The pressure of ever-increasing patient demand and budget restrictions make hospital bed management a daily challenge for clinical staff. Most critical is the efficient allocation of resource-heavy Intensive Care Unit (ICU) beds to the patients who need life support. Central to solving this problem is knowing for how long the current set of ICU patients are likely to stay in the unit. In this work, we propose a new deep learning model based on the combination of temporal convolution and pointwise (1x1) convolution, to solve the length of stay prediction task on the eICU and MIMIC-IV critical care datasets. The model - which we refer to as Temporal Pointwise Convolution (TPC) - is specifically designed to mitigate common challenges with Electronic Health Records, such as skewness, irregular sampling and missing data. In doing so, we have achieved significant performance benefits of 18-68% (metric and dataset dependent) over the commonly used Long-Short Term Memory (LSTM) network, and the multi-head self-attention network known as the Transformer. By adding mortality prediction as a side-task, we can improve performance further still, resulting in a mean absolute deviation of 1.55 days (eICU) and 2.28 days (MIMIC-IV) on predicting remaining length of stay.
Predicting Intensive Care Unit Length of Stay and Mortality Using Patient Vital Signs: Machine Learning Model Development and Validation
New Mexico Institute of Mining and Technology(新墨西哥矿业技术学院);Oak Ridge National Laboratory(橡树岭国家实验室);The University of Tennessee Health Science Center(田纳西大学健康科学中心);Illinois State University(伊利诺伊州立大学)
On the Use of Time Series Kernel and Dimensionality Reduction to Identify the Acquisition of Antimicrobial Multidrug Resistance in the Intensive Care Unit
Rey Juan Carlos University(胡安·卡洛斯国王大学);University Hospital of Fuenlabrada(富恩拉夫拉达大学医院);University Hospital of North-Norway(北挪威大学医院);UiT The Arctic University of Norway(挪威北极大学)
Feature Robustness in Non-stationary Health Records: Caveats to Deployable Model Performance in Common Clinical Machine Learning Tasks
University of Toronto(多伦多大学);Vector Institute(矢量研究所);Massachusetts Institute of Technology(麻省理工学院);Harvard University(哈佛大学);Microsoft Research(微软研究院);Tufts University(塔夫茨大学);Hospital for Sick Children(病童医院)
DeepSOFA: A Continuous Acuity Score for Critically Ill Patients using Clinically Interpretable Deep Learning
University of Florida(佛罗里达大学)
传统的危重病患者病情严重程度评估和院内死亡率预测方法需要使用静态变量阈值进行耗时、易出错的计算。这些方法没有利用流电子健康记录数据的新兴可用性或捕获时间敏感的个体生理模式,这是重症监护室中的关键任务。我们提出了一种新的敏锐度评分框架(DeepSOFA),该框架利用时间测量和可解释的深度学习模型来评估ICU住院期间任何时间点的疾病严重程度。我们使用相同的模型输入将DeepSOFA与SOFA(序贯器官衰竭评估)基线模型进行比较,发现在ICU入院期间的任何时间点,DeepSOFA对院内死亡率的预测都更加准确。在公共数据库中开发并在单个机构队列中验证的DeepSOFA模型在整个ICU住院期间的平均AUC为0.90(95% CI 0.90-0.91),而基线SOFA模型的平均AUC为0.79(95% CI 0.79-0.80)和0.85(95% CI 0.85-0.86)。深度模型非常适合在发生意外不良事件之前识别需要救生干预的ICU患者,并告知患者,提供者和家庭之间关于护理目标和最佳资源利用的共享决策过程。
Predicting the Stay Length of Patients in Hospitals using Convolutional Gated Recurrent Deep Learning Model
Canberra Health Services(堪培拉卫生服务局);Canberra Hospital(堪培拉医院);Torrens University Australia(澳大利亚托伦斯大学);The Australian National University(澳大利亚国立大学);Australian National University(澳大利亚国立大学)
A Comprehensive Benchmark for COVID-19 Predictive Modeling Using Electronic Health Records in Intensive Care
University of Edinburgh(爱丁堡大学);Health Data Research UK(英国健康数据研究中心);Peking University(北京大学);Peking University Third Hospital(北京大学第三医院);Kaihong Digital(凯宏数字)
Hi Sigma, do I have the Coronavirus?: Call for a New Artificial Intelligence Approach to Support Health Care Professionals Dealing With The COVID-19 Pandemic
Massachusetts Institute of Technology(麻省理工学院);Harvard University(哈佛大学);Universitat de Barcelona(巴塞罗那大学);Instituto de Salud Carlos III(卡洛斯三世卫生研究所);Hospital Universitari Germans Trias i Pujol(Germans Trias i Pujol大学医院);Universidad de Guadalajara(瓜达拉哈拉大学);Centro Universitario de Ciencias de la Salud(健康科学中心大学学院);OPD Hospital Civil de Guadalajara(瓜达拉哈拉市立医院)
Predicting Length of Stay in Neurological ICU Patients Using Classical Machine Learning and Neural Network Models: A Benchmark Study on MIMIC-IV
Data and Web Science Group School of Business Informatics and Mathematics University of Mannheim(数据与网络科学组 商务信息与数学学院 瑞士曼海姆大学);Human-Technology Interaction Lab Department of Neurosurgery University of Freiburg - Medical Center(人机交互实验室 神经外科系 瑞士弗赖堡医学院)
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)
Detecting Activities of Daily Living and Routine Behaviours in Dementia Patients Living Alone Using Smart Meter Load Disaggregation
人口老龄化的出现是一个重大的公共卫生问题。这导致患有进行性神经退行性疾病(如痴呆症)的人数增加。因此,这对卫生和社会保健服务造成的压力意味着提供24小时监测是不可持续的。正在考虑技术干预,但是没有解决方案可以非侵入性地监测痴呆症患者的独立生活需求。因此,许多患者在提供干预和支持之前就达到了危机点。与此同时,病人护理依赖于非正式护理人员对重大行为变化的反馈。然而,并非所有人都有社会支持网络,而且痴呆症护理的早期干预往往被错过。智能电表的推出有可能改变这一点。使用机器学习和信号处理技术,家庭能源供应可以被分解以检测哪些家用电器被打开和关闭。这将使日常生活活动(ADL)得到评估,如饮食,并观察到日常生活的变化,以进行早期干预。主要目的是帮助减少病情恶化,使患者能够在家中呆更长时间。一个支持向量机(SVM)和随机决策森林分类器建模使用的数据从三个测试家庭。然后,在与Mersey Care NHS Foundation Trust合作进行的为期六个月的临床试验中,使用经过训练的模型来监测两名痴呆症患者。在用于电器检测的负载分解的情况下,实现了SVM(AUC=0.86074,Sen=0.756和Spec=0.92838)。而决策森林达到(AUC=0.9429,Sen=0.9634和Spec=0.9634)。还分析了ADL,以识别居住者的行为模式,同时检测日常生活的改变。
Prediction of Significant Creatinine Elevation in First ICU Stays with Vancomycin Use: A retrospective study through Catboost
University of Southern California(美国南加州大学);California State Polytechnic University Pomona(加州州立理工大学庞纳分校);California State University Long Beach(加州州立大学长滩分校)
Incremental Outlier Detection Modelling Using Streaming Analytics in Finance & Health Care
National Institute of Technology Warangal(瓦朗加尔国家理工学院);Jawaharlal Nehru Technological University – Gurajada Vizianagaram (JNTU-GV)(贾瓦哈拉尔·尼赫鲁技术大学古拉贾达维齐亚纳格拉姆分校)
Computable Phenotypes of Patient Acuity in the Intensive Care Unit
Intelligent Clinical Care Center (IC3), University of Florida(佛罗里达大学智能临床护理中心(IC3));College of Medicine, University of Florida(佛罗里达大学医学院);J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida(佛罗里达大学J.克雷顿·普鲁伊特家族生物医学工程系)
Explainable Artificial Intelligence Techniques for Irregular Temporal Classification of Multidrug Resistance Acquisition in Intensive Care Unit Patients
Rey Juan Carlos University(雷伊·胡安·卡洛斯大学);University Hospital of Fuenlabrada(芬拉布拉达大学医院)
Benchmarking Deep Learning Architectures for Predicting Readmission to the ICU and Describing Patients-at-Risk
University of New South Wales(新南威尔士大学);The George Institute for Global Health(乔治全球健康研究所);The University of Sydney(悉尼大学);Concord Clinical School(康科德临床学院);Sydney Local Health District(悉尼地方卫生区);Prince of Wales Hospital(威尔士亲王医院)
A Transformer-based Diffusion Probabilistic Model for Heart Rate and Blood Pressure Forecasting in Intensive Care Unit
The University of Arizona(亚利桑那大学);Zhongshan Hospital, Fudan University(复旦大学附属中山医院);The Shanghai Institute of Cardiovascular Diseases(上海市心血管病研究所);Bio5 Institute, The University of Arizona(亚利桑那大学生物5研究所);College of Nursing, The University of Arizona(亚利桑那大学护理学院)
Enhancing Clinical Decision-Making: Integrating Multi-Agent Systems with Ethical AI Governance
College of Computing(计算学院);Georgia Institute of Technology(佐治亚理工学院);University of Illinois(伊利诺伊大学);Neuro Industry Research(神经产业研究);Neuro Industry, Inc.(神经产业公司)