文献速递眼底病与葡萄膜炎青光眼白内障与屈光手术

机器学习确定主要眼病可改变与不可改变危险因素的相对贡献

Machine learning to determine relative contribution of modifiable and non-modifiable risk factors of major eye diseases.
PubMed 文献 · Br J Ophthalmol · 2020-11-18

糖尿病病程对糖尿病视网膜病变贡献最高(RI=22.1%),遗传背景和年龄对年龄相关性黄斑变性贡献最大(RI约20%和约15%),眼轴对后囊下白内障贡献最高(RI=30.8%),社会经济因素对原发性闭角型青光眼贡献最高(20%)。原发性开角型青光眼是可改变因素累积贡献最高的眼病(累积RI约35%)。

要点

  • 糖尿病病程是糖尿病视网膜病变贡献最高的危险因素(RI=22.1%)。
  • 遗传背景和年龄分别是早晚期年龄相关性黄斑变性贡献最高的因素(RI约20%和约15%)。
  • 眼轴是后囊下白内障的主要危险因素(RI=30.8%),社会经济因素对原发性闭角型青光眼影响最高(20%)。

核心结论

  • 机器学习可识别对主要眼病风险贡献最高的因素。
  • 青光眼的可干预因素包括眼压和体重指数,非糖尿病性视网膜病变的可干预因素包括饮酒,糖尿病视网膜病变的可干预因素包括HbA1c水平。

研究设计与样本

  • 评估约100个可改变与不可改变危险因素,使用梯度提升机估计各因素的相对影响(RI)。

主要发现

  • 糖尿病视网膜病变贡献最高的因素为糖尿病病程(RI=22.1%)。
  • 非糖尿病性视网膜病变贡献最高的因素为饮酒(RI=6.4%)。
  • 早期和晚期年龄相关性黄斑变性贡献最高的因素为遗传背景(RI约20%)和年龄(RI约15%)。
  • 后囊下白内障贡献最高的因素为眼轴(RI=30.8%),原发性闭角型青光眼贡献最高的因素为社会经济因素(主要是教育水平,20%)。
  • 原发性开角型青光眼可改变因素累积RI约35%,原发性闭角型青光眼约30%,视网膜病变累积RI在20%至30%之间,晚期年龄相关性黄斑变性约20%。

关键数值与推荐

  • 糖尿病视网膜病变中糖尿病病程的RI=22.1%。
  • 非糖尿病性视网膜病变中饮酒的RI=6.4%。
  • 早期和晚期年龄相关性黄斑变性中遗传背景RI约20%、年龄RI约15%。
  • 后囊下白内障中眼轴RI=30.8%,原发性闭角型青光眼中社会经济因素RI=20%。
  • 原发性开角型青光眼可改变因素累积RI约35%,原发性闭角型青光眼约30%,视网膜病变累积RI 20%至30%,晚期年龄相关性黄斑变性约20%。

临床怎么用

  • 临床可优先关注眼压和体重指数以干预青光眼风险。
  • 对非糖尿病性视网膜病变患者可关注饮酒情况,对糖尿病视网膜病变患者可关注HbA1c水平。

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 use machine learning (ML) to determine the relative contributions of modifiable and non-modifiable clinical, metabolic, genetic, lifestyle and socioeconomic factors on the risk of major eye diseases. METHODS: We conducted analyses in a cross-sectional multi-ethnic population-based study (n=10 033 participants) and determined a range of modifiable and non-modifiable risk factors of common eye diseases, including diabetic retinopathy (DR), non-diabetic-related retinopathy (NDR); early and late age-related macular degeneration (AMD); nuclear, cortical and posterior subcapsular (PSC) cataract; and primary open-angle (POAG) and primary angle-closure glaucoma (PACG). Risk factors included individual characteristics, metabolic profiles, genetic background, lifestyle patterns and socioeconomic status (n~100 risk factors). We used gradient boosting machine to estimate the relative influence (RI) of each risk factor. RESULTS: Among the range of risk factors studied, the highest contributions were duration of diabetes for DR (RI=22.1%), and alcohol consumption for NDR (RI=6.4%). For early and late AMD, genetic background (RI~20%) and age (RI~15%) contributed the most. Axial length was the main risk factor of PSC (RI=30.8%). For PACG, socioeconomic factor (mainly educational level) had the highest influence (20%). POAG was the disease with the highest contribution of modifiable risk factors (cumulative RI~35%), followed by PACG (cumulative RI ~30%), retinopathy (cumulative RI between 20% and 30%) and late AMD (cumulative RI ~20%). CONCLUSION: This study illustrates the utility of ML in identifying factors with the highest contributions. Risk factors possibly amenable to interventions were intraocular pressure (IOP) and Body Mass Index (BMI) for glaucoma, alcohol consumption for NDR and levels of HbA1c for DR.

来源:Br J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Nusinovici S, Zhang L, Chai X, et al. Machine learning to determine relative contribution of modifiable and non-modifiable risk factors of major eye diseases. Br J Ophthalmol. 2020. PMID: 33208351. doi:10.1136/bjophthalmol-2020-317454

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。