arXiv cs.AI· Liangze Ke, Daniel Zelterman, Wei Wei, Guannan Gong·· 13 小时前AI 评分31
StochIKM：从已发表 Kaplan-Meier 曲线自动高保真重建个体患者数据
StochIKM: Automated High-Fidelity Reconstruction of Individual Patient Data from Published Kaplan-Meier Curves
AI 导读
StochIKM 是一种随机算法，用视觉语言模型数字化 Kaplan-Meier 曲线图，并以“精确复现风险表、贴合曲线至图像分辨率、符合印刷中位数/区间/事件数”为约束，输出一组可接受的个体患者数据集。在模拟实验和 79 个已发表肿瘤试验组中，它复现风险表与中位数的效果优于 LLM 改进版 IPDfromKM。只要曲线图被正确读取，解就必然存在，失败则指向原图或数字化环节的问题。
正文 · 原文
Abstract:Individual patient data are the gold standard for secondary analysis of time-to-event evidence, but they are rarely released, and reconstruction from a published Kaplan-Meier figure could help. Existing methods all claim high fidelity, each judged by whichever agreements it happens to achieve, and each returns a single dataset although the map from figure to data is not bijective. We define fidelity explicitly: a dataset is admissible when it reproduces the risk table exactly, follows the digitized curve to within the image resolution, and respects the printed median, interval and event count. We propose StochIKM, a stochastic algorithm that digitizes the figure with a vision-capable language model and uses the high-fidelity definition as constraints, returning an admissible set of individual patient datasets. A solution is guaranteed to exist whenever the figure has been read correctly, so a failure indicts either the published figure or its digitization. In simulation and in 79 arms from published oncology trials, StochIKM reproduces the published risk tables and medians more closely than LLM-improved IPDfromKM, a high-impact alternative.
| Subjects: | Artificial Intelligence (cs.AI); Applications (stat.AP) |
| Cite as: | arXiv:2610.29122 [cs.AI] |
| (or arXiv:2610.29122v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.29122 arXiv-issued DOI via DataCite |
Submission history
From: Guannan Gong [view email]
[v1]
Wed, 21 Oct 2026 03:05:49 UTC (1,072 KB)
[v2]
Thu, 22 Oct 2026 02:47:45 UTC (1,072 KB)
来源：arXiv cs.AI · arxiv.org