轻量模型比精调大模型更适配术后出院预测。
Resource-Conscious Modeling for Next- Day Discharge Prediction Using Clinical Notes
- 用TF-IDF+LGBM等轻量模型处理临床记录，兼顾效率与准确。
- 最佳模型F1为0.47，召回率0.51，AUC-ROC达0.80。
- 适合资源有限、需可解释性的医疗场景部署。
及时预测出院对优化择期脊柱手术病房的床位周转和资源分配至关重要。本研究评估了轻量级微调大语言模型（LLMs）与传统文本模型在基于术后临床记录预测次日出院方面的可行性。对比了13种模型，包括TF-IDF结合XGBoost和LGBM，以及通过LoRA微调的紧凑型LLM（DistilGPT-2、Bio_ClinicalBERT）。TF-IDF配合LGBM表现最佳，对出院类别的F1得分为0.47，召回率为0.51，且AUC-ROC最高（0.80）。尽管LoRA提升了DistilGPT2的召回率，但整体上基于Transformer和生成式模型的表现较差。结果表明，在真实世界中类别不平衡的临床预测任务中，可解释性强且资源消耗低的模型可能优于紧凑型LLMs。
原文摘要 · Abstract (English)
Timely discharge prediction is essential for optimizing bed turnover and resource allocation in elective spine surgery units. This study evaluates the feasibility of lightweight, fine-tuned large language models (LLMs) and traditional text-based models for predicting next-day discharge using postoperative clinical notes. We compared 13 models, including TF-IDF with XGBoost and LGBM, and compact LLMs (DistilGPT-2, Bio_ClinicalBERT) fine-tuned via LoRA. TF-IDF with LGBM achieved the best balance, with an F1-score of 0.47 for the discharge class, a recall of 0.51, and the highest AUC-ROC (0.80). While LoRA improved recall in DistilGPT2, overall transformer-based and generative models underperformed. These findings suggest interpretable, resource-efficient models may outperform compact LLMs in real-world, imbalanced clinical prediction tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。