The contemporary paradigm of trajectory learning operates fundamentally at the level of group dynamics, systematically reducing individual-level complexity to fit group-level models, thus rendering effective patient subtyping difficult and individual-level modeling largely out of reach. We propose a data-driven paradigm that introduces a dedicated individual-level temporal variable to capture \emph{Timing Attention} (i.e., the degree of concentration of an event's timing distribution across the patient cohort), thereby rendering timing a \emph{computable dimension} that enables individualized temporal features in trajectory learning.
Instantiated as the Level-of-Individual Time Transformation (LITT) and applied to longitudinal EHR data from 3,276 breast cancer patients, the proposed paradigm demonstrates, for the first time to our knowledge: (1) automatic discovery of clinically significant patient trajectories, and (2) counterfactual timing deduction, that is, a \emph{What-If Machine}. Both results are purely data-driven, requiring no prior domain knowledge. LITT further achieves strong performance on timing prediction and survival analysis tasks.
Assessing the Real-World Utility of Explainable AI for Arousal Diagnostics: An Application-Grounded User Study
IT-Designers Gruppe Esslingen am Neckar（埃斯林根内卡尔IT设计组）；University of Tübingen（图宾根大学）；University of Giessen（吉森大学）；Klinikum Esslingen, Klinik für Kardiologie, Pneumologie und Angilologie（埃斯林根克林克医院，心内科、呼吸科和内科）；Technical University of Munich（慕尼黑技术大学）
Generating Synthetic Clinical Data that Capture Class Imbalanced Distributions with Generative Adversarial Networks: Example using Antiretroviral Therapy for HIV
the University of New South Wales（新南威尔士大学）；Hospital Universitario San Cecilio（圣塞西利奥大学医院）；Karolinska Institutet（卡罗林斯卡学院）；Università degli Studi di Siena（锡耶纳大学）；Universität zu Köln（科隆大学）；Australian National University（澳大利亚国立大学）
Interaction-Limited Safe Continuous-Time RL for Dynamical Medical Treatment
Tokyo University of Agriculture and Technology（东京大学农业技术大学）；LY Corporation（LY公司）；National University of Singapore（新加坡国立大学）；Institute of Science Tokyo（东京科学研究所）；Altos Labs, Inc.（Altos实验室）；National Institute of Advanced Industrial Science and Technology (AIST)（国家先进工业科学与技术研究院）；Norwegian University of Science and Technology（挪威科学技术大学）；Emory University（埃默里大学）；Hiroshima University（广岛大学）
Harvard Medical School（哈佛医学院）；Harvard College（哈佛学院）；Broad Institute of MIT and Harvard（麻省理工学院和哈佛大学布罗德研究所）；Harvard Data Science Initiative（哈佛数据科学研究院）；Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University（哈佛大学肯普纳自然与人工智能研究学院）
Interpretable Generative and Discriminative Learning for Multimodal and Incomplete Clinical Data
Department of Health Sciences and Technology (DHEST), ETH Zurich（健康科学与技术系，苏黎世联邦理工学院）；Department of Signal Theory and Communications, Universidad Carlos III de Madrid（信号理论与通信系，卡洛斯三世大学）；UCL Hawkes Institute, Department of Computer Science, University College London（UCL Hawkes研究所，伦敦大学学院计算机科学系）；Instituto de Investigación Sanitaria Gregorio Marañón (IiSGM), Madrid（Gregorio Marañón卫生研究所（IiSGM），马德里）
Late fusion of machine learning models using passively captured interpersonal social interactions and motion from smartphones predicts decompensation in heart failure
Georgia Institute of Technology（佐治亚理工学院）；Emory University（埃默里大学）；Emory Healthcare（埃默里医疗保健）
Beyond Random Missingness: Clinically Rethinking for Healthcare Time Series Imputation
King’s College London（伦敦国王学院）；PyPOTS Research（PyPOTS研究中心）；University of Oxford（牛津大学）；Hong Kong University of Science and Technology（香港科技大学）；University College London（伦敦大学学院）
Early Prediction of Sepsis From Clinical Datavia Heterogeneous Event Aggregation
Peking University（北京大学）
脓毒症是一种危及生命的疾病，严重危及全世界数百万人的生命。随着电子健康记录（EHR）的广泛应用，可以有效处理临床序列数据的预测模型有望增加预测脓毒症并采取早期预防治疗的可能性。然而，早期预测是具有挑战性的，因为患者的序列数据在EHR中包含多个临床事件的时间相互作用。传统的LSTM很难捕捉长事件序列中的时间交互。我们提出的模型不是直接将LSTM模型应用于事件序列，而是首先在短时间内聚合异构临床事件，然后捕获聚合表示与LSTM的时间交互。我们提出的异构事件聚合不仅可以缩短临床事件序列的长度，而且还有助于在聚合表示的多个头部中保留临床事件的分类和数值特征的时间交互。在PhysioNet/Computing in Cardiology Challenge 2019中，与名为PKU_DLIB的团队合作，我们提出的模型在全测试集中以高效率获得了效用得分（0.321）。
Bayesian Semiparametric Model for Sequential Treatment Decisions with Informative Timing
Brown University（布朗大学）；University of Pennsylvania（宾夕法尼亚大学）；University of Southern California（南加州大学）；Children’s Hospital of Philadelphia（费城儿童医院）；Rutgers University（罗格斯大学）
