Human-machine partnership with artificial intelligence for chest radiograph diagnosis
Human-machine partnership with artificial intelligence for chest radiograph diagnosis
复制标题
DOI：
10.1038/s41746-019-0189-7
复制
发表时间：
2019-11-18
影响因子：
15.2
通讯作者：
Lungren, Matthew
中科院分区：
文献类型：
--
作者：
Patel, Bhavik N.;Rosenberg, Louis;Lungren, Matthew
人在回路（HITL）人工智能可以实现人类专家和人工智能模型的理想共生，利用两者的优势，同时克服各自的局限性。本研究的目的是研究一种新的集体智能技术，旨在通过形成以生物群为模型的实时系统来放大网络人类群体的诊断准确性。使用小组放射科医生，将基于群的技术应用于胸部X光片上的肺炎诊断，并与单独的人类专家以及两种最先进的深度学习AI模型进行比较。我们的工作表明，基于群体的技术和深度学习技术都比人类专家单独实现了上级诊断准确性。我们的工作进一步证明，当组合使用时，基于群的技术和深度学习技术的性能优于单独使用的任何一种方法。与放射科医师和单独的AI相比，组合的HITL AI解决方案的上级诊断准确性对未来实践中激增的临床AI部署和实施策略具有广泛的影响。
Human-in-the-loop (HITL) Al may enable an ideal symbiosis of human experts and Al models, harnessing the advantages of both while at the same time overcoming their respective limitations. The purpose of this study was to investigate a novel collective intelligence technology designed to amplify the diagnostic accuracy of networked human groups by forming real-time systems modeled on biological swarms. Using small groups of radiologists, the swarm-based technology was applied to the diagnosis of pneumonia on chest radiographs and compared against human experts alone, as well as two state-of-the-art deep learning Al models. Our work demonstrates that both the swarm-based technology and deep-learning technology achieved superior diagnostic accuracy than the human experts alone. Our work further demonstrates that when used in combination, the swarm-based technology and deep-learning technology outperformed either method alone. The superior diagnostic accuracy of the combined HITL Al solution compared to radiologists and Al alone has broad implications for the surging clinical Al deployment and implementation strategies in future practice.