从纵向观测数据中建模疾病进展轨迹。
Modeling Disease Progression Trajectories from Longitudinal Observational Data.
机构信息
IBM Research, Cambridge, Massachusetts, United States.
Helmholtz Zentrum Mu¨ nchen, Germany.
出版信息
AMIA Annu Symp Proc. 2021 Jan 25;2020:668-676. eCollection 2020.
Abstract
Analyzing disease progression patterns can provide useful insights into the disease processes of many chronic conditions. These analyses may help inform recruitment for prevention trials or the development and personalization of treatments for those affected. We learn disease progression patterns using Hidden Markov Models (HMM) and distill them into distinct trajectories using visualization methods. We apply it to the domain of Type 1 Diabetes (T1D) using large longitudinal observational data from the T1DI study group. Our method discovers distinct disease progression trajectories that corroborate with recently published findings. In this paper, we describe the iterative process of developing the model. These methods may also be applied to other chronic conditions that evolve over time.
摘要
分析疾病进展模式可以为许多慢性疾病的发病机制提供有用的见解。这些分析可能有助于为预防试验招募提供信息，或者为受影响者制定和个性化治疗方案。我们使用隐马尔可夫模型（HMM）来学习疾病进展模式，并使用可视化方法将其提炼为不同的轨迹。我们将其应用于 T1DI 研究组的大型纵向观察性数据的 1 型糖尿病（T1D）领域。我们的方法发现了不同的疾病进展轨迹，与最近发表的发现相符。在本文中，我们描述了开发模型的迭代过程。这些方法也可以应用于随着时间的推移而演变的其他慢性疾病。
相似文献
1
Modeling Disease Progression Trajectories from Longitudinal Observational Data.从纵向观测数据中建模疾病进展轨迹。
AMIA Annu Symp Proc. 2021 Jan 25;2020:668-676. eCollection 2020.
2
Disease progression modeling using Hidden Markov Models.使用隐马尔可夫模型进行疾病进展建模。
Annu Int Conf IEEE Eng Med Biol Soc. 2012;2012:2845-8. doi: 10.1109/EMBC.2012.6346556.
3
Hidden Markov models and iterative aligners: study of their equivalence and possibilities.隐马尔可夫模型与迭代比对算法：关于它们的等效性及应用可能性的研究
Proc Int Conf Intell Syst Mol Biol. 1993;1:395-401.
4
Longitudinal modeling of glaucoma progression using 2-dimensional continuous-time hidden Markov model.使用二维连续时间隐马尔可夫模型对青光眼进展进行纵向建模。
Med Image Comput Comput Assist Interv. 2013;16(Pt 2):444-51. doi: 10.1007/978-3-642-40763-5_55.
5
Multi-state Markov models for disease progression in the presence of informative examination times: an application to hepatitis C.存在信息性检查时间时疾病进展的多状态马尔可夫模型：在丙型肝炎中的应用。
Stat Med. 2010 May 20;29(11):1161-74. doi: 10.1002/sim.3812.
6
Updating Markov models to integrate cross-sectional and longitudinal studies.更新马尔可夫模型以整合横断面研究和纵向研究。
Artif Intell Med. 2017 Mar;77:23-30. doi: 10.1016/j.artmed.2017.03.005. Epub 2017 Mar 9.
7
Bayesian quantile nonhomogeneous hidden Markov models.贝叶斯分位数非齐次隐马尔可夫模型。
Stat Methods Med Res. 2021 Jan;30(1):112-128. doi: 10.1177/0962280220942802. Epub 2020 Jul 29.
8
Human Activity Recognition with an HMM-Based Generative Model.基于 HMM 的生成模型的人体活动识别。
Sensors (Basel). 2023 Jan 26;23(3):1390. doi: 10.3390/s23031390.
9
Modeling Chronic Obstructive Pulmonary Disease Progression Using Continuous-Time Hidden Markov Models.使用连续时间隐马尔可夫模型对慢性阻塞性肺疾病进展进行建模
Stud Health Technol Inform. 2019 Aug 21;264:920-924. doi: 10.3233/SHTI190358.
10
Hierarchical continuous-time inhomogeneous hidden Markov model for cancer screening with extensive followup data.用于癌症筛查的分层连续时间非齐次隐马尔可夫模型及大量随访数据
Stat Methods Med Res. 2022 Dec;31(12):2383-2399. doi: 10.1177/09622802221122390. Epub 2022 Aug 30.
引用本文的文献
1
Population longitudinal analysis of Gait Profile Score and North Star Ambulatory Assessment in children with Duchenne muscular dystrophy.人群纵向分析杜氏肌营养不良症患儿步态曲线评分和北极星步态评估
CPT Pharmacometrics Syst Pharmacol. 2024 May;13(5):891-903. doi: 10.1002/psp4.13126. Epub 2024 Mar 27.
2
Quantifying the utility of islet autoantibody levels in the prediction of type 1 diabetes in children.定量检测胰岛自身抗体水平在儿童 1 型糖尿病预测中的作用。
Diabetologia. 2023 Jan;66(1):93-104. doi: 10.1007/s00125-022-05799-y. Epub 2022 Oct 5.
3
Islet Autoantibody Levels Differentiate Progression Trajectories in Individuals With Presymptomatic Type 1 Diabetes.胰岛自身抗体水平可区分有前驱 1 型糖尿病个体的进展轨迹。
Diabetes. 2022 Dec 1;71(12):2632-2641. doi: 10.2337/db22-0360.
4
Progression of type 1 diabetes from latency to symptomatic disease is predicted by distinct autoimmune trajectories.1 型糖尿病从潜伏期到症状期的进展由不同的自身免疫轨迹预测。
Nat Commun. 2022 Mar 21;13(1):1514. doi: 10.1038/s41467-022-28909-1.
5
Islet Autoantibody Type-Specific Titer Thresholds Improve Stratification of Risk of Progression to Type 1 Diabetes in Children.胰岛自身抗体类型特异性滴度阈值可改善儿童 1 型糖尿病进展风险的分层。
Diabetes Care. 2022 Jan 1;45(1):160-168. doi: 10.2337/dc21-0878.
6
Islet Autoimmunity and HLA Markers of Presymptomatic and Clinical Type 1 Diabetes: Joint Analyses of Prospective Cohort Studies in Finland, Germany, Sweden, and the U.S.1型糖尿病症状前和临床阶段的胰岛自身免疫与HLA标记物：芬兰、德国、瑞典和美国前瞻性队列研究的联合分析
Diabetes Care. 2021 Jun 23;44(10):2269-76. doi: 10.2337/dc20-1836.
本文引用的文献
1
DPVis: Visual Analytics With Hidden Markov Models for Disease Progression Pathways.DPVis：用于疾病进展路径的隐马尔可夫模型可视化分析
IEEE Trans Vis Comput Graph. 2021 Sep;27(9):3685-3700. doi: 10.1109/TVCG.2020.2985689. Epub 2021 Jul 29.
2
A probabilistic disease progression modeling approach and its application to integrated Huntington's disease observational data.一种概率性疾病进展建模方法及其在亨廷顿舞蹈症综合观测数据中的应用。
JAMIA Open. 2019 Jan 7;2(1):123-130. doi: 10.1093/jamiaopen/ooy060. eCollection 2019 Apr.
3
Correlating the global increase in type 1 diabetes incidence across age groups with national economic prosperity: A systematic review.将各年龄组1型糖尿病发病率的全球增长与国家经济繁荣程度相关联：一项系统综述。
World J Diabetes. 2019 Dec 15;10(12):560-580. doi: 10.4239/wjd.v10.i12.560.
4
Childhood thyroid autoimmunity and relation to islet autoantibodies in children at risk for type 1 diabetes in the diabetes prediction in skåne (DiPiS) study.在斯科讷糖尿病预测研究（DiPiS）中，自身免疫性甲状腺疾病与儿童期 1 型糖尿病高危人群胰岛自身抗体的关系。
Autoimmunity. 2018 Aug;51(5):228-237. doi: 10.1080/08916934.2018.1519027.
5
Time-Resolved Autoantibody Profiling Facilitates Stratification of Preclinical Type 1 Diabetes in Children.时间分辨自身抗体分析有助于儿童临床前 1 型糖尿病的分层。
Diabetes. 2019 Jan;68(1):119-130. doi: 10.2337/db18-0594. Epub 2018 Oct 10.
6
Disease Progression Modeling: Key Concepts and Recent Developments.疾病进展建模：关键概念与最新进展
Curr Pharmacol Rep. 2016 Oct;2(5):221-230. doi: 10.1007/s40495-016-0066-x. Epub 2016 Aug 15.
7
Penalized nonlinear mixed effects model to identify biomarkers that predict disease progression.用于识别预测疾病进展生物标志物的惩罚非线性混合效应模型。
Biometrics. 2017 Dec;73(4):1343-1354. doi: 10.1111/biom.12663. Epub 2017 Feb 9.
8
A novel approach for the analysis of longitudinal profiles reveals delayed progression to type 1 diabetes in a subgroup of multiple-islet-autoantibody-positive children.一种用于分析纵向数据的新方法显示，在多胰岛自身抗体阳性儿童的一个亚组中，1型糖尿病的进展有所延迟。
Diabetologia. 2016 Oct;59(10):2172-80. doi: 10.1007/s00125-016-4050-0. Epub 2016 Jul 11.
9
Efficient Learning of Continuous-Time Hidden Markov Models for Disease Progression.用于疾病进展的连续时间隐马尔可夫模型的高效学习
Adv Neural Inf Process Syst. 2015;28:3599-3607.
10
Staging presymptomatic type 1 diabetes: a scientific statement of JDRF, the Endocrine Society, and the American Diabetes Association.1型糖尿病症状前分期：美国青少年糖尿病研究基金会、美国内分泌学会及美国糖尿病协会的科学声明
Diabetes Care. 2015 Oct;38(10):1964-74. doi: 10.2337/dc15-1419.
Zotero 插件