TabPFN V2 表格基础模型在四类医学数据集中的临床预测性能评估
Foundation models for tabular medical detection: a robust and generalizable framework for clinical decision support
该研究显示,表格基础模型 TabPFN V2 在肿瘤、内分泌、心血管和产科四个公开医学数据集上的平均准确率为 88.38%,优于资源受限的 AutoGluon (87.02%) 和逻辑回归 (84.81%)。
- Article
- Open access
- Published: 01 October 2026
Scientific Reports (2026) Cite this article
We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.
Abstract
In clinical prediction, tabular data needs to be processed, which is difficult due to small, heterogeneous and imbalanced medical data sets. This work compares the performance of TabPFN V2, a tabular foundation model, across four public medical datasets for oncology, endocrinology, cardiology, and obstetrics. TabPFN V2 was compared against resource-constrained AutoGluon, a stacked ensemble, and logistic regression, with the same splits of stratified five-fold (with the same random seed). All metrics were computed using out-of-fold predictions saved after fitting median imputation in each training fold. The measures of accuracy, precision, recall, F1-score and ROC-AUC were used to assess the predictive performance, and the Brier score, the expected calibration error and reliability diagrams were used to assess the probabilistic reliability. Paired stratified bootstrap resampling (1,000 resamples) quantified uncertainty in pairwise differences. Mean accuracy across the four datasets was 88.38% for TabPFN, 88.13% for the stacked ensemble, 87.02% for resource-constrained AutoGluon, and 84.81% for logistic regression. Compared with AutoGluon, TabPFN had higher mean ROC-AUC by 0.0093 (95% CI 0.0041 to 0.0151). Compared with the stacked ensemble, the ROC-AUC difference was small and compatible with no difference (0.0028; 95% CI -0.0005 to 0.0065), while the stacked ensemble had higher mean F1-score (TabPFN minus stacked ensemble, -0.0150; 95% CI -0.0274 to -0.0028). TabPFN had a lower mean Brier score than all three comparators under the evaluated protocol. TabPFN showed strong predictive discrimination and probability calibration on these four datasets, but the results do not establish general superiority across clinical tasks. The AutoGluon findings should be interpreted as a resource-constrained comparison, and the paired intervals are conditional on the four datasets studied.
Acknowledgements
The authors would like to acknowledge the publicly available medical datasets and open-source research communities that supported this study.
Funding
The authors received no specific funding for this work.
Author information
Authors and Affiliations
Computer Engineering Department, Altinbas University, Istanbul, Turkey
Mustafa Adil Fayez & Safaa Saad Salim
Authors
- Mustafa Adil Fayez
- Safaa Saad Salim
Corresponding author
Correspondence to Mustafa Adil Fayez.
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Fayez, M.A., Salim, S.S. Foundation models for tabular medical detection: a robust and generalizable framework for clinical decision support. Sci Rep (2026). https://doi.org/10.1038/s41598-026-73565-w
Received: 15 May 2026
Accepted: 23 September 2026
Published: 01 October 2026
DOI: https://doi.org/10.1038/s41598-026-73565-w
Keywords
来源:Nature 健康护理主题 · nature.com