Yu Gang, Yu Zhongzhi, Shi Yemin, Wang Yingshuo, Liu Xiaoqing, Li Zheming, Zhao Yonggen, Sun Fenglei, Yu Yizhou, Shu Qiang
Department of IT Center, The Children's Hospital, Zhejiang University School of Medicine, China; National Clinical Research Center for Child Health, China.
Deepwise AI Lab, Beijing, China.
J Biomed Inform. 2021 May;117:103754. doi: 10.1016/j.jbi.2021.103754. Epub 2021 Apr 6.
Respiratory diseases, including asthma, bronchitis, pneumonia, and upper respiratory tract infection (RTI), are among the most common diseases in clinics. The similarities among the symptoms of these diseases precludes prompt diagnosis upon the patients' arrival. In pediatrics, the patients' limited ability in expressing their situation makes precise diagnosis even harder. This becomes worse in primary hospitals, where the lack of medical imaging devices and the doctors' limited experience further increase the difficulty of distinguishing among similar diseases. In this paper, a pediatric fine-grained diagnosis-assistant system is proposed to provide prompt and precise diagnosis using solely clinical notes upon admission, which would assist clinicians without changing the diagnostic process. The proposed system consists of two stages: a test result structuralization stage and a disease identification stage. The first stage structuralizes test results by extracting relevant numerical values from clinical notes, and the disease identification stage provides a diagnosis based on text-form clinical notes and the structured data obtained from the first stage. A novel deep learning algorithm was developed for the disease identification stage, where techniques including adaptive feature infusion and multi-modal attentive fusion were introduced to fuse structured and text data together. Clinical notes from over 12000 patients with respiratory diseases were used to train a deep learning model, and clinical notes from a non-overlapping set of about 1800 patients were used to evaluate the performance of the trained model. The average precisions (AP) for pneumonia, RTI, bronchitis and asthma are 0.878, 0.857, 0.714, and 0.825, respectively, achieving a mean AP (mAP) of 0.819. These results demonstrate that our proposed fine-grained diagnosis-assistant system provides precise identification of the diseases.
呼吸系统疾病，包括哮喘、支气管炎、肺炎和上呼吸道感染（RTI），是临床上最常见的疾病之一。这些疾病症状相似，患者就诊时难以迅速确诊。在儿科，患者表达自身情况的能力有限，这使得准确诊断更加困难。在基层医院，这种情况更糟，那里缺乏医学影像设备，医生经验有限，进一步增加了区分相似疾病的难度。本文提出了一种儿科细粒度诊断辅助系统，仅使用入院时的临床记录即可提供快速准确的诊断，这将在不改变诊断流程的情况下协助临床医生。所提出的系统包括两个阶段：检测结果结构化阶段和疾病识别阶段。第一阶段通过从临床记录中提取相关数值来结构化检测结果，疾病识别阶段则根据文本形式的临床记录和从第一阶段获得的结构化数据进行诊断。针对疾病识别阶段开发了一种新颖的深度学习算法，引入了自适应特征注入和多模态注意力融合等技术，将结构化数据和文本数据融合在一起。使用来自12000多名呼吸系统疾病患者的临床记录来训练深度学习模型，并使用来自约1800名不重叠患者的临床记录来评估训练模型的性能。肺炎、RTI、支气管炎和哮喘的平均精度（AP）分别为0.878、0.857、0.714和0.825，平均AP（mAP）为0.819。这些结果表明，我们提出的细粒度诊断辅助系统能够准确识别疾病。
