开发与评估用于设定青光眼目标眼压的人工智能模型
本研究开发人工智能模型为青光眼眼设定个体化目标眼压,在14,871眼数据集上训练测试,预测平均绝对误差2.28 mmHg;在10,559眼进展数据集中,AI与临床医生目标眼压偏差对视野恶化影响相似,均大于加拿大眼科学会指南目标及平均绝对眼压的影响。
要点
- AI模型预测目标眼压平均绝对误差2.28 mmHg。
- AI与临床医生目标偏差对视野恶化影响相似(0.032 vs 0.026 dB/年,p=0.09)。
- AI与临床医生目标偏差影响大于COS指南目标(0.011 dB/年,p<0.001)及平均绝对眼压(0.001 dB/年,p<0.001)。
核心结论
- AI模型设定目标眼压的性能与青光眼专家相当,优于使用平均眼压或基于学会指南设定目标。
- 需要进一步研究评估AI目标眼压指导对非青光眼专家管理患者的临床影响。
研究设计与样本
- 人工智能治疗算法的开发与评估。
- 训练测试数据集为14,871眼,均有定义的目标眼压(由青光眼专家在常规临床诊疗中设定)及基线OCT、视野和临床测量。
- 进展数据集为10,559眼,与训练集不重叠,具有纵向视野测试(至少5次可靠测试)。
- 在具有基线结构、功能和临床数据的数据集上训练和测试机器学习模型,为进展数据集中每只眼预测目标眼压。
- 线性模型估计平均目标差(测量眼压减目标眼压)对视野恶化速率(以平均偏差斜率定义)的影响,并比较AI、临床医生和加拿大眼科学会指南目标偏差的影响;线性模型也估计平均绝对眼压对视野恶化速率的影响。
主要发现
- AI模型预测目标眼压的平均绝对误差为2.28 mmHg。
- 平均目标差每增加1 mmHg,AI目标差对应平均偏差恶化速率加快0.032 dB/年,临床医生目标差对应加快0.026 dB/年,两者相似(p=0.09)。
- 平均目标差每增加1 mmHg,AI和临床医生目标差的影响大于加拿大眼科学会目标差(加快0.011 dB/年,p<0.001)和平均绝对眼压(加快0.001 dB/年,p<0.001)。
临床怎么用
- 原文未据此给出推荐。
局限性
- 需要进一步研究评估AI目标眼压指导对非青光眼专家管理患者的临床影响。
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
PURPOSE: Develop an artificial intelligence (AI) model to predict a personalized target intraocular pressure (IOP) for eyes with glaucoma. Compare the impact of achieving the AI-predicted, clinician-defined, and society guideline-based target IOP on rates of visual field (VF) worsening. DESIGN: Development and evaluation of an AI treatment algorithm SUBJECTS: A dataset of 14,871 eyes with a defined target IOP (set by glaucoma specialists during routine clinical care) and baseline OCT, VF, and clinical measurements. A non-overlapping progression dataset of 10,559 eyes with longitudinal VF testing (≥ 5 reliable tests). METHODS: We trained and tested a machine-learning model on the dataset of eyes with baseline structural, functional, and clinical data to predict a target IOP for each eye in the progression dataset. Linear models estimated the effect of mean target difference (measured IOP - target IOP) on the rate of VF worsening, defined by mean deviation (MD) slope. The effect of deviations from AI targets was compared to deviations from clinician-set targets and targets from society-based guidelines by the Canadian Ophthalmological Society (COS). Linear models also estimated the effect of mean absolute IOP on the rate of VF worsening. The effect of mean target difference (AI, clinician, or COS) was compared to the effect of mean absolute IOP. MAIN OUTCOME MEASURES: Effect of 1 mm Hg increase in mean target difference (AI, clinician, or COS) on the rate of MD worsening (dB/year). RESULTS: The AI model achieved a mean absolute error of 2.28 mm Hg for predicting target IOP. AI and clinician target differences had similar effects on VF outcomes (0.032 dB/year vs 0.026 dB/year faster rate of MD worsening per 1 mm Hg increase, respectively, p = 0.09). AI and clinician target difference had greater effects than COS target difference (0.011 dB/year faster per 1 mm Hg increase, p < 0.001) and mean absolute IOP (0.001 dB/year faster per 1 mm Hg increase, p < 0.001). CONCLUSIONS: AI models can set target IOP with comparable performance to glaucoma specialists and are superior to utilizing mean IOP or society-based guidelines to set targets. Further work is needed to assess the clinical impact of AI-based target IOP guidance for patients managed by non-glaucoma specialists.
引用
- Pham A, Robitaille E, Bradley C, et al. Development and Evaluation of an Artificial Intelligence Model to Set Target IOP for Glaucoma. Am J Ophthalmol. 2025. PMID: 40850449. doi:10.1016/j.ajo.2025.08.046
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。