The Ophthalmological Center of the Federal Medical and Biological Agency of the Russian Federation.
Federal Research Center for Chemical Physics RAS.
J Glaucoma. 2023 Jun 1;32(6):e43-e55. doi: 10.1097/IJG.0000000000002145. Epub 2022 Nov 28.
Treatment strategy of primary angle closure (PAC) is not clear due to the large number of clinical and anatomic-topographic parameters in PAC, influencing the treatment algorithm. Using the machine learning method DD-SIMCA, we justify the expediency of early lens extraction (LE) in PAC.
To compare the anatomic and functional efficacy of LE and laser peripheral iridotomy (LPI) in patients with PAC using Machine Learning.
This prospective study included 120 patients aged 41-80 years: 60 eyes with PAC, 30 with PAC suspects, and 30 with healthy eyes (control). Thirty PAC eyes with intraocular pressure (IOP) up to 30 mm Hg were treated using LE with intraocular lens implantation and 30 eyes with LPI. All subjects underwent Swept Source optical coherence tomography. We analyzed 35 parameters of each eye including the lens vault, the choroidal thickness, the anterior chamber angle, and iris specifications such as iris curvature. Considering the correlations between them, the machine learning method DD-SIMCA 1-class classification was applied: the proximity of each sample to the target class (control) was characterized by the total distance to it.
After LE, IOP was significantly lower than after LPI ( P =0). Every third eye with PAC after LE reached the target class: specificity according to DD-SIMCA equals 0.67. This was not observed for the eyes after LPI: specificity equals 1.0. After LE, all parameters of the anterior chamber angle did not differ from the control (all P >0.05). After LPI, there was an increase in anterior chamber depth ( P =0) and a decrease in lens vault ( P =0), but results comparable to the control were achieved only for iris curvature ( P =1.000).
The efficacy of LE in PAC is higher than LPI due to the better postoperative anterior chamber topography and lower IOP. This study lends further clinical and anatomic support to the emerging notion of LE as an effective treatment for PAC.
由于原发性闭角型青光眼(PAC)有大量的临床和解剖-拓扑参数,影响治疗方案,因此其治疗策略尚不明确。本研究采用机器学习方法 DD-SIMCA,验证早期晶状体抽吸术(LE)治疗 PAC 的优势。
利用机器学习比较 LE 和激光周边虹膜切除术(LPI)治疗 PAC 的解剖和功能效果。
本前瞻性研究纳入了 120 名年龄在 41-80 岁的患者:60 只眼为 PAC,30 只为 PAC 疑似患者,30 只为健康眼(对照组)。30 只眼压(IOP)不超过 30mmHg 的 PAC 眼采用 LE 联合人工晶状体植入治疗,30 只眼采用 LPI。所有患者均行扫频源光学相干断层扫描。我们分析了每只眼的 35 个参数,包括晶状体拱高、脉络膜厚度、前房角和虹膜曲率等虹膜特征。考虑到它们之间的相关性,应用机器学习方法 DD-SIMCA 1 类分类:通过到目标类(对照组)的总距离来描述每个样本与目标类的接近程度。
LE 后 IOP 明显低于 LPI( P =0)。每 3 只 LE 治疗的 PAC 眼中有 1 只达到目标类:DD-SIMCA 的特异性为 0.67。LPI 后未观察到这种情况:特异性为 1.0。LE 后,前房角的所有参数均与对照组无差异(均 P >0.05)。LPI 后,前房深度增加( P =0),晶状体拱高降低( P =0),但仅虹膜曲率达到与对照组相当的结果( P =1.000)。
LE 治疗 PAC 的效果优于 LPI,因为术后前房形态更好,IOP 更低。本研究为 LE 作为 PAC 有效治疗方法的新观点提供了进一步的临床和解剖学支持。