利用机器学习预测新生血管性年龄相关性黄斑变性治疗患者的视力
这项数据库研究纳入653例(738眼)新生血管性AMD患者,用5种机器学习算法在首次3次抗VEGF注射后预测3个月和12个月视力,并与实际视力比较。3个月预测的平均绝对误差为0.11~0.18 logMAR,12个月为0.16~0.22 logMAR,表现最好的算法是Lasso。作者认为3个月预测结果与视力测量可靠性相当,12个月预测可能有助于鼓励患者坚持玻璃体腔治疗。
要点
- 3个月视力预测的平均绝对误差为0.11~0.18 logMAR(5.5~9个字母)。
- 12个月视力预测的平均绝对误差为0.16~0.22 logMAR(8~11个字母)。
- 5种算法中表现最好的是Lasso。
核心结论
- 机器学习可在首次3次抗VEGF注射后预测新生血管性AMD患者3个月和12个月视力。
- 3个月预测结果与视力测量可靠性相当。
- 12个月治疗后的视力预测可能有助于鼓励患者坚持玻璃体腔治疗。
研究设计与样本
- 数据库研究,纳入653例患者(379例女性)、738眼,平均年龄74.1岁,用于3个月视力预测。
- 其中456例患者(270例女性)、508眼有足够随访数据,用于12个月视力预测,平均年龄74.2岁。
- 采用AdaBoost.R2、Gradient Boosting、Random Forests、Extremely Randomized Trees和Lasso共5种机器学习算法进行预测。
- 临床数据特征来自包含电子病历的数据仓库(41个特征,如视力),OCT测量特征124个(如黄斑中心凹厚度)。
- 将被排除于机器学习之外的患者眼视力预测值与数据仓库记录的实际视力(真实值)进行比较。
主要发现
- 3个月视力预测:预测值与真实值的平均绝对误差为0.11 logMAR(5.5个字母)至0.18 logMAR(9个字母),均方根误差为0.14 logMAR(7个字母)至0.2 logMAR(10个字母)。
- 12个月视力预测:预测值与真实值的平均绝对误差为0.16 logMAR(8个字母)至0.22 logMAR(11个字母),均方根误差为0.2 logMAR(10个字母)至0.26 logMAR(13个字母)。
- 表现最好的算法是Lasso。
关键数值与推荐
- 3个月视力预测的平均绝对误差范围为0.11~0.18 logMAR,均方根误差范围为0.14~0.2 logMAR。
- 12个月视力预测的平均绝对误差范围为0.16~0.22 logMAR,均方根误差范围为0.2~0.26 logMAR。
- 首次注射前基线视力:3个月预测组为0.54 logMAR(±0.39),12个月预测组为0.56 logMAR(±0.42)。
临床怎么用
- 原文未据此给出临床推荐。
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: To predict, by using machine learning, visual acuity (VA) at 3 and 12 months in patients with neovascular age-related macular degeneration (AMD) after initial upload of 3 anti-vascular endothelial growth factor (VEGF) injections. DESIGN: Database study. PARTICIPANTS: For the 3-month VA forecast, 653 patients (379 female) with 738 eyes and an average age of 74.1 years were included. The baseline VA before the first injection was 0.54 logarithm of the minimum angle of resolution (logMAR) (±0.39). A total of 456 of these patients (270 female, 508 eyes, average age: 74.2 years) had sufficient follow-up data to be included for a 12-month VA prediction. The baseline VA before the first injection was 0.56 logMAR (±0.42). METHODS: Five different machine-learning algorithms (AdaBoost.R2, Gradient Boosting, Random Forests, Extremely Randomized Trees, and Lasso) were used to predict VA in patients with neovascular AMD after treatment with 3 anti-VEGF injections. Clinical data features came from a data warehouse (DW) containing electronic medical records (41 features, e.g., VA) and measurement features from OCT (124 features, e.g., central retinal thickness). The VA of patient eyes excluded from machine learning was predicted and compared with the ground truth, namely, the actual VA of these patients as recorded in the DW. MAIN OUTCOME MEASURES: Difference in logMAR VA after 3 and 12 months upload phase between prediction and ground truth as defined. RESULTS: For the 3-month VA forecast, the difference between the prediction and ground truth was between 0.11 logMAR (5.5 letters) mean absolute error (MAE)/0.14 logMAR (7 letters) root mean square error (RMSE) and 0.18 logMAR (9 letters) MAE/0.2 logMAR (10 letters) RMSE. For the 12-month VA forecast, the difference between the prediction and ground truth was between 0.16 logMAR (8 letters) MAE/0.2 logMAR (10 letters) RMSE and 0.22 logMAR (11 letters) MAE/0.26 logMAR (13 letters) RMSE. The best performing algorithm was the Lasso protocol. CONCLUSIONS: Machine learning allowed VA to be predicted for 3 months with a comparable result to VA measurement reliability. For a forecast after 12 months of therapy, VA prediction may help to encourage patients adhering to intravitreal therapy.
引用
- Rohm M, Tresp V, Müller M, et al. Predicting Visual Acuity by Using Machine Learning in Patients Treated for Neovascular Age-Related Macular Degeneration. Ophthalmology. 2018. PMID: 29454659. doi:10.1016/j.ophtha.2017.12.034
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。