, H. K.; Ferrario, F.; Stellato, T.; Egido, J.; Martin, C.; Floege, J.; Eitner, F.; Rauen, T.; Lupo, A.; Bernich, P.; Mene, P.; Morosetti, M.; van Kooten, C.; Rabelink, T.; Reinders, M. E. J.; Grinyo, J. M. B.; Cusinato, S.; Benozzi, L.; Savoldi, S.; Licata, C.; Mizerska-Wasiak, M.; Roszkowska-Blaim, M.; Martina, G.; Messuerotti, A.; Canton, A. D.; Esposito, C.; Migotto, C.; Triolo, G.; Mariano, F.; Pozzi, C.; Boero, R.; Mazzucco, Michele; Giannakakis, C.; Honsova, E.; Sundelin, B.; Di Palma, A. M.; Gutierrez, E.; Asunis, A. M.; Barratt, J.; Tardanico, R.; Perkowska-Ptasinska, A.; Terroba, J. A.; Fortunato, M.; Pantzaki, A.; Ozluk, Y.; Steenbergen, E.; Soderberg, M.; Riispere, Z.; Furci, L.; Orhan, D.; Kipgen, D.; Casartelli, D.; Galesicljubanovic, D.; Gakiopoulou, H.; Bertoni, E.; Ortiz, P. C.; Karkoszka, H.; Groene, H. J.; Stoppacciaro, A.; Bajema, I.; Bruijn, J.; Fulladosaoliveras, X.; Maldyk, J.; Ioachim, E.; Abbrescia, D.; Kouri, N.; Scolari, F.; Delbarba, E.; Bonomini, M.; Piscitani, L.; Stallone, G.; Infante, B.; Godeas, G.; Madio, D.; Biancone, L.; Campagna, M.; Zaza, G.; Squarzoni, I.; Cangemi, C.. - In: KIDNEY INTERNATIONAL. - ISSN 0085-2538. - 99:5(2021), pp. 1179-1188. [10.1016/j.kint.2020.07.046]
Development and testing of an artificial intelligence tool for predicting end-stage kidney disease in patients with immunoglobulin A nephropathy
Zoccali C.;Beltrame G.;Peruzzi L.;Maggio M.;Magistroni R.;D'Amico M.;Quaglia M.;Salvadori M.;Pozzi C.;Mazzucco;
2021
Abstract
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.
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris
