Identifying subtypes of heart failure with machine learning: external, prognostic and genetic validation in three electronic health record sources with 320,863 individuals
Identifying subtypes of heart failure with machine learning: external, prognostic and genetic validation in three electronic health record sources with 320,863 individuals
复制标题
通过机器学习识别心力衰竭的亚型：对 320,863 人的三个电子健康记录源进行外部、预后和遗传验证
DOI：
10.1101/2022.06.27.22276961
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Banerjee A
中科院分区：
文献类型：
--
作者：
Banerjee A
背景可靠地识别心力衰竭 (HF) 亚型可能有助于进行有针对性的管理。机器学习 (ML) 已被用于探索心力衰竭亚型，但既没有跨大型、独立、基于人群的数据集，也没有跨全部原因和表现，也没有通过不同的 ML 方法进行临床和非临床验证。使用我们发布的框架，我们确定并验证了心力衰竭亚型，以弥补这些差距。方法我们从两个基于人群的电子健康记录资源（1998-2018；临床实践研究数据链，CPRD：n = 188,799 心力衰竭病例；健康改善网络，THIN：n = 124,263 心力衰竭病例）分析了≥30年发生心力衰竭的个体。心力衰竭前后的因素 (n=645) 包括人口统计学、病史、检查、血液实验室值和药物治疗。我们使用四种无监督 ML 方法（K-means、分层、K-Medoids 和混合模型聚类）识别子类型，每个数据集中有 87 个（从 645 个）因素。我们评估了亚型：(i) 外部有效性（跨独立数据集）；(ii) 预后有效性（1 年死亡率的预测准确性）； (iii) 独特的是，遗传有效性（在英国生物库；n=9573 例）：与 11 个 HF 相关性状的多基因风险评分 (PRS) 相关，并与 12 个报告的 HF 单核苷酸多态性 (SNP) 直接相关。结果在识别出 5 个簇后，我们标记了 HF 亚型：1. 早发性、2. 晚发性、3. AF 相关性、4. 代谢性和5.心脏代谢。外部有效性：各数据集的子类型相似（c 统计量：CPRD 中的 THIN 模型为 0.94、0.80、0.79、0.83、0.92，子类型 1-5 的 CPRD 模型为 0.79、0.92、0.90、0.89、0.92，预后有效性：CPRD 和 THIN 数据中不同亚型的一年全因死亡率、非致命性心血管疾病风险和全因住院（心力衰竭诊断前后）不同。遗传有效性：AF 相关亚型显示与 PRS 的相关特征相关。晚发亚型和心脏代谢亚型最具可比性，并且与高血压、心肌梗死和肥胖的 PRS 密切相关（p 值 < 9.09 × 10−4）。我们开发了一个临床使用的原型，可以评估有效性和成本效益。解释在迄今为止最大的心力衰竭研究中，通过四种方法和三个数据集（包括遗传数据），机器学习算法识别出了心力衰竭患者的五种亚型。这些亚型可能为病因学研究、临床风险预测和心力衰竭试验的设计提供信息。资助欧盟创新药物计划。背景研究本研究之前的证据在截至 2019 年 12 月的系统评价中，我们表明，机器学习在心血管疾病亚型分型和风险预测方面的研究受到人口规模小、因素相对较少以及由于缺乏外部验证而导致结果普遍性差的限制。我们进一步搜索了 PubMed、medRxiv、bioRxiv、arXiv，寻找相关的同行评审文章和预印本，重点关注心力衰竭的机器学习研究。研究仍然集中于单一疾病、有限的风险因素，通常是单一的机器学习方法，很少同时使用子类型和风险预测，并且尚未在数据集上进行外部验证。对于心力衰竭，所有亚型发现研究都基于聚类确定了亚型，但迄今为止尚未应用于临床实践。这项研究的附加价值在两个独立的、基于人群的数据集中，我们使用了四种机器学习方法来对 89 个病因因素以及 556 个心力衰竭的其他因素进行亚型分型和风险预测。我们 …
BackgroundReliable identification of heart failure (HF) subtypes might allow targeted management. Machine learning (ML) has been used to explore HF subtypes, but neither across large, independent, population-based datasets, nor across the full spectrum of causes and presentations, nor with clinical and non-clinical validation by different ML methods. Using our published framework, we identified and validated HF subtypes to address these gaps.MethodsWe analysed individuals ≥30 years with incident HF from two population-based electronic health records resources (1998-2018; Clinical Practice Research Datalink, CPRD: n=188,799 HF cases; The Health Improvement Network, THIN: n=124,263 HF cases). Pre-and post-HF factors (n=645) included demography, history, examination, blood laboratory values and medications. We identified subtypes using four unsupervised ML methods (K-means, hierarchical, K-Medoids and mixture model clustering) with 87 (from 645) factors in each dataset. We evaluated subtypes for: (i)external validity(across independent datasets);(ii) prognostic validity(predictive accuracy for 1-year mortality); and (iii) uniquely,genetic validity(in UK Biobank; n=9573 cases): association with polygenic risk score (PRS) for 11 HF related traits, and direct association with 12 reported HF single nucleotide polymorphisms (SNPs).FindingsAfter identifying five clusters, we labelled HF subtypes: 1.Early-onset, 2.Late-onset, 3.AF-related, 4.Metabolic, and 5.Cardiometabolic.External validity:Subtypes were similar across datasets (c-statistic: 0.94, 0.80, 0.79, 0.83, 0.92 for the THIN model in CPRD and 0.79, 0.92, 0.90, 0.89, 0.92 for the CPRD model in THIN for subtypes 1-5, respectively).Prognostic validity:One-year all-cause mortality, risk of non-fatal cardiovascular diseases and all-cause hospitalisation (before and after HF diagnosis) differed across subtypes in CPRD and THIN data.Genetic validity:The AF-related subtype showed associations with PRS for related traits. Late-onset and Cardiometabolic subtypes were most comparable and strongly associated with PRS for Hypertension, Myocardial Infarction and Obesity (p-value < 9.09 × 10−4). We developed a prototype for clinical use, which could enable evaluation of effectiveness and cost-effectiveness.InterpretationAcross four methods and three datasets, and including genetic data, in the largest HF study to-date, ML algorithms identified five subtypes in individuals with incident HF. These subtypes may inform aetiologic research, clinical risk prediction and the design of HF trials.FundingEuropean Union Innovative Medicines Initiative.Research in contextEvidence before this studyIn a systematic review until December 2019, we showed that studies of machine learning in subtyping and risk prediction in cardiovascular diseases are limited by small population size, relatively few factors and poor generalisability of findings due to lack of external validation. We further searched PubMed, medRxiv, bioRxiv, arXiv, for relevant peer-reviewed articles and preprints, focusing on machine learning studies in heart failure. Studies remain focused on single diseases, limited risk factors, often single method of machine learning, rarely use subtyping and risk prediction together, and have not been externally validated across datasets. For heart failure, all subtype discovery studies have identified subtypes based on clustering, but so far with no application to clinical practice.Added value of this studyAcross two independent, population-based datasets, we used four machine learning methods for subtyping and risk prediction with 89 aetiologic factors as well as 556 further factors for heart failure. We …
登录
查看更多内容
影响因子：
2.6
作者：
Cai, Bing;Xu, Weifeng;Watson, Douglas J.
通讯作者：
Watson, Douglas J.
影响因子：
37.8
作者：
Santhanakrishnan R;Wang N;Larson MG;Magnani JW;McManus DD;Lubitz SA;Ellinor PT;Cheng S;Vasan RS;Lee DS;Wang TJ;Levy D;Benjamin EJ;Ho JE
通讯作者：
Ho JE
影响因子：
3.2
作者：
Saraswat, Mukesh;Arya, K. V.
通讯作者：
Arya, K. V.
DOI：
10.1016/j.jchf.2018.05.018
发表时间：
2018-08
期刊：
JACC. Heart failure
影响因子：
--
作者：
Savji N;Meijers WC;Bartz TM;Bhambhani V;Cushman M;Nayor M;Kizer JR;Sarma A;Blaha MJ;Gansevoort RT;Gardin JM;Hillege HL;Ji F;Kop WJ;Lau ES;Lee DS;Sadreyev R;van Gilst WH;Wang TJ;Zanni MV;Vasan RS;Allen NB;Psaty BM;van der Harst P;Levy D;Larson M;Shah SJ;de Boer RA;Gottdiener JS;Ho JE
通讯作者：
Ho JE
影响因子：
37.8
作者：
Solomon, Scott D.;Pfeffer, Marc A.
通讯作者：
Pfeffer, Marc A.