背景:迄今为止,关于2型糖尿病(T2D)亚型的研究都没有使用相关的人群水平数据来研究事件和流行的T2D,包含一组不同的变量,簇表征的可解释方法,或坚持既定的框架。我们旨在使用具有全国代表性的数据开发和验证2型糖尿病(T2D)的机器学习(ML)知情亚型。
方法:在基于人群的电子健康记录(2006-2020年;临床实践研究数据链)中,≥18岁的T2D事件(n=420448),我们包括因素(n=3787),包括人口统计学,历史,考试,生物标志物和药物。使用已发布的框架,我们通过9种无监督ML方法(K-means,K-means++,K模式,K-原型,小批量,凝聚层次聚类,桦木,高斯混合模型,和共识聚类)。我们使用内部分布和可解释的人工智能(AI)技术来表征集群。我们评估了以下亚型:(1)内部效度(在数据集中;跨方法);(2)预后效度(预测5年全因死亡率,住院和新的慢性病);和(3)药物负担。
结果:发展:我们确定了四种T2D亚型:代谢,早期发病,晚发性和心脏代谢。内部效度:预测亚型的准确性很高(F1评分>0.98)。预后有效性:5年全因死亡率,住院治疗,不同T2D亚型的新慢性病发病率和用药负担不同。与代谢亚型相比,T2D事件的5年死亡率和住院风险在晚发型亚型中最高(HR1.95,1.85-2.05和1.66,1.58-1.75),在早发型亚型中最低(1.18,1.11-1.27和0.85,0.80-0.90)。慢性疾病的发病率在晚发型亚型中最高,在早发型亚型中最低。药物:与代谢亚型相比,在调整了年龄之后,性别,和T2D前的药物,晚发型亚型(1.31,1.28-1.35)和早发型亚型(0.83,0.81-0.85)的可能性最大和最小,分别,在T2D发病后5年内服用处方药。
结论:在迄今为止在T2D事件中使用ML的最大研究中,我们确定了四种不同的亚型,对病因有潜在的未来影响,治疗学,和风险预测。
BACKGROUND: None of the studies of type 2 diabetes (T2D) subtyping to date have used linked population-level data for incident and prevalent T2D, incorporating a diverse set of variables, explainable methods for cluster characterization, or adhered to an established framework. We aimed to develop and validate machine learning (ML)-informed subtypes for type 2 diabetes mellitus (T2D) using nationally representative data.
METHODS: In population-based electronic health records (2006-2020; Clinical Practice Research Datalink) in individuals ≥18 years with incident T2D (n=420 448), we included factors (n=3787), including demography, history, examination, biomarkers and medications. Using a published framework, we identified subtypes through nine unsupervised ML methods (K-means, K-means++, K-mode, K-prototype, mini-batch, agglomerative hierarchical clustering, Birch, Gaussian mixture models, and consensus clustering). We characterized clusters using intracluster distributions and explainable artificial intelligence (AI) techniques. We evaluated subtypes for (1) internal validity (within dataset; across methods); (2) prognostic validity (prediction for 5-year all-cause mortality, hospitalization and new chronic diseases); and (3) medication burden.
RESULTS: Development: We identified four T2D subtypes: metabolic, early onset, late onset and cardiometabolic. Internal validity: Subtypes were predicted with high accuracy (F1 score >0.98). Prognostic validity: 5-year all-cause mortality, hospitalization, new chronic disease incidence and medication burden differed across T2D subtypes. Compared with the metabolic subtype, 5-year risks of mortality and hospitalization in incident T2D were highest in late-onset subtype (HR 1.95, 1.85-2.05 and 1.66, 1.58-1.75) and lowest in early-onset subtype (1.18, 1.11-1.27 and 0.85, 0.80-0.90). Incidence of chronic diseases was highest in late-onset subtype and lowest in early-onset subtype. Medications: Compared with the metabolic subtype, after adjusting for age, sex, and pre-T2D medications, late-onset subtype (1.31, 1.28-1.35) and early-onset subtype (0.83, 0.81-0.85) were most and least likely, respectively, to be prescribed medications within 5 years following T2D onset.
CONCLUSIONS: In the largest study using ML to date in incident T2D, we identified four distinct subtypes, with potential future implications for etiology, therapeutics, and risk prediction.