Beyond Traditional Diagnostics: Transforming Patient-Side Information into Predictive Insights with Knowledge Graphs and Prototypes
Joint SDU-NTU Centre for Artificial Intelligence Research \& School of Software Shandong University Jinan, China;College of Computing;Data Science Nanyang Technological University Singapore
Yibowen Zhao, Yinan Zhang, Zhixiang Su, Lizhen Cui, Chunyan Miao
备注:
This work has been accepted by ICDE 2026 and is available on arXiv for early access
仅从患者侧信息(如人口统计数据和自报症状)预测疾病吸引了大量研究关注,因其有潜力提高患者意识、促进早期医疗参与并改善医疗系统效率。然而,现有方法面临关键挑战,包括疾病分布不平衡和缺乏可解释性,导致预测偏倚或不可靠。为此,我们提出Knowledge graph-enhanced, Prototype-aware, and Interpretable(KPI)框架。KPI系统地将结构化和可信的医学知识整合到统一的疾病知识图谱中,构建具有临床意义的疾病原型,并利用对比学习提高预测准确性,这对长尾疾病尤为重要。此外,KPI利用大型语言模型(LLMs)生成患者特定且医学相关的解释,从而提高可解释性和可靠性。在真实世界数据集上的大量实验表明,KPI在预测准确性上优于最先进的方法,并提供临床有效的解释,这些解释与患者叙述紧密相关,突显了其在以患者为中心的医疗保健交付中的实际价值。
英文摘要:
Predicting diseases solely from patient-side information, such as demographics and self-reported symptoms, has attracted significant research attention due to its potential to enhance patient awareness, facilitate early healthcare engagement, and improve healthcare system efficiency. However, existing approaches encounter critical challenges, including imbalanced disease distributions and a lack of interpretability, resulting in biased or unreliable predictions. To address these issues, we propose the Knowledge graph-enhanced, Prototype-aware, and Interpretable (KPI) framework. KPI systematically integrates structured and trusted medical knowledge into a unified disease knowledge graph, constructs clinically meaningful disease prototypes, and employs contrastive learning to enhance predictive accuracy, which is particularly important for long-tailed diseases. Additionally, KPI utilizes large language models (LLMs) to generate patient-specific, medically relevant explanations, thereby improving interpretability and reliability. Extensive experiments on real-world datasets demonstrate that KPI outperforms state-of-the-art methods in predictive accuracy and provides clinically valid explanations that closely align with patient narratives, highlighting its practical value for patient-centered healthcare delivery.
Using a Personal Health Library-Enabled mHealth Recommender System for Self-Management of Diabetes Among Underserved Populations: Use Case for Knowledge Graphs and Linked Data
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)
Transforming Tuberculosis Care: Optimizing Large Language Models For Enhanced Clinician-Patient Communication
School of Engineering and Technology, University of Washington Tacoma(华盛顿大学塔科马分校工程与技术学院);Institute for Clinical Effectiveness and Health Policy(临床效果与健康政策研究所);Centre for Research on Epidemiology and Public Health (CIESP), CONICET(CONICET流行病学与公共卫生研究中心);School of Nursing, University of Washington Seattle(华盛顿大学西雅图分校护理学院);School of Nursing and Healthcare Leadership, University of Washington Tacoma(华盛顿大学塔科马分校护理与医疗保健领导学院)
Predict and Interpret Health Risk using EHR through Typical Patients
Peking University(北京大学);Key Laboratory of High Confidence Software Technologies, Ministry of Education(高可信软件技术教育部重点实验室);National Engineering Research Center of Software Engineering, Peking University(北京大学软件工程国家工程研究中心);Peking University Third Hospital(北京大学第三医院);Coventry University(考文垂大学)
Towards Outcome-Driven Patient Subgroups: A Machine Learning Analysis Across Six Depression Treatment Studies
McGill University(麦吉尔大学);Stanford University(斯坦福大学);Aifred Health;Bar-Ilan University(巴伊兰大学);Kyoto University(京都大学);University of Pittsburgh(匹兹堡大学);Tufts University(塔夫茨大学);University of Arizona(亚利桑那大学);University of Toronto(多伦多大学);Queens College, City University of New York(纽约城市大学皇后学院);Université du Québec à Montréal(蒙特利尔魁北克大学)
Simulated patient systems powered by large language model-based AI agents offer potential for transforming medical education
The Chinese University of Hong Kong(香港中文大学);University of Michigan(密歇根大学);Stanford University(斯坦福大学);Mass General Brigham(麻省总医院布莱根医疗体系);Harvard Medical School(哈佛医学院);Cornell University(康奈尔大学);Peking University Third Hospital(北京大学第三医院);Shandong University(山东大学);Qilu Hospital of Shandong University(山东大学齐鲁医院);Rutgers University(罗格斯大学);Broad Institute of MIT and Harvard(麻省理工学院与哈佛大学布罗德研究所);The University of Hong Kong(香港大学);Chinese Academy of Medical Sciences and Peking Union Medical College(中国医学科学院北京协和医学院);Chinese Academy of Medical Sciences(中国医学科学院);University of Ottawa(渥太华大学);Peking University Sixth Hospital(北京大学第六医院)
"It Felt Like I Was Left in the Dark": Exploring Information Needs and Design Opportunities for Family Caregivers of Older Adult Patients in Critical Care Settings
Northeastern University(东北大学);University of Michigan(密歇根大学);University of Colorado College of Nursing(科罗拉多大学护理学院);University of Colorado Anschutz Medical Campus(科罗拉多大学安舒茨医疗校区)
Leveraging Large Language Models for Patient Engagement: The Power of Conversational AI in Digital Health
IBM T. J. Watson Research Center(IBM TJ沃森研究中心);Morehouse School of Medicine(莫尔豪斯医学院);Cleveland Clinic Foundation(克利夫兰诊所基金会);Queen’s University(女王大学);Red Hat(红帽公司)
Transforming Surgical Interventions with Embodied Intelligence for Ultrasound Robotics
Centre for Artificial Intelligence and Robotics (CAIR), HKISI-CAS(香港中文大学(深圳)人工智能与机器人中心(HKISI-CAS));Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
Resolving superposition in AI for interpretability and cross-modal alignment in patient-neuronal images
KAIST(韩国科学技术院);Konyang University(建阳大学);Chang Gung University(长庚大学);UCL Queen Square Institute of Neurology & The Francis Crick Institute(伦敦大学学院皇后广场神经病学研究所与弗朗西斯·克里克研究所)
AI in Oncology: Transforming Cancer Detection through Machine Learning and Deep Learning Applications
School of Basic Medical Sciences, Zhengzhou University(郑州大学基础医学院);School of Electrical and Information Engineering, Zhengzhou University(郑州大学电气与信息工程学院);Academy of Medical Sciences, Zhengzhou University(郑州大学医学科学院);China-US (Henan) Hormel Cancer Institute(中美(河南)荷美尔肿瘤研究院);The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer Hospital(郑州大学附属肿瘤医院 河南省肿瘤医院);State Key Laboratory of Esophageal Cancer Prevention and Treatment(食管癌防治国家重点实验室);The Collaborative Innovation Center of Henan Province for Cancer Chemoprevention(河南省癌症化预防协同创新中心)