Monitoring patients in ICU is a challenging and high-cost task. Hence, predicting the condition of patients during their ICU stay can help provide better acute care and plan the hospital's resources. There has been continuous progress in machine learning research for ICU management, and most of this work has focused on using time series signals recorded by ICU instruments. In our work, we show that adding clinical notes as another modality improves the performance of the model for three benchmark tasks: in-hospital mortality prediction, modeling decompensation, and length of stay forecasting that play an important role in ICU management. While the time-series data is measured at regular intervals, doctor notes are charted at irregular times, making it challenging to model them together. We propose a method to model them jointly, achieving considerable improvement across benchmark tasks over baseline time-series model. Our implementation can be found at \url{https://github.com/kaggarwal/ClinicalNotesICU}.
Mining the contribution of intensive care clinical course to outcome after traumatic brain injury
University of Cambridge（剑桥大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Humanitas University（Humanitas大学）；Karolinska Institutet（卡罗林斯卡学院）；University of Stirling（斯特灵大学）；Leiden University Medical Center（莱顿大学医学中心）；Cambridge Centre for Artificial Intelligence in Medicine（剑桥医学人工智能中心）
Leveraging Clinical Time-Series Data for Prediction: A Cautionary Tale
University of Michigan（密歇根大学）；Michigan Medicine（密歇根医学中心）
在医疗保健中，患者风险分层模型通常使用从电子健康记录中提取的时间序列数据来学习。当为临床预测任务提取数据时，存在几种公式，这取决于如何选择预测时间和预测范围。在本文中，我们展示了该制剂如何极大地影响模型性能和临床实用性。利用公开的ICU数据集，我们考虑两个临床预测任务：住院死亡率和低钾血症。通过这些案例研究，我们证明了使用结果独立的参考点来评估模型的必要性，因为选择相对于事件的预测时间可能会导致不切实际的性能。此外，当在模拟真实世界使用的测试集上进行评估时，结果独立方案在两项任务上的表现优于结果依赖方案（住院死亡率AUROC 0.882 vs. 0.831;血清钾：AUROC 0.829 vs. 0.740）。
RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation
Technical University of Munich（慕尼黑技术大学）；TUM University Hospital（TUM大学医院）；LMU Munich（慕尼黑大学）；University of Sheffield（谢菲尔德大学）；University of Oxford（牛津大学）；Zhongshan Hospital Fudan University（复旦大学中山医院）；Sun Yat-sen University Cancer Center（中山大学肿瘤中心）；Imperial College London（伦敦帝国学院）；Munich Center for Machine Learning（慕尼黑机器学习中心）；relAI – Konrad Zuse School of Excellence in Reliable AI（relAI – 卡诺夫茨卓越可靠人工智能学校）
Stochastic Parrots or ICU Experts? Large Language Models in Critical Care Medicine: A Scoping Review
National Institute of Health Data Science, Peking University（北京大学健康医疗大数据国家研究院）；Institute of Medical Technology, Peking University Health Science Center（北京大学医学部医学技术研究院）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；Advanced Institute of Information Technology, Peking University（北京大学信息技术高等研究院）；Peking University Third Hospital（北京大学第三医院）；University of Liverpool（利物浦大学）；Johns Hopkins School of Medicine（约翰斯·霍普金斯大学医学院）；University of California, Los Angeles（加州大学洛杉矶分校）；Peking University People’s Hospital（北京大学人民医院）
