Liu Yan, Zhang Yu, Wang Yuexin, Dong Ruilan, Chen Yueguo
Department of Ophthalmology, Peking University Third Hospital, 49 North Garden Road, Haidian District, Beijing 100191, China.
Beijing Key Laboratory of Restoration of Damaged Ocular Nerve, Peking University Third Hospital, Beijing 100191, China.
Diagnostics (Basel). 2024 Oct 17;14(20):2304. doi: 10.3390/diagnostics14202304.
This study aimed to evaluate the diagnostic accuracy of a novel shape index, the Pentacam Random Forest Index (PRFI), in detecting keratoconus (KC), specifically subclinical keratoconus, in Chinese refractive surgery candidates. This prospective cohort study included 856 participants who were divided into four groups based on their tomographic outcomes: the KC group ( = 137), the very asymmetric ectasia (VAE) group ( = 73), the normal cornea group ( = 363) and the tomographically suspected KC (TSK) group ( = 283). The diagnostic performance of PRFI and other widely used indices, including the shape index BAD-D and the combined index TBI, was assessed using receiver operating characteristic (ROC) curve analysis and compared using DeLong's test. The area under the curve (AUC), best cutoff values, and Youden index for each parameter are reported. Additionally, the false-positive rates of BAD-D and PRFI were calculated and compared in "normal corneas". All shape and biomechanical parameters collected in this study were found to be significantly different among the four groups (KC, VAE, TSK, and normal groups; = 0.000). The AUC of PRFI was the highest in detecting any form of KC (including clinical KC eyes and VAE-NT eyes) in Chinese refractive surgery candidates, outperforming the widely used shape index BAD-D (0.919 vs. 0.890, < 0.001). There was no significant difference in performance between the PRFI and the combined TBI index (0.919 vs. 0.916, > 0.05). For detecting subclinical KC eyes (i.e., VAE-NT), the AUC of PRFI was 0.774, which was statistically comparable to TBI (0.774 vs. 0.776, > 0.05), while outperforming BAD-D (0.774 vs. 0.684, < 0.001). The best cutoff values of PRFI for detecting any KC and VAE-NT eyes were determined to be 0.37 and 0.27, respectively. Additionally, PRFI demonstrated a lower false-positive rate than BAD-D (13.8% vs. 43.8%, < 0.001). Notably, the relatively high false-positive rate of BAD-D observed in this study might be attributed to the smaller horizontal corneal diameter in tomographically suspected eyes. The PRFI proved to be a superior shape index compared to BAD-D in detecting any form of keratoconus, including subclinical cases, in Chinese refractive surgery candidates. This finding may be attributed to the relatively small corneas commonly observed in Asians.
本研究旨在评估一种新型形状指数——Pentacam随机森林指数（PRFI）在中国屈光手术候选者中检测圆锥角膜（KC），特别是亚临床圆锥角膜的诊断准确性。这项前瞻性队列研究纳入了856名参与者，根据他们的断层扫描结果将其分为四组：KC组（n = 137）、极不对称扩张（VAE）组（n = 73）、正常角膜组（n = 363）和断层扫描疑似KC（TSK）组（n = 283）。使用受试者工作特征（ROC）曲线分析评估PRFI和其他广泛使用的指数（包括形状指数BAD - D和综合指数TBI）的诊断性能，并使用德龙检验进行比较。报告了每个参数的曲线下面积（AUC）、最佳截断值和尤登指数。此外，计算并比较了BAD - D和PRFI在“正常角膜”中的假阳性率。本研究收集的所有形状和生物力学参数在四组（KC组、VAE组、TSK组和正常组）之间均存在显著差异（P = 0.000）。在中国屈光手术候选者中，PRFI在检测任何形式的KC（包括临床KC眼和VAE - NT眼）方面的AUC最高，优于广泛使用的形状指数BAD - D（0.919对0.890，P < 0.001）。PRFI与综合TBI指数在性能上无显著差异（0.919对0.916，P > 0.05）。对于检测亚临床KC眼（即VAE - NT），PRFI的AUC为0.774，与TBI在统计学上相当（0.774对0.776，P > 0.05），同时优于BAD - D（0.774对0.684，P < 0.001）。检测任何KC和VAE - NT眼的PRFI最佳截断值分别确定为0.37和0.27。此外，PRFI的假阳性率低于BAD - D（13.8%对43.8%，P < 0.001）。值得注意的是，本研究中观察到的BAD - D相对较高的假阳性率可能归因于断层扫描疑似眼中较小的角膜水平直径。在检测中国屈光手术候选者中的任何形式的圆锥角膜（包括亚临床病例）方面，PRFI被证明是一种优于BAD - D的形状指数。这一发现可能归因于亚洲人常见的相对较小的角膜。
