Conventional machine learning-based prediction models did not outperform the International IgA Nephropathy Prediction Tool
Kidney Research and Clinical Practice · 01.09.2025 · 44 (5) · 802-813
DOI: 10.23876/j.krcp.23.212 ↗Kurz gefasst
Fachartikel in der Zeitschrift Kidney Research and Clinical Practice, erschienen am 01.09.2025. Verfasst von Sehoon Park und 14 weiteren Autor:innen. Beteiligte Einrichtung: Department of Internal Medicine, Seoul National University Hospital, Seoul, Republic of Korea. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Research Foundation of Korea, Korean Nephrology Research Foundation.
Abstract (Originalsprache)
Background
Immunoglobulin A nephropathy (IgAN) is a major cause of end-stage kidney disease (ESKD). The International IgA Nephropathy Prediction Tool (IIgAN-PT) predicts IgAN prognosis, but improvement in the prediction performance using machine learning (ML)-based methods is needed.
Methods
We analyzed 4,425 biopsy-confirmed patients with IgAN and ≥6 months of follow-up from nine tertiary university hospitals in Korea. The study population was divided into development and validation cohorts. Using the collected 87 clinicodemographic and pathological variables, ML-based prediction models for ESKD or estimated glomerular filtration rate were constructed: 1) the conventional CatBoost model, 2) the optimized CatBoost model with Cox proportional hazards, 3) the deep Cox proportional hazards model, and 4) the deep Cox mixture model. The area under the curve (AUC) and calibration plots were used to investigate the discriminative and calibration performance of the models, which were then compared with those of the IIgAN-PT full model.
Results
The full model showed excellent performance (AUC [95% confidence interval] for 5-year outcome, 0.896 [0.8530.940]), with acceptable calibration results. The ML-based models showed good performance in predicting adverse kidney outcomes and revealed acceptable discrimination performance in the external validation (AUC [95% confidence interval] for the 5-year outcome: 1) 0.829 [0.791–0.866]; 2) 0.847 [0.804–0.890]; 3) 0.823 [0.784–0.862]; and 4) 0.832 [0.794–0.870]), although they underestimated the external validation cohort risks. With the validation data, the overall performance of the IIgAN-PT was non-inferior to that of the ML-based model.
Conclusions
Our ML-based models showed good performance in predicting adverse kidney outcomes in patients with IgAN but they did not outperform the IIgAN-PT.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Internal Medicine, Seoul National University Hospital, Seoul, Republic of Korea.
- Interdisciplinary Program in Bioengineering, Seoul National University Graduate School, Seoul, Republic of Korea.
- Integrated Major in Innovative Medical Science, Seoul National University Graduate School, Seoul, Republic of Korea.
- Department of Internal Medicine, Asan Medical Center, Seoul, Republic of Korea.
- Department of Internal Medicine, Chungbuk National University Hospital, Cheongju, Republic of Korea.
- Department of Internal Medicine, Kangwon National University Hospital, Kangwon National University School of Medicine, Chuncheon, Republic of Korea.
Förderung
- National Research Foundation of Korea
- Korean Nephrology Research Foundation
Zitieren
APA
Park, S., Kim, Y., Baek, C. H., Cho, H., Park, J. I., Koh, E. S., Lee, J. P., Park, S. H., Kim, H. W., Han, S. H., Chin, H. J., Kim, D. K., Moon, K. C., Kim, Y. G., & Lee, H. (2025). Conventional machine learning-based prediction models did not outperform the International IgA Nephropathy Prediction Tool. Kidney Research and Clinical Practice, 44(5), 802-813. https://doi.org/10.23876/j.krcp.23.212
Vancouver
Park S, Kim Y, Baek CH, Cho H, Park JI, Koh ES, et al. Conventional machine learning-based prediction models did not outperform the International IgA Nephropathy Prediction Tool. Kidney Research and Clinical Practice. 2025;44(5):802-813. doi:10.23876/j.krcp.23.212
BibTeX
@article{Park2025,
author = {Park, Sehoon and Kim, Yisak and Baek, Chung Hee and Cho, Hyunjeong and Park, Ji In and Koh, Eun Sil and Lee, Jung Pyo and Park, Sun-Hee and Kim, Hyung Woo and Han, Seung Hyeok and Chin, Ho Jun and Kim, Dong Ki and Moon, Kyung Chul and Kim, Young-Gon and Lee, Hajeong},
title = {Conventional machine learning-based prediction models did not outperform the International IgA Nephropathy Prediction Tool},
journal = {Kidney Research and Clinical Practice},
year = {2025},
volume = {44},
number = {5},
pages = {802--813},
doi = {10.23876/j.krcp.23.212}
}
EUVIMED