arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.03482cs.AIcs.LGstat.AP
收藏

为健康干预个性化设计大型基础模型

Personalization of Large Foundation Models for Health Interventions

Stefan Konigorski, Johannes E. Vedder, Babajide Alamu Owoyele, İbrahim Özkan

备注：
Accepted to the AAAI 2026 Workshop on Personalization in the Era of Large Foundation Models (PerFM)
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出混合框架，结合LFMs和N-of-1试验，以实现个性化医疗中的因果推断与责任AI整合。

摘要：

大型基础模型（LFMs）正在预防、诊断和治疗领域转变医疗AI。然而，LFMs是否能够提供真正个性化的治疗建议仍是一个开放性问题。最近的研究揭示了多个个性化方面的挑战，包括根本的泛化悖论：模型在一个临床研究中表现高准确率，在其他研究中则处于偶然水平，这表明个性化和外部有效性之间存在张力。这体现了人工智能驱动医疗中的更广泛矛盾：隐私性能悖论、规模特异性悖论以及自动化同理心悖论。另一个挑战是，个性化推荐所需的因果理解程度，而非LFMs的预测能力，仍是一个开放性问题。N-of-1试验——交叉自我实验以及个性化医学中个体因果推断的黄金标准——通过提供个体因果证据并通过本地实验保护隐私来解决这些张力。尽管其令人印象深刻的能力，本文认为LFMs无法替代N-of-1试验。我们主张LFMs和N-of-1试验是互补的：LFMs在利用多模态数据从人口模式中快速生成假设方面表现卓越，而N-of-1试验在对特定个体进行因果验证方面表现卓越。我们提出一个混合框架，结合两者的优点以实现个性化并解决已识别的悖论：LFMs生成具有不确定性估计的干预候选者排名，这将触发后续的N-of-1试验。明确预测与因果之间的边界并明确解决悖论性张力对于负责任地将人工智能整合到个性化医学中至关重要。

英文摘要：

Large foundation models (LFMs) transform healthcare AI in prevention, diagnostics, and treatment. However, whether LFMs can provide truly personalized treatment recommendations remains an open question. Recent research has revealed multiple challenges for personalization, including the fundamental generalizability paradox: models achieving high accuracy in one clinical study perform at chance level in others, demonstrating that personalization and external validity exist in tension. This exemplifies broader contradictions in AI-driven healthcare: the privacy-performance paradox, scale-specificity paradox, and the automation-empathy paradox. As another challenge, the degree of causal understanding required for personalized recommendations, as opposed to mere predictive capacities of LFMs, remains an open question. N-of-1 trials -- crossover self-experiments and the gold standard for individual causal inference in personalized medicine -- resolve these tensions by providing within-person causal evidence while preserving privacy through local experimentation. Despite their impressive capabilities, this paper argues that LFMs cannot replace N-of-1 trials. We argue that LFMs and N-of-1 trials are complementary: LFMs excel at rapid hypothesis generation from population patterns using multimodal data, while N-of-1 trials excel at causal validation for a given individual. We propose a hybrid framework that combines the strengths of both to enable personalization and navigate the identified paradoxes: LFMs generate ranked intervention candidates with uncertainty estimates, which trigger subsequent N-of-1 trials. Clarifying the boundary between prediction and causation and explicitly addressing the paradoxical tensions are essential for responsible AI integration in personalized medicine.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑