机器学习预测晚期年龄相关性黄斑变性进展
该研究基于两项人群队列(鹿特丹研究I为训练集,ALIENOR为测试集),采用bootstrap LASSO生存分析构建综合预测模型,筛选出年龄、表型 predictor、49个SNP的遗传风险评分、吸烟、饮食质量、教育及脉压等预测因子,在训练集5年、10年、15年的AUC分别为0.92、0.92、0.91,测试集5年AUC为0.92,但模型在高风险组倾向于低估累积发病率。
要点
- 模型纳入年龄、表型、49个SNP遗传风险评分、吸烟、饮食、教育及脉压等预测因子。
- 训练集5年、10年、15年AUC分别为0.92、0.92、0.91,测试集5年AUC为0.92。
- 模型对高风险组的累积发病率倾向于低估,尤其在ALIENOR队列中。
核心结论
- 该预测模型对晚期年龄相关性黄斑变性(AMD)的发病达到较高的区分能力,为AMD精准医学的应用铺平道路。
研究设计与样本
- 两项基于人群的队列研究:鹿特丹研究I(RS-I)为训练集,纳入3838名55岁及以上参与者,中位随访10.8年,108例晚期AMD新发病例;ALIENOR研究为测试集,纳入362名73岁及以上参与者,中位随访6.5年,33例晚期AMD新发病例。
- 采用bootstrap LASSO生存分析方法在训练集中筛选最佳预测因子。
主要发现
- 预测模型保留了年龄、表型预测因子组合(基于中等玻璃膜疣、单眼或双眼色素沉着及AREDS简化评分)、基于49个单核苷酸多态性的遗传风险评分、吸烟、饮食质量、教育及脉压。
- RS-I交叉验证AUC:5年0.92(95%CI 0.88-0.97),10年0.92(95%CI 0.90-0.95),15年0.91(95%CI 0.88-0.94)。
- ALIENOR的5年AUC为0.92(95%CI 0.87-0.98)。
- 在校准方面,模型对高风险组的晚期AMD累积发病率倾向于低估,尤其在ALIENOR中。
关键数值与推荐
- 预测模型最终保留的预测因子包括年龄、中等玻璃膜疣及色素沉着等表型特征、49个SNP遗传风险评分、吸烟、饮食质量、教育和脉压。
- RS-I的5年AUC为0.92(95%CI 0.88-0.97),10年AUC为0.92(95%CI 0.90-0.95),15年AUC为0.91(95%CI 0.88-0.94);ALIENOR的5年AUC为0.92(95%CI 0.87-0.98)。
临床怎么用
- 该模型可用于综合评估个体进展为晚期AMD的风险,辅助识别高风险人群并支持精准医学决策。
- 临床应用中需注意模型对高风险组可能低估累积发病率,尤其在外部队列中应谨慎解读绝对风险。
局限性
- 模型在高风险组的校准欠佳,倾向于低估累积发病率,尤其在ALIENOR测试集中。
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
PURPOSE: Current prediction models for advanced age-related macular degeneration (AMD) are based on a restrictive set of risk factors. The objective of this study was to develop a comprehensive prediction model applying a machine learning algorithm allowing selection of the most predictive risk factors automatically. DESIGN: Two population-based cohort studies. PARTICIPANTS: The Rotterdam Study I (RS-I; training set) included 3838 participants 55 years of age or older, with a median follow-up period of 10.8 years, and 108 incident cases of advanced AMD. The Antioxydants, Lipids Essentiels, Nutrition et Maladies Oculaires (ALIENOR) study (test set) included 362 participants 73 years of age or older, with a median follow-up period of 6.5 years, and 33 incident cases of advanced AMD. METHODS: The prediction model used the bootstrap least absolute shrinkage and selection operator (LASSO) method for survival analysis to select the best predictors of incident advanced AMD in the training set. Predictive performance of the model was assessed using the area under the receiver operating characteristic curve (AUC). MAIN OUTCOME MEASURES: Incident advanced AMD (atrophic, neovascular, or both), based on standardized interpretation of retinal photographs. RESULTS: The prediction model retained (1) age, (2) a combination of phenotypic predictors (based on the presence of intermediate drusen, hyperpigmentation in one or both eyes, and Age-Related Eye Disease Study simplified score), (3) a summary genetic risk score based on 49 single nucleotide polymorphisms, (4) smoking, (5) diet quality, (6) education, and (7) pulse pressure. The cross-validated AUC estimation in RS-I was 0.92 (95% confidence interval [CI], 0.88-0.97) at 5 years, 0.92 (95% CI, 0.90-0.95) at 10 years, and 0.91 (95% CI, 0.88-0.94) at 15 years. In ALIENOR, the AUC reached 0.92 at 5 years (95% CI, 0.87-0.98). In terms of calibration, the model tended to underestimate the cumulative incidence of advanced AMD for the high-risk groups, especially in ALIENOR. CONCLUSIONS: This prediction model reached high discrimination abilities, paving the way toward making precision medicine for AMD patients a reality in the near future.
引用
- Ajana S, Cougnard-Grégoire A, Colijn JM, et al. Predicting Progression to Advanced Age-Related Macular Degeneration from Clinical, Genetic, and Lifestyle Factors Using Machine Learning. Ophthalmology. 2020. PMID: 32890546. doi:10.1016/j.ophtha.2020.08.031
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。