文献类型：期刊文献

英文题名：Decision Tree Extraction for Clinical Decision Support System With If-Else Pseudocode and PlanSelect Strategy

作者：Hou, Ruihui[1];Wang, Xiaojun[1];Zhang, Weiyan[1];Song, Zhexin[1];Wang, Kai[1];Chen, Yifei[1];Liu, Jingping[1];Ruan, Tong[1]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China

年份：2025

卷号：29

期号：5

起止页码：3642

外文期刊名：IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS

收录：;EI(收录号：20250317718779);WOS:【SCI-EXPANDED(收录号:WOS:001483871500023)】；

基金：This work was supported in part by the National Key Research and Development Program of China under Grant 2021YFC2701800 and Grant 2021YFC2701801, in part by the Shanghai Sailing Program under Grant 23YF1409400, in part by the National Natural Science Foundation of China under Grant 62306112, and in part by the Shanghai Pilot Program for Basic Research under Grant 22TQ1400100-20.

语种：英文

外文关键词：Decision trees; Data mining; Cognition; Medical diagnostic imaging; Medical services; Large language models; Decision support systems; Predictive models; Pipelines; Pediatrics; Medical decision tree extraction; large language model; If-Else pseudocode; PlanSelect

摘要：Decision trees, as a structured representation of medical knowledge, are critical resources for building clinical decision support systems. Their structured decision pathways can be used for retrieval to enhance clinical decision making. Currently, mainstream methods mainly utilize large language models and in-context learning for decision tree extraction. However, these methods often face challenges in understanding the structure of decision trees and accurately extracting the complete content of tree nodes, leading to noise in the extracted trees and ultimately impacting their effectiveness in clinical decision support system. To this end, in this paper, we propose a novel decision tree extraction framework, including two stages. In the first stage, we propose to use the If-Else pseudocode to represent the decision tree structure and design specific constraints on format and content to guide the LLM in generating outputs. In the second stage, we introduce a novel node-filling strategy called PlanSelect to match the extracted triplets with sub-sentences in the generated pseudocode, including four reasoning steps: observation, plan, action, and answer. To evaluate the effectiveness of our proposed method, we construct an English decision tree extraction dataset (EMDT) and conduct extensive experiments on the built and public datasets. Experiments on the Text2DT and EMDT datasets demonstrate that our method outperforms the current state-of-the-art approaches, achieving improvements of 1.37% and 1.54% on the $ER$ metric (which is lower is better), respectively. Furthermore, we use the medical decision trees extracted using our framework to improve the model's performance on clinical decision making tasks, i.e., CMB-Clin and MedQA.