文献速递眼底病与葡萄膜炎角膜与眼表疾病眼外伤

EE-Explorer:用于眼科急诊分诊与初步诊断的多模态人工智能系统

EE-Explorer: A Multimodal Artificial Intelligence System for Eye Emergency Triage and Primary Diagnosis.
PubMed 文献 · Am J Ophthalmol · 2023-05-02

本研究开发了多模态人工智能系统EE-Explorer,利用手机采集的元数据和眼表图像进行眼科急诊分诊(紧急、半紧急、非紧急),并利用配对元数据和裂隙灯图像进行初步诊断。分诊模型AUC为0.982(95% CI 0.966-0.998),优于分诊护士(P < .001);初步诊断模型内部测试分类准确率0.808(95% CI 0.776-0.840),外部测试分诊平均AUC 0.988(95% CI 0.967-1.000)。在广州的试点测试中,该系统在分级转诊模式下表现稳健且接受度高。

要点

  • 分诊模型基于2038例患者的元数据和智能手机眼表图像开发,输出紧急、半紧急、非紧急三类,AUC 0.982。
  • 初步诊断模型基于2405例患者的配对元数据和裂隙灯图像开发,内部测试分类准确率0.808,汉明损失0.016。
  • 外部测试纳入4家其他医院的103名参与者,分诊平均AUC 0.988,初步诊断分类准确率0.718。

核心结论

  • EE-Explorer系统在眼科急诊患者的分诊和初步诊断中均表现出稳健的性能。
  • EE-Explorer可为有急性眼部症状的患者提供远程自我分诊,并在非专科医疗机构辅助初步诊断,以实现快速有效的治疗策略。

研究设计与样本

  • 诊断性、横断面、效度和信度研究。
  • 分诊模型基于中山眼科中心2038例患者的元数据(事件、症状、病史)和智能手机眼表图像开发,输出紧急、半紧急、非紧急三类分类。
  • 初步诊断模型基于中山眼科中心2405例患者的配对元数据和裂隙灯图像开发。
  • 两个模型均在来自4家其他医院的103名参与者中进行外部测试。
  • 在广州开展试点测试,评估EE-Explorer辅助非专科医疗机构的分级转诊服务模式。

主要发现

  • 分诊模型总体AUC为0.982(95% CI 0.966-0.998),优于分诊护士(P < .001)。
  • 初步诊断模型内部测试诊断分类准确率为0.808(95% CI 0.776-0.840),汉明损失为0.016(95% CI 0.006-0.026)。
  • 外部测试中,分诊模型平均AUC为0.988(95% CI 0.967-1.000),初步诊断模型分类准确率为0.718(95% CI 0.644-0.792),汉明损失为0.023(95% CI 0.000-0.048)。
  • 在广州分级转诊设置下的试点测试中,EE-Explorer表现出持续稳健的性能和广泛的参与者接受度。

临床怎么用

  • 原文结论指出,EE-Explorer可为有急性眼部症状的患者提供远程自我分诊,并在非专科医疗机构辅助初步诊断,以实现快速有效的治疗策略。

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

PURPOSE: To develop a multimodal artificial intelligence (AI) system, EE-Explorer, to triage eye emergencies and assist in primary diagnosis using metadata and ocular images. DESIGN: A diagnostic, cross-sectional, validity and reliability study. METHODS: EE-Explorer consists of 2 models. The triage model was developed from metadata (events, symptoms, and medical history) and ocular surface images via smartphones from 2038 patients presenting to Zhongshan Ophthalmic Center (ZOC) to output 3 classifications: urgent, semiurgent, and nonurgent. The primary diagnostic model was developed from the paired metadata and slitlamp images of 2405 patients from ZOC. Both models were externally tested on 103 participants from 4 other hospitals. A pilot test was conducted in Guangzhou to evaluate the hierarchical referral service pattern assisted by EE-Explorer for unspecialized health care facilities. RESULTS: A high overall accuracy, as indicated by an area under the receiver operating characteristic curve (AUC) of 0.982 (95% CI, 0.966-0.998), was obtained using the triage model, which outperformed the triage nurses (P < .001). In the primary diagnostic model, the diagnostic classification accuracy (CA) and Hamming loss (HL) in the internal testing were 0.808 (95% CI 0.776-0.840) and 0.016 (95% CI 0.006-0.026), respectively. In the external testing, model performance was robust for both triage (average AUC, 0.988, 95% CI 0.967-1.000) and primary diagnosis (CA, 0.718, 95% CI 0.644-0.792; and HL, 0.023, 95% CI 0.000-0.048). In the pilot test in the hierarchical referral settings, EE-explorer demonstrated consistently robust performance and broad participant acceptance. CONCLUSION: The EE-Explorer system showed robust performance in both triage and primary diagnosis for ophthalmic emergency patients. EE-Explorer can provide patients with acute ophthalmic symptoms access to remote self-triage and assist in primary diagnosis in unspecialized health care facilities to achieve rapid and effective treatment strategies.

来源:Am J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Chen J, Wu X, Li M, et al. EE-Explorer: A Multimodal Artificial Intelligence System for Eye Emergency Triage and Primary Diagnosis. Am J Ophthalmol. 2023. PMID: 37142171. doi:10.1016/j.ajo.2023.04.007

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。