Explainable Prediction of Medical Codes from Clinical Text
This work addresses the need for accurate and explainable medical code prediction in healthcare, reducing annotation effort and providing interpretability for clinicians, though it is incremental as it builds on existing neural network and attention techniques.
The paper tackles the problem of predicting medical codes from clinical text, which is labor-intensive and error-prone, by presenting an attentional convolutional network that achieves a precision@8 of 0.71 and a Micro-F1 of 0.54, outperforming prior state-of-the-art methods.
Clinical notes are text documents that are created by clinicians for each patient encounter. They are typically accompanied by medical codes, which describe the diagnosis and treatment. Annotating these codes is labor intensive and error prone; furthermore, the connection between the codes and the text is not annotated, obscuring the reasons and details behind specific diagnoses and treatments. We present an attentional convolutional network that predicts medical codes from clinical text. Our method aggregates information across the document using a convolutional neural network, and uses an attention mechanism to select the most relevant segments for each of the thousands of possible codes. The method is accurate, achieving precision@8 of 0.71 and a Micro-F1 of 0.54, which are both better than the prior state of the art. Furthermore, through an interpretability evaluation by a physician, we show that the attention mechanism identifies meaningful explanations for each code assignment