文献速递糖尿病

基于组学的机器学习方法预测糖尿病进展:一项RHAPSODY研究

An omics-based machine learning approach to predict diabetes progression: a RHAPSODY study.
PubMed 文献 · Diabetologia · 2024-02-19

在IMI-RHAPSODY项目的两个前瞻性队列中,研究采用lasso、ridge、GRridge和随机森林等机器学习方法,评估临床变量及代谢物、脂质、蛋白质三类分子标志物预测2型糖尿病患者需起始胰岛素治疗时间的能力。模型在Hoorn糖尿病照护系统队列开发并在GoDARTS队列验证,结果显示以临床变量为主的模型预测能力中等,加入分子标志物可使预后性能最多提升5%。

要点

  • 以临床变量为主的模型预测胰岛素需求风险的能力中等,DCS队列C统计量0.71,GoDARTS队列C统计量0.71。
  • 包含HDL-胆固醇和C肽的扩展模型在两个队列中表现更好,DCS队列C统计量0.74,GoDARTS队列C统计量0.73。
  • 乳脂肪球表皮生长因子8(lactadherin)和原癌基因酪氨酸蛋白激酶受体被最一致地筛选出,并轻微改善模型性能。

核心结论

  • 采用机器学习方法,胰岛素需求风险可被以临床变量为主的指标中等程度地预测,纳入分子标志物可使预后性能较临床变量提升最多5%。
  • 此类预后模型可能有助于识别进展至治疗强化风险较高的糖尿病患者。

研究设计与样本

  • 作为IMI-RHAPSODY项目的一部分,在两项前瞻性队列研究中开展。
  • 模型在Hoorn糖尿病照护系统(DCS)队列开发,并在Genetics of Diabetes Audit and Research in Tayside Scotland(GoDARTS)队列应用验证。
  • 采用lasso、ridge、GRridge和随机森林等不同机器学习方法预测需起始胰岛素治疗的时间。
  • 临床变量包括年龄、性别、HbA1c、HDL-胆固醇和C肽;模型分别以未惩罚临床变量(即始终无权重纳入模型)、惩罚临床变量或不含临床变量的方式运行。
  • 模型性能采用Harrel's C统计量评估。

主要发现

  • Hoorn DCS队列585例中69例在随访期间(1.0-11.4年)需起始胰岛素;GoDARTS队列571例中175例在随访期间(0.3-11.8年)需起始胰岛素。
  • 在不同模型中被选择最多的是临床变量和蛋白质,其次是代谢物。
  • 最常被选择的临床变量为HbA1c(36个模型中的18个,50%)、年龄(15个模型,41.2%)和C肽(15个模型,41.2%)。
  • 仅含临床变量的基础模型(年龄、性别、BMI、HbA1c)在DCS发现队列(C统计量0.71 [95% CI 0.64, 0.79])和GoDARTS重复队列(C统计量0.71 [95% CI 0.69, 0.75])中表现中等。
  • 包含HDL-胆固醇和C肽的扩展模型在两个队列中表现更好(DCS队列C统计量0.74 [95% CI 0.67, 0.81];GoDARTS队列C统计量0.73 [95% CI 0.69, 0.77])。

关键数值与推荐

  • 基础模型(年龄、性别、BMI、HbA1c)在DCS队列的C统计量为0.71(95% CI 0.64, 0.79),在GoDARTS队列为0.71(95% CI 0.69, 0.75)。
  • 包含HDL-胆固醇和C肽的扩展模型在DCS队列的C统计量为0.74(95% CI 0.67, 0.81),在GoDARTS队列为0.73(95% CI 0.69, 0.77)。
  • 分子标志物的纳入使预后性能较临床变量提升最多5%。
  • Hoorn DCS队列585例中69例需起始胰岛素,随访时间1.0-11.4年;GoDARTS队列571例中175例需起始胰岛素,随访时间0.3-11.8年。

临床怎么用

  • 作者认为,此类预后模型可能有助于识别进展至治疗强化风险较高的糖尿病患者。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

AIMS/HYPOTHESIS: People with type 2 diabetes are heterogeneous in their disease trajectory, with some progressing more quickly to insulin initiation than others. Although classical biomarkers such as age, HbA1c and diabetes duration are associated with glycaemic progression, it is unclear how well such variables predict insulin initiation or requirement and whether newly identified markers have added predictive value. METHODS: In two prospective cohort studies as part of IMI-RHAPSODY, we investigated whether clinical variables and three types of molecular markers (metabolites, lipids, proteins) can predict time to insulin requirement using different machine learning approaches (lasso, ridge, GRridge, random forest). Clinical variables included age, sex, HbA1c, HDL-cholesterol and C-peptide. Models were run with unpenalised clinical variables (i.e. always included in the model without weights) or penalised clinical variables, or without clinical variables. Model development was performed in one cohort and the model was applied in a second cohort. Model performance was evaluated using Harrel's C statistic. RESULTS: Of the 585 individuals from the Hoorn Diabetes Care System (DCS) cohort, 69 required insulin during follow-up (1.0-11.4 years); of the 571 individuals in the Genetics of Diabetes Audit and Research in Tayside Scotland (GoDARTS) cohort, 175 required insulin during follow-up (0.3-11.8 years). Overall, the clinical variables and proteins were selected in the different models most often, followed by the metabolites. The most frequently selected clinical variables were HbA1c (18 of the 36 models, 50%), age (15 models, 41.2%) and C-peptide (15 models, 41.2%). Base models (age, sex, BMI, HbA1c) including only clinical variables performed moderately in both the DCS discovery cohort (C statistic 0.71 [95% CI 0.64, 0.79]) and the GoDARTS replication cohort (C 0.71 [95% CI 0.69, 0.75]). A more extensive model including HDL-cholesterol and C-peptide performed better in both cohorts (DCS, C 0.74 [95% CI 0.67, 0.81]; GoDARTS, C 0.73 [95% CI 0.69, 0.77]). Two proteins, lactadherin and proto-oncogene tyrosine-protein kinase receptor, were most consistently selected and slightly improved model performance. CONCLUSIONS/INTERPRETATION: Using machine learning approaches, we show that insulin requirement risk can be modestly well predicted by predominantly clinical variables. Inclusion of molecular markers improves the prognostic performance beyond that of clinical variables by up to 5%. Such prognostic models could be useful for identifying people with diabetes at high risk of progressing quickly to treatment intensification. DATA AVAILABILITY: Summary statistics of lipidomic, proteomic and metabolomic data are available from a Shiny dashboard at https://rhapdata-app.vital-it.ch .

来源:Diabetologia,查看原文。版权归原作者所有。

引用

  1. Slieker RC, Münch M, Donnelly LA, et al. An omics-based machine learning approach to predict diabetes progression: a RHAPSODY study. Diabetologia. 2024. PMID: 38374450. doi:10.1007/s00125-024-06105-8

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。