文献速递角膜与眼表疾病

使用机器学习方法检测干眼患者自发瞬目模式

[Detection of the spontaneous blinking pattern of dry eye patients using the machine learning method].
PubMed 文献 · Zhonghua Yan Ke Za Zhi · 2022-01-01

横断面研究纳入北京同仁眼科中心干眼患者357例与健康对照152名,用UNet分割与ResNet分类模型分析瞬目视频。干眼组瞬目频率及不完全瞬目次数高于对照,完全瞬目次数低于对照,眼睑完全闭合期缩短,以Ⅱ型不完全瞬目和A型完全瞬目为主。

要点

  • 干眼组瞬目频率30(18,42)次/min高于对照组20(9,46)次/min(P=0.002)。
  • 干眼组不完全瞬目15(6,27)次/min高于对照3(0,10)次/min(P<0.001)。
  • 干眼组眼睑完全闭合期0.8 s短于对照1.3 s(P=0.006)。

核心结论

  • 干眼患者不完全瞬目次数增加、完全瞬目次数减少,眼睑完全闭合时间明显缩短。
  • 干眼患者瞬目模式以闭合幅度减少的Ⅱ型不完全瞬目及闭合时间缩短的A型完全瞬目为主。

研究设计与样本

  • 横断面研究,连续纳入2019年1至12月首都医科大学附属北京同仁眼科中心角膜病专科门诊干眼患者357例(男102例、女255例,年龄(46.2±13.3)岁)为干眼组。
  • 对照组为健康志愿者152名(男32名、女120名,年龄(48.1±13.9)岁)。
  • 所有参与者完成眼表疾病评分指数问卷、瞬目视频获取、泪膜破裂时间检查、角结膜荧光素染色及基础泪液分泌试验。
  • 采用UNet分割算法与ResNet分类算法建立模型分析瞬目视频单帧图片,获取睑裂高度百分比绘制瞬目波,分析完全瞬目(A、B、C型)与不完全瞬目(Ⅰ、Ⅱ、Ⅲ型)特征。
  • 使用独立样本t检验和Wilcoxon秩和检验分析两组差异的统计学意义。

主要发现

  • 分割模型与分类模型准确度分别为96.3%与96.0%,与人工分析的一致性为97.9%。
  • 干眼组瞬目频率30(18,42)次/min高于对照组20(9,46)次/min(U=18 132.50,P=0.002)。
  • 干眼组完全瞬目次数6(3,24)次/min低于对照组12(3,33)次/min(U=12 361.00,P=0.016),不完全瞬目次数15(6,27)次/min高于对照组3(0,10)次/min(U=22 839.00,P<0.001)。
  • 完全瞬目中干眼组A型占比53.7%(2 796/5 177)高于对照组39.3%(633/1 698)(χ²=101.83,P<0.001);不完全瞬目中干眼组Ⅱ型占比36.0%(2 334/6 477)高于对照组29.6%(126/426)(χ²=6.99,P=0.008)。
  • 干眼组眼睑完全闭合期0.8 s短于对照组1.3 s(U=16 291.50,P=0.006);平均瞬目间期、闭眼期、睁眼前期、睁眼末期与对照组差异均无统计学意义(均P>0.05)。

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

Objective: To establish a method to record the spontaneous blink pattern with a machine learning model, and to clarify the spontaneous blink pattern in patients with dry eye. Methods: It was a cross-setional study.We selected 357 dry eye patients (102 males and 255 females), aged (46.2±13.3) years, who visited corneal specialist clinics of Beijing Tongren Eye Center in 2019, as the dry eye group. The control group enrolled 152 normal controls, including 32 males and 120 females, aged (48.1±13.9) years. All participants completed the Ocular Surface Disease Index questionnaire, blink video capture, lipid layer thickness measurement, tear break-up time measurement, corneal fluorescein staining, and Schirmer Ⅱ test. Based on the assembled model built using UNet image segmentation algorithm and ResNet image classification algorithm, single frames of the blink video were analyzed, and then the palpebral opening height of each frame was obtained in order to establish a spontaneous blink wave. Finally, the characteristics of spontaneous blinks in dry eye patients were analyzed based on different types of complete blinks (types A, B and C) and partial blinks (types Ⅰ, Ⅱ and Ⅲ). Independent sample t test and Wilcoxon rank-sum test were used to judge if there was significant difference between the dry eye group and the normal group. Results: The accuracy of the segmentation model and the classification model was 96.3% and 96.0%, respectively, and the consistency with the manual analysis was 97.9%. In dry eye patients, the number of blinks was 30 (18, 42)/min, which was higher than that in normal controls [20 (9, 46)/min] (U=18 132.50, P=0.002). The number of complete blinks in dry eye cases was significantly lower than that in normal controls [6 (3, 24)/min vs. 12 (3,33)/min; U=12 361.00, P=0.016], and the number of partial blinks was significantly higher than that in normal controls [15 (6, 27)/min vs. 3 (0, 10)/min; U=22 839.00, P<0.001]. In complete blinks, the proportion of type A blinks in dry eye patients was significantly higher than that in normal controls [53.7% (2 796/5 177) vs. 39.3% (633/1 698); χ²=101.83, P<0.001]; in partial blinks, the proportion of type Ⅱ blinks in dry eye patients was significantly higher than that in normal controls [36.0%(2 334/6 477) vs. 29.6%(126/426); χ²=6.99, P=0.007]. The average interblink interval of dry eye patients was 1.2 s, which was not significantly different from that of normal controls (1.1 s; U=15 230.00, P=0.093). The eyelid closed phase of dry eye patients was 0.8 s, which was significantly shorter than that of normal controls (1.3 s; U=16 291.50, P=0.006). There were no significant differences in eyelid closing phase, early opening phase and late opening phase between the two groups (all P>0.05). Conclusions: In dry eye patients, the number of partial blinks increased, the number of complete blinks decreased, and the duration of eyelid closed phase shortened significantly. The main blink patterns of dry eye patients included type Ⅱ partial blinks with a reduced closure amplitude and type A complete blinks with a shortened closure time. 目的: 探讨干眼患者自发瞬目模式的特点。 方法: 横断面研究。连续纳入2019年1至12月在首都医科大学附属北京同仁眼科中心角膜病专科门诊就诊的干眼患者357例作为干眼组,其中男性102例,女性255例;年龄(46.2±13.3)岁;同时纳入健康志愿者152名作为对照组,其中男性32例,女性120例;年龄(48.1±13.9)岁。所有患者进行问卷调查眼表疾病评分指数、瞬目视频获取、泪膜破裂时间(BUT)检查、角结膜荧光素染色、基础泪液分泌试验。将瞬目视频的单帧图片输入UNet分割算法与ResNet分类算法建立的模型进行分析,获取睑裂高度百分比绘制瞬目波。将完全瞬目分为A、B、C型,不完全瞬目分为Ⅰ、Ⅱ、Ⅲ型,进而分析干眼患者的自发瞬目特征,并使用独立样本t检验和Wilcoxon秩和检验分析其与对照组差异的统计学意义。 结果: 本研究建立的分割模型与分类模型准确度分别为96.3%与96.0%,与人工分析的一致性为97.9%。干眼组患者瞬目频率为30(18,42)次/min,显著高于对照组的20(9,46)次/min(U=18 132.50,P=0.002),但完全瞬目次数为6(3,24)次/min,明显低于对照组的12(3,33)次/min(U=12 361.00,P=0.016),不完全瞬目次数为15(6,27)次/min,明显高于对照组的3(0,10)次/min(U=22 839.00,P<0.001)。完全瞬目中,干眼患者A型瞬目占比显著高于对照组[53.7%(2 796/5 177)和39.3%(633/1 698);χ²=101.83,P<0.001];不完全瞬目中,干眼患者Ⅱ型瞬目占比显著高于对照组[36.0%(2 334/6 477)和29.6%(126/426);χ²=6.99,P=0.008]。干眼患者平均瞬目间期为1.5 s,与对照组2.2 s比较,差异无统计学意义(U=15 230.00,P=0.093);干眼患者眼睑完全闭合期为0.8 s,明显短于对照组1.3 s(U=16 291.50,P=0.006)。闭眼期、睁眼前期、睁眼末期与对照组比较,差异均无统计学意义(均P>0.05)。 结论: 干眼患者不完全瞬目次数增加、完全瞬目次数减少,眼睑完全闭合时间明显缩短;其瞬目模式以闭合幅度减少的Ⅱ型不完全瞬目及闭合时间缩短的A型完全瞬目为主。.

来源:Zhonghua Yan Ke Za Zhi,查看原文。版权归原作者所有。

引用

  1. Zhang ZZ, Kuang RF, Wei ZY, et al. [Detection of the spontaneous blinking pattern of dry eye patients using the machine learning method]. Zhonghua Yan Ke Za Zhi. 2022. PMID: 35144352. doi:10.3760/cma.j.cn112142-20211110-00537

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。