arXiv cs.CL· Daniel Palacios, Guantong Qi, Mikael Guzman Karlsson, Shawntel K. David, Mohammed Sameeruddin, Bernhard Suter, Zhandong Liu, Davut Pehlivan, Hu Chen·· 2 天前AI 评分23
双 LLM 共识流程记录 Rett 综合征 Trofinetide 治疗表型
Documenting Trofinetide Treatment Phenotypes in Rett Syndrome with a Dual-LLM Consensus Pipeline
AI 导读
研究者开发了一套双 LLM 共识流程，从 Texas Children's Hospital 108 名患者的 26,763 份临床笔记中提取 18 种 Trofinetide 治疗反应表型。
正文 · 原文
Abstract:Objective: Trofinetide, approved in 2023 as the first Rett syndrome treatment, lacks scalable real-world monitoring because chart review is labor-intensive. We developed a dual large language model (LLM) consensus pipeline to extract 18 treatment-response phenotypes, comprising 4 adverse effects, 13 Rett clinical features, and medication refusal, from clinical notes. Materials and Methods: We analyzed 26,763 notes from 108 patients with confirmed sustained trofinetide exposure at Texas Children's Hospital. The pipeline filters notes by keyword, classifies each through two LLMs requiring consensus, and aggregates a patient-by-timepoint matrix. Architecture and prompt were selected on a diarrhea development set, then frozen and applied to the other 17 phenotypes with the phenotype definition substituted, as an out-of-sample test. The reported prompt comparison scores 183 expert-labeled cells. Results: A prompt requiring diarrhea to be active and severe performed best (84.2 $\pm$ 0.0% accuracy; F1 = 0.674), 47 percentage points above regular-expression matching ($p < 0.0001$). Expert reviewers judged six of the pipeline's calls per phenotype, three positive and three negative, and agreed with 90.2% (92/102). The 13 Rett clinical features are manifestations of the disorder itself rather than adverse effects of trofinetide. Gross and fine motor impairment, language/communication, and stereotypy were documented present in 92-100% of patients at every visit. Discussion: In-context LLM extraction captured multi-domain treatment responses. The outcome is documented presence at each visit, not a direction-of-change judgment. Conclusion: Coupling in-context LLM reasoning with a consensus architecture offers a scalable alternative to keyword and regular-expression extraction for real-world evidence, adapting to new phenotypes and medications through configuration alone.
| Comments: | 20 pages, 3 figures, 4 tables; supplementary material (22 pages, 1 figure, 11 tables) included |
| Subjects: | Quantitative Methods (q-bio.QM); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.22062 [q-bio.QM] |
| (or arXiv:2610.22062v1 [q-bio.QM] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22062 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Daniel Palacios [view email]
[v1]
Thu, 15 Oct 2026 15:24:47 UTC (405 KB)
来源：arXiv cs.CL · arxiv.org