Resource-Conscious Modeling for Next- Day Discharge Prediction Using Clinical Notes
University of California, Irvine, Donald Bren School of Information, Department of Informatics(加州大学尔湾分校,唐纳德·布伦信息与计算机科学学院,信息学系);University of California, Irvine, Department of Neurosurgery(加州大学尔湾分校,神经外科系)
Ha Na Cho, Sairam Sutari, Alexander Lopez, Hansen Bow, Kai Zheng
及时的出院预测对于优化 elective spine surgery 单位的床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)和传统文本模型在使用术后临床笔记进行次日出院预测的可行性。我们比较了13种模型,包括TF-IDF与XGBoost、LGBM以及通过LoRA微调的紧凑型LLMs(DistilGPT-2、Bio_ClinicalBERT)。TF-IDF与LGBM在平衡性上表现最佳,出院类别的F1得分为0.47,召回率为0.51,AUC-ROC最高为0.80。尽管LoRA提高了DistilGPT2的召回率,但整体上基于Transformer和生成模型的表现不佳。这些发现表明,在实际的不平衡临床预测任务中,可解释性且资源高效的模型可能优于紧凑型LLMs。
英文摘要:
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.
EHRNote-ChatQA: A Benchmark for Evidence-Grounded Multi-Turn Clinical Question Answering over Longitudinal Discharge Summaries
KAIST(韩国科学技术院);Seoul National University(首尔大学);Seoul National University Bundang Hospital(首尔大学盆唐医院);SAIHST, Sungkyunkwan University(成均馆大学);Yonsei University College of Medicine(延世大学医学院);Gangnam Severance Hospital(江南塞弗伦斯医院);Severance Hospital(塞弗伦斯医院);Seoul Medical Center(首尔医疗中心);Seoul National University Hospital(首尔大学医院);National Cancer Center(国立癌症中心);Icahn School of Medicine at Mount Sinai(西奈山伊坎医学院);Samsung Medical Center(三星医疗中心)
MIMIC-\RNum{4}-Ext-22MCTS: A 22 Millions-Event Temporal Clinical Time-Series Dataset with Relative Timestamp for Risk Prediction
National Library of Medicine(国家医学图书馆);AWS AI Labs(AWS人工智能实验室);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Stevens Institute of Technology(史蒂文斯理工学院);Carnegie Mellon University(卡内基梅隆大学)
DischargeSim: A Simulation Benchmark for Educational Doctor-Patient Communication at Discharge
Center for Healthcare Organization and Implementation Research, VA Bedford Health Care(VA贝德福德医疗保健中心医疗组织与实施研究中心);Manning College of Information and Computer Sciences, UMass Amherst(马萨诸塞大学阿默斯特分校曼宁信息与计算机科学学院);Miner School of Computer and Information Sciences, UMass Lowell(马萨诸塞大学洛厄尔分校迈纳计算机与信息科学学院);Department of Internal Medicine, Chung-Ang University(韩国中央大学内科学系)
Model selection meets clinical semantics: Optimizing ICD-10-CM prediction via LLM-as-Judge evaluation, redundancy-aware sampling, and section-aware fine-tuning
National Kaohsiung University of Science and Technology(高雄科技大学);National Health Research Institutes(国家卫生研究院);Kaohsiung Medical University(高雄医学大学);Taitung MacKay Memorial Hospital(台东马偕纪念医院);MacKay Medical University(马偕医科大学);Kaohsiung Medical University Hospital(高雄医学大学附设医院)
PaniniQA: Enhancing Patient Education Through Interactive Question Answering
University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校);Emory University(埃默里大学);Northeastern University(东北大学);UMass Chan Medical School(马萨诸塞大学陈医学院);University of Minnesota(明尼苏达大学);University of Massachusetts Lowell(马萨诸塞大学洛厄尔分校)
ClinicalMC: A Benchmark for Multi-Course Clinical Decision-Making with Large Language Models
East China University of Science and Technology, Shanghai, China(东华大学);Renji Hospital Affiliated to Shanghai Jiaotong University School of Medicine, Shanghai, China(复旦大学附属中山医院)
Phase 1 Implementation of LLM-generated Discharge Summaries showing high Adoption in a Dutch Academic Hospital
Department of Health Information Office, Data & Digitalization, University Medical Center(健康信息办公室、数据与数字化化大学医院);Department of Trauma Surgery / Orthopedics, University Medical Center(创伤外科/骨科大学医院);Department of Orthopaedic Surgery, Massachusetts General Hospital(骨科手术科马萨诸塞总医院);Harvard Medical School Orthopaedic Trauma Initiative(哈佛医学院骨创伤倡议);Department of Orthopaedic Surgery and Sports Medicine, Amsterdam UMC location University of Amsterdam(骨科手术与运动医学部门,阿姆斯特丹UMC地点大学);Department of Orthopaedic Trauma, Flinders University Medical Centre(骨创伤部门,弗林德斯大学医疗中心);Department of Otolaryngology – Head and Neck Surgery, University Medical Center(耳鼻喉科-头颈外科大学医院);Department of Pediatrics, Pediatrics Nephrology, Beatrix Children’s Hospital, University Medical Center(儿科、儿科肾病学,比西特儿童医院,大学医院)
LLM-Orchestrated Conformance Checking in Stroke Care Without Computer-Interpretable Guidelines
Computer Science Institute, DiSIT, University of Piemonte Orientale(皮埃蒙特东方大学计算机科学研究所);Integrated Laboratory of AI and Medical Informatics, DAIRI, SS. Antonio e Biagio e Cesare Arrigo Hospital(圣安东尼奥、比亚焦与切萨雷·阿里戈医院DAIRI人工智能与医学信息学综合实验室)
Countering Catastrophic Forgetting of Large Language Models for Better Instruction Following via Weight-Space Model Merging
University of Florida(佛罗里达大学);Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida(佛罗里达大学医学院健康结果与生物医学信息学系);Department of Engineering Education, Herbert Wertheim College of Engineering, University of Florida(佛罗里达大学赫伯特·韦特海姆工程学院工程教育系);Preston A. Wells, Jr. Center for Brain Tumor Therapy, Lillian S. Wells Department of Neurosurgery, University of Florida(佛罗里达大学莉莉安·S·威尔斯神经外科系普雷斯顿·A·威尔斯脑肿瘤治疗中心)
Learning Preference-Based Objectives from Clinical Narratives for Dynamic Sepsis Treatment
Institute of Data Science, National University of Singapore, Singapore(新加坡国立大学数据科学研究所);National University Hospital, Singapore(新加坡国立大学医院);Saw Swee Hock School of Public Health, National University of Singapore, Singapore(新加坡国立大学 Saw Swee Hock 公共卫生学院)
Reconstructing Sepsis Trajectories from Clinical Case Reports using LLMs: the Textual Time Series Corpus for Sepsis
Machine Learning Department and Heinz College Carnegie Mellon University(卡内基梅隆大学机器学习系和海恩兹学院);National Library of Medicine National Institutes of Health(美国国家医学图书馆)
Lightweight Transformers for Clinical Natural Language Processing
University of Oxford(牛津大学);NLPie Research(NLPie研究院);University of Surrey(萨里大学);Oxford-Suzhou Centre for Advanced Research(牛津苏州高等研究院);Nuffield Department of Population Health, University of Oxford(牛津大学纳菲尔德人口健康系);Pandemic Sciences Institute, University of Oxford(牛津大学流行病科学研究所);Sharif University of Technology(谢里夫理工大学);Infectious Diseases Data Observatory (IDDO), University of Oxford(牛津大学传染病数据观测站(IDDO))
Assisted morbidity coding: the SISCO.web use case for identifying the main diagnosis in Hospital Discharge Records
Institute of Informatics and Telematics, National Research Council(国家研究委员会信息学与电信研究所);Azienda Sanitaria Universitaria Giuliano Isontina (ASUGI)(朱利亚诺-伊松蒂纳大学卫生集团(ASUGI))
针对临床编码可重复性差的问题,本文提出 SISCO.web 方法,利用 NLP 算法、特定编码规则和 ad hoc 决策树,辅助医生使用 ICD 在住院出院记录中识别主要病理状况并提供准确的编码建议。
Trajectory-guided discharge stratification for heart failure using short-context electronic health record sequence modeling
Sahlgrenska University Hospital(斯德哥尔摩大学医院);Department of Computer Science and Engineering, Chalmers University of Technology and University of Gothenburg(计算机科学与工程系,查尔姆斯理工大学和乌普萨拉大学);Department of Molecular and Clinical Medicine, Sahlgrenska Academy, University of Gothenburg(分子与临床医学系,斯德哥尔摩学院,乌普萨拉大学);Department of Medicine, Geriatrics and Emergency Medicine, Sahlgrenska University Hospital(医学、老年医学和急诊医学系,斯德哥尔摩大学医院);Department of Food and Nutrition, and Sport Science, Faculty of Education, University of Gothenburg(营养学与体育科学系,教育学院,乌普萨拉大学);School of Public Health and Community Medicine, Institute of Medicine, University of Gothenburg(公共卫生与社区医学系,医学院,乌普萨拉大学)
ArrhythmiaVision: Resource-Conscious Deep Learning Models with Visual Explanations for ECG Arrhythmia Classification
Dipartimento di Informatica, Università di Verona, Verona, Italy(信息学院,威尼斯大学,威尼斯,意大利);Department of Computer Science, School of Mathematics and Computer Science, Institute of Business Administration, Karachi, Pakistan(计算机科学系,数学与计算机科学学院,商学院,卡拉奇,巴基斯坦);Faculty of Information Technology, Salim Habib University, Karachi, Pakistan(信息技术学院,萨利姆·哈比大学,卡拉奇,巴基斯坦)
Clinical Term Extraction using Open-Source Small Language Models
Informatics and Data Science Institute(信息学与数据科学研究所);Biomedical Informatics, Biostatistics and Medical Epidemiology Department(生物医学信息学、生物统计学与医学流行病学系);Department of Occupational Therapy(职业治疗系);University of Missouri, Columbia, Missouri, USA(密苏里大学哥伦比亚分校)