文献速递眼底病与葡萄膜炎小儿眼科与斜弱视

人工神经网络预测早产儿视网膜病变玻璃体腔注射与激光治疗后的视觉结局

Prediction of visual outcomes by an artificial neural network following intravitreal injection and laser therapy for retinopathy of prematurity.
PubMed 文献 · Br J Ophthalmol · 2019-11-19

本研究为回顾性研究,构建前馈人工神经网络(误差反向传播学习算法),基于60例有治疗史的早产儿视网膜病变(ROP)患儿的出生数据、治疗方式和随访年龄,预测3至12岁时的视力(VA)、最佳矫正视力(BCVA)和球镜等效(SE)。玻璃体腔注射(IVI)组VA、BCVA、SE的归一化平均RMSE分别为0.272、0.185、0.131,激光组分别为0.190、0.250、0.104;两组SE预测均优于VA和BCVA(p<0.001),激光组预测略优(p<0.001)。

要点

  • IVI组VA、BCVA、SE的归一化平均RMSE分别为0.272、0.185、0.131。
  • 激光组VA、BCVA、SE的归一化平均RMSE分别为0.190、0.250、0.104。
  • 两组SE预测均优于VA和BCVA(p<0.001),激光组预测略优(p<0.001)。

核心结论

  • 该算法对有治疗史的ROP患者视觉结局具有可接受的预测能力。
  • 两组中SE的预测均比VA和BCVA更精确。

研究设计与样本

  • 回顾性研究,采用前馈人工神经网络与误差反向传播学习算法。
  • 共纳入60例有既往治疗史的ROP婴儿,按既往治疗分为两组。
  • 基于患者出生数据、所接受治疗和随访时年龄预测视觉结局。
  • 主要结局指标为预测值与实际值之差,采用归一化均方根误差(RMSE)分析。
  • 采用双因素重复测量方差分析比较该算法的预测准确性。

主要发现

  • IVI组VA、BCVA、SE的归一化平均RMSE分别为0.272、0.185、0.131。
  • 激光组VA、BCVA、SE的归一化平均RMSE分别为0.190、0.250、0.104。
  • 两组中SE的预测能力均优于VA或BCVA(p<0.001)。
  • 该算法在激光组中预测视觉结局略优(p<0.001)。

关键数值与推荐

  • IVI组归一化平均RMSE:VA 0.272、BCVA 0.185、SE 0.131。
  • 激光组归一化平均RMSE:VA 0.190、BCVA 0.250、SE 0.104。
  • 两组SE预测优于VA或BCVA的差异有统计学意义(p<0.001)。
  • 激光组预测略优于IVI组的差异有统计学意义(p<0.001)。

临床怎么用

  • 原文未据此给出推荐。

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

AIMS: To construct a program to predict the visual acuity (VA), best corrected VA (BCVA) and spherical equivalent (SE) of patients with retinopathy of prematurity (ROP) from 3 to 12 years old after intravitreal injection (IVI) of anti-vascular endothelial growth factor and/or laser photocoagulation treatment. METHODS: This retrospective study employed a feedforward artificial neural network with an error backpropagation learning algorithm to predict visual outcomes based on patient birth data, treatment received and age at follow-up. Patients were divided into two groups based on prior treatments. The main outcome measures were the difference between the predicted and actual values of visual outcomes. These were analysed using the normalised root mean square error (RMSE). Two-way repeated measures analysis of variance was used to compare the predictive accuracy by this algorithm. RESULTS: A total of 60 ROP infants with prior treatments were included. In the IVI group, the normalised average RMSE for VA, BCVA, and SE was 0.272, 0.185 and 0.131, respectively. In the laser group, the normalised average RMSE for VA, BCVA and SE was 0.190, 0.250 and 0.104, respectively. This result shows that better predictive power was obtained for SE than for VA or BCVA in both the IVI and laser groups (p<0.001). In addition, the algorithm performed slightly better in predicting visual outcomes in the laser group (p<0.001). CONCLUSIONS: This algorithm offers acceptable power for predicting visual outcomes in patients with ROP with prior treatment. Predictions of SE were more precise than predictions of for VA and BCVA in both groups.

来源:Br J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Huang CY, Kuo RJ, Li CH, et al. Prediction of visual outcomes by an artificial neural network following intravitreal injection and laser therapy for retinopathy of prematurity. Br J Ophthalmol. 2019. PMID: 31744795. doi:10.1136/bjophthalmol-2019-314860

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。