$\textbf{Objective}$ Develop an automatic diagnostic system which only uses
textual admission information from Electronic Health Records (EHRs) and assist
clinicians with a timely and statistically proved decision tool. The hope is
that the tool can be used to reduce mis-diagnosis.
$\textbf{Materials and Methods}$ We use the real-world clinical notes from
MIMIC-III, a freely available dataset consisting of clinical data of more than
forty thousand patients who stayed in intensive care units of the Beth Israel
Deaconess Medical Center between 2001 and 2012. We proposed a Convolutional
Neural Network model to learn semantic features from unstructured textual input
and automatically predict primary discharge diagnosis.
$\textbf{Results}$ The proposed model achieved an overall 96.11% accuracy and
80.48% weighted F1 score values on 10 most frequent disease classes,
significantly outperforming four strong baseline models by at least 12.7% in
weighted F1 score.
$\textbf{Discussion}$ Experimental results imply that the CNN model is
suitable for supporting diagnosis decision making in the presence of complex,
noisy and unstructured clinical data while at the same time using fewer layers
and parameters that other traditional Deep Network models.
$\textbf{Conclusion}$ Our model demonstrated capability of representing
complex medical meaningful features from unstructured clinical notes and
prediction power for commonly misdiagnosed frequent diseases. It can use easily
adopted in clinical setting to provide timely and statistically proved decision
support.
$\textbf{Keywords}$ Convolutional neural network, text classification,
discharge diagnosis prediction, admission information from EHRs.

本文针对采用电子病历的诊疗信息，提出卷积神经网络模型，从非结构化文本中丝毫不受噪声和复杂性影响地预测出患者的出院诊断，精确率和 F1 分数的性能均优于四个强基线模型，较常见疾病的预测成功率提高了至少 12.7% ，从而为医生诊断判断提供决策支持。