Transfer Learning para Doença Renal Crônica: Avaliando a Generalização de Modelos em Diferentes Cenários Clínicos
Resumo
A Doença Renal Crônica (DRC) exige modelos preditivos robustos frente à heterogeneidade populacional e escassez de dados. Este estudo avalia estratégias de Transfer Learning (TL) em dados tabulares para predição de progressão da DRC sob domain shift, comparando MLP com fine-tuning, TASC (modelo proposto) e TabPFN a modelos treinados do zero. O desempenho variou conforme a similaridade entre domínios: o TASC destacou-se em métricas clínicas com menor domain shift, enquanto o TabPFN apresentou alta discriminação, mas desempenho inferior em métricas balanceadas. Os resultados reforçam a importância de considerar o domain shift na escolha de modelos preditivos em nefrologia.Referências
Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M. (2019). Optuna: A next-generation hyperparameter optimization framework. In Proc. of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pages 2623–2631.
Borisov, V., Leemann, T., Seßler, K., Haug, J., Pawelczyk, M., and Kasneci, G. (2024). Deep neural networks and tabular data: A survey. IEEE Transactions on Neural Networks and Learning Systems, 35(6):7499–7519.
Brasil. Ministério da Saúde (2014). Diretrizes clínicas para o cuidado ao paciente com doença renal crônica – drc no sistema Único de saúde. Secretaria de Atenção à Saúde, Departamento de Atenção Especializada e Temática.
Desautels, T., Calvert, J., Hoffman, J., Mao, Q., Jay, M., Fletcher, G., Barton, C., Chettipally, U., Kerem, Y., and Das, R. (2017). Using transfer learning for improved mortality prediction in a data-scarce hospital setting. Biomedical informatics insights, 9:1178222617712994.
Ebbehoj, A., Thunbo, M. Ø., Andersen, O. E., Glindtvad, M. V., and Hulman, A. (2022). Transfer learning for non-image data in clinical research: A scoping review. PLOS Digital Health, 1(2):e0000014.
El-Melegy, M., Mamdouh, A., Ali, S., Badawy, M., El-Ghar, M. A., Alghamdi, N. S., and El-Baz, A. (2024). Prostate cancer diagnosis via visual representation of tabular data and deep transfer learning. Bioengineering, 11(7):635.
Gao, Y. and Cui, Y. (2020). Deep transfer learning for reducing health care disparities arising from biomedical data inequality. Nature communications, 11(1):5131.
Hollmann, N., Müller, S., Eggensperger, K., and Hutter, F. (2023). Tabpfn: A transformer that solves small tabular classification problems in a second. In International Conference on Learning Representations 2023.
Hollmann, N., Müller, S., Purucker, L., Krishnakumar, A., Körfer, M., Hoo, S. B., Schirrmeister, R. T., and Hutter, F. (2025). Accurate predictions on small data with a tabular foundation model. Nature, 637(8045):319–326.
Iimori, S., Naito, S., Noda, Y., Sato, H., Nomura, N., Sohara, E., Okado, T., Sasaki, S., Uchida, S., and Rai, T. (2018). Prognosis of chronic kidney disease with normal-range proteinuria: the ckd-route study. PLoS One, 13(1):e0190493.
Kursa, M. B., Jankowski, A., and Rudnicki, W. R. (2010). Boruta–a system for feature selection. Fundamenta informaticae, 101(4):271–285.
Macias, E., Lopez Vicario, J., Serrano, J., Ibeas, J., and Morell, A. (2022). Transfer learning improving predictive mortality models for patients in end-stage renal disease. Electronics, 11(9):1447.
Okita, J., Nakata, T., Uchida, H., Kudo, A., Fukuda, A., Ueno, T., Tanigawa, M., Sato, N., and Shibata, H. (2024). Development and validation of a machine learning model to predict time to renal replacement therapy in patients with chronic kidney disease. BMC nephrology, 25(1):101.
Sanmarchi, F., Fanconi, C., Golinelli, D., Gori, D., Hernandez-Boussard, T., and Capodici, A. (2023). Predict, diagnose, and treat chronic kidney disease with machine learning: a systematic literature review. Journal of nephrology, 36(4):1101–1117.
Savalli, C., Carneiro, A. H. A., Barcellos Filho, F., Bigoto, M. A. R., Wichmann, R. M., Chiavegatto Filho, A. D. P., et al. (2025). Transfer learning for covid-19 predictive modeling: A multicenter study of 12 hospitals. Annals of Epidemiology, 108:1–7.
Segev, N., Harel, M., Mannor, S., Crammer, K., and El-Yaniv, R. (2017). Learn on source, refine on target: A model transfer learning framework with random forests. IEEE transactions on pattern analysis and machine intelligence, 39(9):1811–1824.
Shih, C., Youchen, L., Chen, C.-h., and Chu, W. C.-C. (2020). An early warning system for hemodialysis complications utilizing transfer learning from hd iot dataset. In 2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC), pages 759–767.
Tan, Z., Luo, L., and Zhong, J. (2023). Knowledge transfer in evolutionary multi-task optimization: A survey. Applied Soft Computing, 138:110182.
Zhu, Y., Bi, D., Saunders, M., and Ji, Y. (2023). Prediction of chronic kidney disease progression using recurrent neural network and electronic health records. Scientific reports, 13(1):22091.
Borisov, V., Leemann, T., Seßler, K., Haug, J., Pawelczyk, M., and Kasneci, G. (2024). Deep neural networks and tabular data: A survey. IEEE Transactions on Neural Networks and Learning Systems, 35(6):7499–7519.
Brasil. Ministério da Saúde (2014). Diretrizes clínicas para o cuidado ao paciente com doença renal crônica – drc no sistema Único de saúde. Secretaria de Atenção à Saúde, Departamento de Atenção Especializada e Temática.
Desautels, T., Calvert, J., Hoffman, J., Mao, Q., Jay, M., Fletcher, G., Barton, C., Chettipally, U., Kerem, Y., and Das, R. (2017). Using transfer learning for improved mortality prediction in a data-scarce hospital setting. Biomedical informatics insights, 9:1178222617712994.
Ebbehoj, A., Thunbo, M. Ø., Andersen, O. E., Glindtvad, M. V., and Hulman, A. (2022). Transfer learning for non-image data in clinical research: A scoping review. PLOS Digital Health, 1(2):e0000014.
El-Melegy, M., Mamdouh, A., Ali, S., Badawy, M., El-Ghar, M. A., Alghamdi, N. S., and El-Baz, A. (2024). Prostate cancer diagnosis via visual representation of tabular data and deep transfer learning. Bioengineering, 11(7):635.
Gao, Y. and Cui, Y. (2020). Deep transfer learning for reducing health care disparities arising from biomedical data inequality. Nature communications, 11(1):5131.
Hollmann, N., Müller, S., Eggensperger, K., and Hutter, F. (2023). Tabpfn: A transformer that solves small tabular classification problems in a second. In International Conference on Learning Representations 2023.
Hollmann, N., Müller, S., Purucker, L., Krishnakumar, A., Körfer, M., Hoo, S. B., Schirrmeister, R. T., and Hutter, F. (2025). Accurate predictions on small data with a tabular foundation model. Nature, 637(8045):319–326.
Iimori, S., Naito, S., Noda, Y., Sato, H., Nomura, N., Sohara, E., Okado, T., Sasaki, S., Uchida, S., and Rai, T. (2018). Prognosis of chronic kidney disease with normal-range proteinuria: the ckd-route study. PLoS One, 13(1):e0190493.
Kursa, M. B., Jankowski, A., and Rudnicki, W. R. (2010). Boruta–a system for feature selection. Fundamenta informaticae, 101(4):271–285.
Macias, E., Lopez Vicario, J., Serrano, J., Ibeas, J., and Morell, A. (2022). Transfer learning improving predictive mortality models for patients in end-stage renal disease. Electronics, 11(9):1447.
Okita, J., Nakata, T., Uchida, H., Kudo, A., Fukuda, A., Ueno, T., Tanigawa, M., Sato, N., and Shibata, H. (2024). Development and validation of a machine learning model to predict time to renal replacement therapy in patients with chronic kidney disease. BMC nephrology, 25(1):101.
Sanmarchi, F., Fanconi, C., Golinelli, D., Gori, D., Hernandez-Boussard, T., and Capodici, A. (2023). Predict, diagnose, and treat chronic kidney disease with machine learning: a systematic literature review. Journal of nephrology, 36(4):1101–1117.
Savalli, C., Carneiro, A. H. A., Barcellos Filho, F., Bigoto, M. A. R., Wichmann, R. M., Chiavegatto Filho, A. D. P., et al. (2025). Transfer learning for covid-19 predictive modeling: A multicenter study of 12 hospitals. Annals of Epidemiology, 108:1–7.
Segev, N., Harel, M., Mannor, S., Crammer, K., and El-Yaniv, R. (2017). Learn on source, refine on target: A model transfer learning framework with random forests. IEEE transactions on pattern analysis and machine intelligence, 39(9):1811–1824.
Shih, C., Youchen, L., Chen, C.-h., and Chu, W. C.-C. (2020). An early warning system for hemodialysis complications utilizing transfer learning from hd iot dataset. In 2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC), pages 759–767.
Tan, Z., Luo, L., and Zhong, J. (2023). Knowledge transfer in evolutionary multi-task optimization: A survey. Applied Soft Computing, 138:110182.
Zhu, Y., Bi, D., Saunders, M., and Ji, Y. (2023). Prediction of chronic kidney disease progression using recurrent neural network and electronic health records. Scientific reports, 13(1):22091.
Publicado
19/07/2026
Como Citar
PREGARDIER, Rafael C.; SILVA, Luis A. L.; COSTA, Rafael A. da; CAETANO, Gabriel V. S.; ASSUNÇÃO, Joaquim V. C.; POLI-DE-FIGUEIREDO, Carlos E.; REINHEIMER, Isabel C..
Transfer Learning para Doença Renal Crônica: Avaliando a Generalização de Modelos em Diferentes Cenários Clínicos. In: SEMINÁRIO INTEGRADO DE SOFTWARE E HARDWARE (SEMISH), 53. , 2026, Gramado/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 722-733.
ISSN 2595-6205.
DOI: https://doi.org/10.5753/semish.2026.23036.
