文献速递眼底病与葡萄膜炎

预测十年近视性黄斑病变风险:可解释机器学习算法的开发与验证

Forecasting Myopic Maculopathy Risk Over a Decade: Development and Validation of an Interpretable Machine Learning Algorithm.
PubMed 文献 · Invest Ophthalmol Vis Sci · 2024-01-01

本研究基于中山高度近视队列660例双眼球镜≤-6.00D、7至70岁患者开发预测模型,并用中国眼成像项目212例眼轴≥25.5mm者外部验证;中位随访10.9年,133例(20.2%)出现近视性黄斑变性进展。极端梯度提升算法在训练队列中AUROC为0.87±0.02,外部验证组(中位-5.38D)48例(22.6%)4年内进展,AUROC为0.80±0.008。

要点

  • 中位随访10.9年,开发队列133例(20.2%)出现近视性黄斑变性进展。
  • 前六位预测因素包括黄斑中心凹下脉络膜较薄、眼轴较长、最佳矫正视力较差、年龄较大、女性、前房深度较浅。
  • 极端梯度提升算法训练队列AUROC为0.87±0.02,外部验证组AUROC为0.80±0.008。

核心结论

  • 机器学习模型利用临床和影像指标可有效预测十年后近视性黄斑变性进展。
  • 该工具有望识别「高危」高度近视患者以便及时干预和保护视力。

研究设计与样本

  • 模型开发队列为中山高度近视队列,纳入660例双眼球镜≤-6.00D、年龄7至70岁患者。
  • 外部验证使用中国眼成像项目212例眼轴≥25.5mm参与者。
  • 分析34个临床变量,包括人口学、生活方式、近视史和扫频源光学相干断层扫描数据。
  • 采用序列前向选择筛选预测因子,使用五种机器学习算法建立二分类模型预测10年近视性黄斑变性进展风险。

主要发现

  • 开发队列中位随访10.9年,133例(20.2%)出现近视性黄斑变性进展。
  • 进展者中69例(51.9%)为新发近视性黄斑变性,11例(8.3%)由弥漫性萎缩发展为斑块状萎缩,54例(40.6%)病灶扩大,9例(6.8%)出现加号。
  • 前六位预测因素为黄斑中心凹下脉络膜较薄、眼轴较长、最佳矫正视力较差、年龄较大、女性、前房深度较浅。
  • 极端梯度提升算法在训练队列中判别性能最佳,AUROC为0.87±0.02,校准良好。
  • 外部验证组近视程度较轻(中位-5.38D),48例(22.6%)4年内出现近视性黄斑变性进展,模型AUROC验证为0.80±0.008。

临床怎么用

  • 原文结论指出该工具有望识别「高危」高度近视患者以便及时干预和保护视力。

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

PURPOSE: The purpose of this study was to develop and validate prediction model for myopic macular degeneration (MMD) progression in patients with high myopia. METHODS: The Zhongshan High Myopia Cohort for model development included 660 patients aged 7 to 70 years with a bilateral sphere of ≤-6.00 diopters (D). Two hundred twelve participants with an axial length (AL) ≥25.5 mm from the Chinese Ocular Imaging Project were used for external validation. Thirty-four clinical variables, including demographics, lifestyle, myopia history, and swept source optical coherence tomography data, were analyzed. Sequential forward selection was used for predictor selection, and binary classification models were created using five machine learning algorithms to forecast the risk of MMD progression over 10 years. RESULTS: Over a median follow-up of 10.9 years, 133 patients (20.2%) showed MMD progression in the development cohort. Among them, 69 (51.9%) developed newly-onset MMD, 11 (8.3%) developed patchy atrophy from diffuse atrophy, 54 (40.6%) showed an enlargement of lesions, and 9 (6.8%) developed plus signs. Top six predictors for MMD progression included thinner subfoveal choroidal thickness, longer AL, worse best-corrected visual acuity, older age, female gender, and shallower anterior chamber depth. The eXtreme Gradient Boosting algorithm yielded the best discriminative performance (area under the receiver operating characteristic curve [AUROC] = 0.87 ± 0.02) with good calibration in the training cohort. In a less myopic external validation group (median -5.38 D), 48 patients (22.6%) developed MMD progression over 4 years, with the model's AUROC validated at 0.80 ± 0.008. CONCLUSIONS: Machine learning model effectively predicts MMD progression a decade ahead using clinical and imaging indicators. This tool shows promise for identifying "at-risk" high myopes for timely intervention and vision protection.

来源:Invest Ophthalmol Vis Sci,查看原文。版权归原作者所有。

引用

  1. Chen Y, Yang S, Liu R, et al. Forecasting Myopic Maculopathy Risk Over a Decade: Development and Validation of an Interpretable Machine Learning Algorithm. Invest Ophthalmol Vis Sci. 2024. PMID: 38935031. doi:10.1167/iovs.65.6.40

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。