Ministry-of-Education Key Laboratory of Aerospace Medicine, School of Aerospace Medicine, Air Force Medical University, Xi'an, Shaanxi Province, China.
Qingdao Special Servicemen Recuperation Center of PLA Navy, Qingdao, Shandong Province, China.
BMC Ophthalmol. 2023 Jun 27;23(1):293. doi: 10.1186/s12886-023-03044-7.
To develop machine learning models for objectively evaluating visual acuity (VA) based on pattern-reversal visual evoked potentials (PRVEPs) and other related visual parameters.
Twenty-four volunteers were recruited and forty-eight eyes were divided into four groups of 1.0, 0.8, 0.6, and 0.4 (decimal vision). The relationship between VA, peak time, or amplitude of P100 recorded at 5.7°, 2.6°, 1°, 34', 15', and 7' check sizes were analyzed using repeated-measures analysis of variance. Correlations between VA and P100, contrast sensitivity (CS), refractive error, wavefront aberrations, and visual field were analyzed by rank correlation. Based on meaningful P100 peak time, P100 amplitude, and other related visual parameters, four machine learning algorithms and an ensemble classification algorithm were used to construct objective assessment models for VA. Receiver operating characteristic (ROC) curves were used to compare the efficacy of different models by repeated sampling comparisons and ten-fold cross-validation.
The main effects of P100 peak time and amplitude between different VA and check sizes were statistically significant (all P < 0.05). Except amplitude at 2.6° and 5.7°, VA was negatively correlated with peak time and positively correlated with amplitude. The peak time initially shortened with increasing check size and gradually lengthened after the minimum value was reached at 1°. At the 1° check size, there were statistically significant differences when comparing the peak times between the vision groups with each other (all P < 0.05), and the amplitudes of the vision reduction groups were significantly lower than that of the 1.0 vision group (all P < 0.01). The correlations between peak time, amplitude, and visual acuity were all highest at 1° (r = - 0.740, 0.438). VA positively correlated with CS and spherical equivalent (all P < 0.001). There was a negative correlation between VA and coma aberrations (P < 0.05). For different binarization classifications of VA, the classifier models with the best assessment efficacy all had the mean area under the ROC curves (AUC) above 0.95 for 500 replicate samples and above 0.84 for ten-fold cross-validation.
Machine learning models established by meaning visual parameters related to visual acuity can assist in the objective evaluation of VA.
开发基于图形翻转视觉诱发电位（PRVEP）和其他相关视觉参数的机器学习模型，以客观评估视力（VA）。
招募了 24 名志愿者，将 48 只眼分为 4 组，每组 1.0、0.8、0.6 和 0.4（十进制视力）。使用重复测量方差分析分析记录在 5.7°、2.6°、1°、34'、15'和 7'检查尺寸时 VA、P100 峰值时间或振幅之间的关系。通过秩相关分析 VA 与 P100、对比敏感度（CS）、屈光不正、波前像差和视野之间的相关性。基于有意义的 P100 峰值时间、P100 振幅和其他相关视觉参数，使用四种机器学习算法和集成分类算法构建 VA 的客观评估模型。通过重复采样比较和十折交叉验证，使用接收者操作特征（ROC）曲线比较不同模型的效果。
不同 VA 和检查尺寸之间的 P100 峰值时间和振幅的主要影响均具有统计学意义（均 P<0.05）。除了 2.6°和 5.7°处的振幅外，VA 与峰值时间呈负相关，与振幅呈正相关。随着检查尺寸的增加，峰值时间最初缩短，在达到 1°的最小值后逐渐延长。在 1°检查尺寸下，视力降低组之间的峰值时间比较存在统计学差异（均 P<0.05），且降低视力组的振幅明显低于 1.0 视力组（均 P<0.01）。峰值时间、振幅和视力之间的相关性在 1°时均最高（r=-0.740，0.438）。VA 与 CS 和等效球镜（均 P<0.001）呈正相关。VA 与彗差像差呈负相关（P<0.05）。对于 VA 的不同二值化分类，具有最佳评估效果的分类器模型在 500 个重复样本中均具有高于 0.95 的平均 ROC 曲线下面积（AUC），在十折交叉验证中具有高于 0.84 的 AUC。
通过与视力相关的有意义的视觉参数建立机器学习模型，可以辅助 VA 的客观评估。
