arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2307.08290cs.CL
收藏

CoAD:通过症状与疾病协同生成实现自动诊断

CoAD: Automatic Diagnosis through Symptom and Disease Collaborative Generation

The Chinese University of Hong Kong(香港中文大学);Tencent(腾讯)

Huimin Wang, Wai-Chung Kwan, Kam-Fai Wong, Yefeng Zheng

AI总结:

针对 Transformer 自动诊断中训练-生成症状不匹配及症状顺序影响问题,提出 CoAD 协同生成框架,通过标签对齐、扩展标注和重复输入实现平均 2.3% 的性能提升。

摘要:

自动诊断(AD)是人工智能在医疗保健中的一项关键应用,它采用机器学习技术协助医生收集患者症状信息,以实现精确的疾病诊断。基于 Transformer 的方法利用输入症状序列,通过自回归对其进行预测,并使用最后一个症状的隐藏状态来确定疾病。尽管该方法简单且已展现出优越性能,但仍观察到疾病诊断准确率下降,其原因包括:1)训练期间观察到的症状与生成时的症状之间存在不匹配;2)不同症状顺序对疾病预测产生影响。为克服上述障碍,我们提出 CoAD,这是一种新颖的疾病与症状协同生成框架,融合了若干关键创新以改进 AD:1)将句子级疾病标签与多个可能的症状询问步骤对齐,以弥合训练与生成之间的差距;2)为每个症状子序列扩展症状标签,以增强标注并消除症状顺序的影响;3)开发重复症状输入模式,以有效且高效地学习扩展后的疾病和症状标签。我们使用四个数据集评估 CoAD 框架,其中包括三个公开数据集和一个私有数据集,并证明其在自动疾病诊断方面相较先前最先进结果平均提升 2.3%。为便于复现,我们在 https://github.com/KwanWaiChung/coad 发布代码和数据。

英文摘要:

Automatic diagnosis (AD), a critical application of AI in healthcare, employs machine learning techniques to assist doctors in gathering patient symptom information for precise disease diagnosis. The Transformer-based method utilizes an input symptom sequence, predicts itself through auto-regression, and employs the hidden state of the final symptom to determine the disease. Despite its simplicity and superior performance demonstrated, a decline in disease diagnosis accuracy is observed caused by 1) a mismatch between symptoms observed during training and generation, and 2) the effect of different symptom orders on disease prediction. To address the above obstacles, we introduce the CoAD, a novel disease and symptom collaborative generation framework, which incorporates several key innovations to improve AD: 1) aligning sentence-level disease labels with multiple possible symptom inquiry steps to bridge the gap between training and generation; 2) expanding symptom labels for each sub-sequence of symptoms to enhance annotation and eliminate the effect of symptom order; 3) developing a repeated symptom input schema to effectively and efficiently learn the expanded disease and symptom labels. We evaluate the CoAD framework using four datasets, including three public and one private, and demonstrate that it achieves an average 2.3% improvement over previous state-of-the-art results in automatic disease diagnosis. For reproducibility, we release the code and data at https://github.com/KwanWaiChung/coad.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑