ProtoPal：原型基学习在医疗保健领域的可解释AI演示
机器学习
2026-01-06 v1
摘要
尽管近期在机器学习和可解释AI方面取得了进展，但在个性化预防性医疗保健领域仍存在差距：预测、干预和建议应对所有医疗保健部门相关方而既可理解又可验证。我们演示原型基学习如何满足这些需求。我们提出的框架ProtoPal具有前台和后台两种模式；在保持优异定量性能的同时，还能提供对干预及其模拟结果的直观呈现。
引用
@article{arxiv.2601.02106,
title = {Prototype-Based Learning for Healthcare: A Demonstration of Interpretable AI},
author = {Ashish Rana and Ammar Shaker and Sascha Saralajew and Takashi Suzuki and Kosuke Yasuda and Shintaro Kato and Toshikazu Wada and Toshiyuki Fujikawa and Toru Kikutsuji},
journal= {arXiv preprint arXiv:2601.02106},
year = {2026}
}
备注
Accepted to the Demo Track at the IEEE International Conference on Data Mining (ICDM) 2025, where it received the Best Demo Award