Department of Clinical Epidemiology and Biostatistics, Faculty of Medicine Ramathibodi Hospital, Mahidol University, 270 Rama VI Road, Pyathai, Bangkok, 10400, Thailand.
Department of Epidemiology Biostatistics Population and Health Promotion, Faculty of Public Health, Airlangga University, Surabaya, Indonesia.
Syst Rev. 2021 Nov 1;10(1):288. doi: 10.1186/s13643-021-01841-z.
Many prognostic models of diabetic microvascular complications have been developed, but their performances still varies. Therefore, we conducted a systematic review and meta-analysis to summarise the performances of the existing models.
Prognostic models of diabetic microvascular complications were retrieved from PubMed and Scopus up to 31 December 2020. Studies were selected, if they developed or internally/externally validated models of any microvascular complication in type 2 diabetes (T2D).
In total, 71 studies were eligible, of which 32, 30 and 18 studies initially developed prognostic model for diabetic retinopathy (DR), chronic kidney disease (CKD) and end stage renal disease (ESRD) with the number of derived equations of 84, 96 and 51, respectively. Most models were derived-phases, some were internal and external validations. Common predictors were age, sex, HbA1c, diabetic duration, SBP and BMI. Traditional statistical models (i.e. Cox and logit regression) were mostly applied, otherwise machine learning. In cohorts, the discriminative performance in derived-logit was pooled with C statistics of 0.82 (0.73‑0.92) for DR and 0.78 (0.74‑0.83) for CKD. Pooled Cox regression yielded 0.75 (0.74‑0.77), 0.78 (0.74‑0.82) and 0.87 (0.84‑0.89) for DR, CKD and ESRD, respectively. External validation performances were sufficiently pooled with 0.81 (0.78‑0.83), 0.75 (0.67‑0.84) and 0.87 (0.85‑0.88) for DR, CKD and ESRD, respectively.
Several prognostic models were developed, but less were externally validated. A few studies derived the models by using appropriate methods and were satisfactory reported. More external validations and impact analyses are required before applying these models in clinical practice.
PROSPERO CRD42018105287.
已经开发出许多糖尿病微血管并发症的预后模型，但它们的性能仍存在差异。因此，我们进行了系统评价和荟萃分析，以总结现有模型的性能。
从 PubMed 和 Scopus 中检索到 2020 年 12 月 31 日之前的糖尿病微血管并发症预后模型。如果研究开发或内部/外部验证了 2 型糖尿病（T2D）任何微血管并发症的模型，则将其纳入研究。
共有 71 项研究符合条件，其中 32 项、30 项和 18 项研究分别最初开发了糖尿病视网膜病变（DR）、慢性肾脏病（CKD）和终末期肾病（ESRD）的预后模型，分别得到 84、96 和 51 个预测方程。大多数模型为推导阶段，部分为内部和外部验证。常见的预测因素包括年龄、性别、HbA1c、糖尿病病程、SBP 和 BMI。传统的统计模型（即 Cox 和对数回归）大多被应用，否则是机器学习。在队列中，推导-logit 的判别性能汇总为 C 统计量为 0.82（0.73-0.92）用于 DR 和 0.78（0.74-0.83）用于 CKD。汇总的 Cox 回归分别产生 0.75（0.74-0.77）、0.78（0.74-0.82）和 0.87（0.84-0.89）用于 DR、CKD 和 ESRD。外部验证性能也进行了充分的汇总，0.81（0.78-0.83）、0.75（0.67-0.84）和 0.87（0.85-0.88）分别用于 DR、CKD 和 ESRD。
已经开发出了几种预后模型，但很少有模型进行了外部验证。少数研究采用了适当的方法推导模型，并进行了满意的报告。在将这些模型应用于临床实践之前，需要进行更多的外部验证和影响分析。
PROSPERO CRD42018105287。
