文献速递青光眼

基于机器学习的智能手机眼压计的开发与验证

Development and validation of a machine learning, smartphone-based tonometer.
PubMed 文献 · Br J Ophthalmol · 2019-12-23

该研究在学术性青光眼门诊招募患者,比较原型智能手机眼压计与临床常用眼压计的测量值。共成功测量81名受试者的92只眼,智能手机眼压计与Goldmann压平眼压计(GAT)的平均差异为+0.24 mmHg,95%一致性界限为-4.35至4.83 mmHg,相关性最佳(R2=0.67,p<0.001)。结论认为该原型设备测得的眼压与参考标准大致相当。

要点

  • 智能手机眼压计与GAT平均差异+0.24 mmHg,95%一致性界限-4.35至4.83 mmHg。
  • 97.8%(90/92)的视频测量值在GAT±5 mmHg以内,63.0%(58/92)在±2 mmHg以内。
  • 与ICare、pneumotonometry和Tono-Pen相比,智能手机眼压计与GAT相关性最佳(R2=0.67,p<0.001)。

核心结论

  • 原型智能手机眼压计的初步眼压测量结果与参考标准GAT大致相当。

研究设计与样本

  • 从学术性青光眼门诊招募患者,比较智能手机眼压计与GAT、ICare、pneumotonometry及Tono-Pen的测量值。
  • 共成功测量81名受试者的92只眼,所有受试者均用GAT测量,部分患者另用ICare、pneumotonometry(坐位和仰卧位)及Tono-Pen(坐位和仰卧位)测量。

主要发现

  • 智能手机眼压计与GAT的平均差异为+0.24 mmHg,95%一致性界限为-4.35至4.83 mmHg。
  • 与ICare的平均差异为-1.39 mmHg,95%一致性界限为-6.48至3.70 mmHg。
  • 与pneumotonometry的平均差异为-3.71 mmHg,95%一致性界限为-7.66至-0.15 mmHg。
  • 与Tono-Pen的平均差异为-1.30 mmHg,95%一致性界限为-5.72至3.12 mmHg。
  • 智能手机眼压计与GAT相关性最佳(R2=0.67,p<0.001);92个视频中90个(97.8%)在GAT±5 mmHg以内,58个(63.0%)在±2 mmHg以内。

关键数值与推荐

  • 智能手机眼压计与GAT的平均差异+0.24 mmHg,95%一致性界限-4.35至4.83 mmHg。
  • 与ICare的平均差异-1.39 mmHg,95%一致性界限-6.48至3.70 mmHg。
  • 与pneumotonometry的平均差异-3.71 mmHg,95%一致性界限-7.66至-0.15 mmHg。
  • 与Tono-Pen的平均差异-1.30 mmHg,95%一致性界限-5.72至3.12 mmHg。
  • 与GAT相关性R2=0.67(p<0.001);97.8%测量在GAT±5 mmHg以内,63.0%在±2 mmHg以内。

临床怎么用

  • 该原型智能手机眼压计测得的眼压与GAT大致相当,可作为眼压测量的初步筛查或辅助工具。
  • 与pneumotonometry的一致性界限较宽且上限接近0 mmHg,提示两者测量值可能存在系统差异。

局限性

  • 本研究为原型设备的初步验证,样本来自单一学术性青光眼门诊,共81名受试者92只眼。
  • 仅部分患者使用ICare、pneumotonometry和Tono-Pen进行对比测量。

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

BACKGROUND/AIMS: To compare intraocular pressure (IOP) measurements using a prototype smartphone tonometer with other tonometers used in clinical practice. METHODS: Patients from an academic glaucoma practice were recruited. The smartphone tonometer uses fixed force applanation and in conjunction with a machine-learning computer algorithm is able to calculate the IOP. IOP was also measured using Goldmann applanation tonometry (GAT) in all subjects. A subset of patients were also measured using ICare, pneumotonometry (upright and supine positions) and Tono-Pen (upright and supine positions) and the results were compared. RESULTS: 92 eyes of 81 subjects were successfully measured. The mean difference (in mm Hg) for IOP measurements of the smartphone tonometer versus other devices was +0.24 mm Hg for GAT, -1.39 mm Hg for ICare, -3.71 mm Hg for pneumotonometry and -1.30 mm Hg for Tono-Pen. The 95% limits of agreement for the smartphone tonometer versus other devices was -4.35 to 4.83 mm Hg for GAT, -6.48 to 3.70 mm Hg for ICare, -7.66 to -0.15 mm Hg for pneumotonometry and -5.72 to 3.12 mm Hg for Tono-Pen. Overall, the smartphone tonometer results correlated best with GAT (R2=0.67, p<0.001). Of the 92 videos, 90 (97.8%) were within ±5 mm Hg of GAT and 58 (63.0%) were within ±2 mm Hg of GAT. CONCLUSIONS: Preliminary IOP measurements using a prototype smartphone-based tonometer was grossly equivalent to the reference standard.

来源:Br J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Wu Y, Luttrell I, Feng S, et al. Development and validation of a machine learning, smartphone-based tonometer. Br J Ophthalmol. 2019. PMID: 31871048. doi:10.1136/bjophthalmol-2019-315446

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。