A Model Predictive Control Functional Continuous Time Bayesian Network for Self-Management of Multiple Chronic Conditions
Northwestern University（西北大学）；The University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）；Florida State University（佛罗里达州立大学）；The University of Texas Health Science Center at Houston（德克萨斯大学休斯顿健康科学中心）
Syed Hasib Akhter Faruqui, Adel Alaeddini, Jing Wang, Susan P Fisher-Hoch, Joseph B Mccormick, Julian Carvajal Rico
备注：
Submitted for review in Artificial Intelligence in Medicine
Multiple chronic conditions (MCC) are one of the biggest challenges of modern times. The evolution of MCC follows a complex stochastic process that is influenced by a variety of risk factors, ranging from pre-existing conditions to modifiable lifestyle behavioral factors (e.g. diet, exercise habits, tobacco use, alcohol use, etc.) to non-modifiable socio-demographic factors (e.g., age, gender, education, marital status, etc.). People with MCC are at an increased risk of new chronic conditions and mortality. This paper proposes a model predictive control functional continuous time Bayesian network, an online recursive method to examine the impact of various lifestyle behavioral changes on the emergence trajectories of MCC and generate strategies to minimize the risk of progression of chronic conditions in individual patients. The proposed method is validated based on the Cameron county Hispanic cohort (CCHC) dataset, which has a total of 385 patients. The dataset examines the emergence of 5 chronic conditions (diabetes, obesity, cognitive impairment, hyperlipidemia, and hypertension) based on four modifiable risk factors representing lifestyle behaviors (diet, exercise habits, tobacco use, alcohol use) and four non-modifiable risk factors, including socio-demographic information (age, gender, education, marital status). The proposed method is tested under different scenarios (e.g., age group, the prior existence of MCC), demonstrating the effective intervention strategies for improving the lifestyle behavioral risk factors to offset MCC evolution.
Collaborative Management for Chronic Diseases and Depression: A Double Heterogeneity-based Multi-Task Learning Method
City University of Hong Kong（香港城市大学）；University of Science and Technology of China（中国科学技术大学）；University of Delaware（特拉华大学）；Hefei University of Technology（合肥工业大学）
COBRA: Multimodal Sensing Deep Learning Framework for Remote Chronic Obesity Management via Wrist-Worn Activity Monitoring
Department of Electrical and Electronic Engineering, Imperial College London, London SW7 2AZ, UK（帝国理工学院电子与电气工程系）；Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford OX3 7DQ, UK（牛津大学生物医学工程研究所）
A Generative Framework for Predictive Modeling of Multiple Chronic Conditions Using Graph Variational Autoencoder and Bandit-Optimized Graph Neural Network
Department of Mechanical Engineering, The University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校机械工程系）；Department of Mechanical Engineering, Southern Methodist University（南方 Methodist 大学机械工程系）；Engineering Technology Department, Sam Houston State University（萨姆霍茨顿州立大学工程技术系）；UTHealth Houston, The University of Texas Health Science Center at Houston（德克萨斯大学健康科学中心休斯顿分校）
Deep Learning for Detecting and Early Predicting Chronic Obstructive Pulmonary Disease from Spirogram Time Series
Tianjin University of Technology（天津理工大学）；Tsinghua University（清华大学）；The Second Hospital of Tianjin Medical University（天津医科大学第二医院）；Peking University People’s Hospital（北京大学人民医院）；HeartVoice Medical Technology（声脉医疗科技）；University of Oxford（牛津大学）；Peking University（北京大学）
Concept for a Technical Infrastructure for Management of Predictive Models in Industrial Applications
Josef Ressel Center for Symbolic Regression（约瑟夫·雷塞尔符号回归中心）；Heuristic and Evolutionary Algorithms Laboratory（启发式与进化算法实验室）；University of Applied Sciences Upper Austria（上奥地利应用科学大学）
Transformer-based Time-to-Event Prediction for Chronic Kidney Disease Deterioration
Faculty of Data and Decision Sciences, Technion-Israel Institute of Technology（以色列理工学院数据与决策科学学院）；Faculty of Biology, Technion-Israel Institute of Technology（以色列理工学院生物学院）；The Taub Faculty of Computer Science, Technion-Israel Institute of Technology（以色列理工学院陶布计算机科学学院）
Nationwide EHR-Based Chronic Rhinosinusitis Prediction Using Demographic-Stratified Models
Electrical and Computer Engineering（电气与计算机工程）；University of Houston（休斯顿大学）；Otolaryngology（耳鼻喉科）；Houston Methodist Hospital（休斯顿方法医院）；Information Science Technology（信息科学与技术）
Leveraging Activity Recognition to Enable Protective Behavior Detection in Continuous Data
University College London（伦敦大学学院）；Uppsala University（乌普萨拉大学）；Nokia Bell Labs（诺基亚贝尔实验室）；University of Cambridge（剑桥大学）
慢性疼痛（CP）患者在体力活动中表现出的保护性行为是了解其身体和情绪状态的关键。现有的自动保护行为检测（PBD）方法依赖于用户预定义的活动的预分割。然而，在现实生活中，人们随意地进行活动。因此，当这些活动对慢性疼痛患者造成困难时，应持续提供技术支持，并自动适应活动类型和保护行为的发生。因此，为了促进无处不在的CP管理，在连续数据上实现准确的PBD变得至关重要。在本文中，我们提出通过一种新的分层HAR-PBD架构将人类活动识别（HAR）与PBD集成在一起，该架构包括图卷积和长短期记忆（GC-LSTM）网络，并使用类平衡的焦点类别交叉熵（CFCC）损失来缓解类不平衡。通过使用CP患者数据集对该方法进行深入评估，我们发现HAR，GC-LSTM网络和CFCC损失的利用导致PBD性能相对于基线明显增加（宏观F1评分为0.81 vs. 0.66，精确召回曲线下面积（PR-AUC）为0.60 vs. 0.44）。最后，我们讨论了CP管理及其他方面的分层架构的可能用例。我们还讨论了目前的局限性和前进的道路。
Open-Source LLM-Driven Federated Transformer for Predictive IoV Management
School of Computer Science and Technology, Algoma University, Canada（计算机科学与技术学院，阿尔戈马大学，加拿大）；Faculty of Electrical Engineering, Czech Technical University in Prague, Czech Republic（电气工程系，布拉格捷克技术大学，捷克共和国）
Evaluating Time Series Models for Urban Wastewater Management: Predictive Performance, Model Complexity and Resilience
Berlin University of Applied Sciences and Technology（柏林应用科学与技术大学）；Intelligent Embedded Systems Department, University of Duisburg-Essen（智能嵌入式系统系，杜伊斯堡- Essen大学）；Einstein Center Digital Future（爱因斯坦数字未来研究中心）
