Lin Dan, Tian Lei, Zhang Shu, Wang Like, Jie Ying, Zhou Yongjin
Shenzhen University, Health Science Center, School of Biomedical Engineering, Xueyuan Avenue 1066, Shenzhen 518055, China.
Beijing Institute of Ophthalmology, Beijing Tongren Eye Center, Beijing Tongren Hospital, Capital Medical University, Beijing, China.
J Ophthalmol. 2020 Oct 28;2020:6530279. doi: 10.1155/2020/6530279. eCollection 2020.
Considering that intraocular pressure (IOP) is an important confounding factor in corneal biomechanical evaluation, the notion of matching IOP should be introduced to eliminate any potential bias. This study aimed to assess the capability of a novel parameter set (NPS) derived from IOP-matched scenario to diagnose keratoconus.
Seventy samples (training set; 35 keratoconus and 35 normal corneas; pairwise matching for IOP) were used to determine NPS by forward logistic regression. A large validation dataset comprising 62 matching samples (31 keratoconus and 31 normal corneas) and 203 unmatching samples (112 keratoconus and 91 normal corneas) was used to evaluate its clinical significance. To further assess its diagnosis capability, NPS was compared with the other two prior biomechanical indexes.
NPS was comprised of three biomechanical parameters, namely, DA Ratio Max 1 mm (DRM1), the first applanation time (AT1), and an energy loading parameter (Eload). NPS was successfully applied to the validation dataset, with a higher accuracy of 96.8% and 95.6% in the IOP-matched and -unmatched scenarios, respectively. More surprisingly, accuracy of NPS was 95.5% in the combined validation, an improvement compared to the two prior biomechanical indexes.
This is the first study taking IOP bias into consideration to determine a biomechanical parameter set. Our study shows that NPS indeed offers comparable performance in keratoconus diagnosis. . Determining a parameter set after eliminating the influence from IOP is useful in revealing the essential differences between keratoconus and normal corneas and possibly facilitating further progress in keratoconus diagnosis.
鉴于眼压（IOP）是角膜生物力学评估中的一个重要混杂因素，应引入眼压匹配的概念以消除任何潜在偏差。本研究旨在评估从眼压匹配场景中得出的一组新参数（NPS）诊断圆锥角膜的能力。
使用70个样本（训练集；35个圆锥角膜和35个正常角膜；眼压成对匹配）通过向前逻辑回归确定NPS。一个大型验证数据集包括62个匹配样本（31个圆锥角膜和31个正常角膜）和203个不匹配样本（112个圆锥角膜和91个正常角膜），用于评估其临床意义。为进一步评估其诊断能力，将NPS与其他两个先前的生物力学指标进行比较。
NPS由三个生物力学参数组成，即1毫米处的DA比率最大值（DRM1）、首次压平时间（AT1）和一个能量加载参数（Eload）。NPS成功应用于验证数据集，在眼压匹配和不匹配场景中的准确率分别为96.8%和95.6%。更令人惊讶的是，在联合验证中NPS的准确率为95.5%，与之前的两个生物力学指标相比有所提高。
这是第一项考虑眼压偏差来确定生物力学参数集的研究。我们的研究表明，NPS在圆锥角膜诊断中确实具有相当的性能。消除眼压影响后确定参数集有助于揭示圆锥角膜与正常角膜之间的本质差异，并可能推动圆锥角膜诊断取得进一步进展。
