利用基于机器学习的结构-功能关联评估地图样萎缩中视网膜敏感度丧失的进展(OMEGA 2)
研究纳入30例地图样萎缩患者(37眼),在基线及第12、24、48周进行微视野检查和SD-OCT,比较随机森林、LASSO回归和MARS模型预测视网膜敏感度的效果。随机森林模型在各场景中准确度最高,未知患者平均绝对误差为3.67 dB,已知患者随访时为2.96 dB,访视内插值为3.10 dB;推断的敏感度数据较观察数据显著降低变异性,残差方差为2.72 dB² vs 8.67 dB²。
要点
- 随机森林模型在未知患者、已知患者随访和访视内插值场景中均表现最高准确度。
- 推断的敏感度数据较观察数据显著降低纵向混合模型分析中的变异性。
- 推断的敏感度映射可作为临床试验的可靠功能替代终点,无需大量心理物理测试。
核心结论
- 机器学习模型尤其是随机森林模型能有效预测地图样萎缩患者的视网膜敏感度,患者特异性基线数据可提高后续访视的准确度。
- 推断的敏感度映射为临床试验提供了可靠的功能替代终点,具有高空间分辨率且无需大量心理物理测试。
研究设计与样本
- OMEGA研究纳入30例地图样萎缩(继发于年龄相关性黄斑变性)患者共37眼,在基线及第12、24、48周进行眼底控制视野检查(微视野)和频域光学相干断层扫描(SD-OCT)。
- 视网膜层使用自编深度学习算法分割,采用随机森林、LASSO回归和多变量自适应回归样条(MARS)等机器学习模型预测视网膜敏感度。
- 预测场景包括:未知患者、已知患者后续访视、访视内插值;用平均绝对误差(MAE)评估预测准确度,用线性混合模型分析模型降低测试变异性的能力。
主要发现
- 随机森林模型在所有场景中准确度最高,未知患者MAE为3.67分贝(dB),已知患者随访时为2.96 dB,访视内插值为3.10 dB。
- 纵向混合模型分析中,推断的敏感度数据较观察数据显著降低变异性,残差方差分别为2.72 dB² vs 8.67 dB²。
关键数值与推荐
- 随机森林模型未知患者MAE为3.67 dB,已知患者随访时MAE为2.96 dB,访视内插值MAE为3.10 dB。
- 推断敏感度数据残差方差为2.72 dB²,观察数据残差方差为8.67 dB²。
临床怎么用
- 原文未据此给出推荐。
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 evaluate the effectiveness of different machine-learning models in predicting retinal sensitivity in geographic atrophy (GA) secondary to age-related macular degeneration (AMD) and compare the progression of sensitivity loss using observed versus inferred data over time. METHODS: Thirty patients with GA (37 eyes) were recruited for the OMEGA study. Participants underwent fundus-controlled perimetry (microperimetry) and spectral-domain optical coherence tomography (SD-OCT) imaging at baseline and follow-up visits at weeks 12, 24, and 48. Retinal layers were segmented using a custom-written deep-learning algorithm. We used various machine-learning models, including random forest, LASSO regression, and multivariate adaptive regression splines (MARS), to predict retinal sensitivity across three scenarios: (1) unknown patients, (2) known patients at later visits, and (3) interpolation within visits. Predictive accuracy was evaluated using the mean absolute error (MAE), and the models' ability to reduce test variability over time was analyzed using linear mixed models. RESULTS: The random forest model demonstrated the highest accuracy across all scenarios, with an MAE of 3.67 decibels (dB) for unknown patients, 2.96 dB for known patients at follow-up, and 3.10 dB for within-visit interpolation. The inferred sensitivity data significantly reduced variability compared to the observed data in longitudinal mixed model analysis, with a residual variance of 2.72 dB² versus 8.67 dB², respectively. CONCLUSIONS: Machine-learning models, particularly the random forest model, effectively predict retinal sensitivity in patients with GA, with patient-specific baseline data improving accuracy for subsequent visits. Inferred sensitivity mapping presents a reliable, functional surrogate endpoint for clinical trials, offering high spatial resolution without extensive psychophysical testing.
引用
- Ansari G, Schärer N, Pfau K, et al. Evaluating the Progression of Retinal Sensitivity Loss in Geographic Atrophy Using Machine-Learning-Based Structure-Function Correlation (OMEGA 2). Invest Ophthalmol Vis Sci. 2025. PMID: 40801672. doi:10.1167/iovs.66.11.34
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。