Academic Journal
An explainable CNN approach for medical codes prediction from clinical text
| العنوان: | An explainable CNN approach for medical codes prediction from clinical text |
|---|---|
| المؤلفون: | Hu, Shuyuan, Teng, Fei, Huang, Lufei, Yan, Jun, Zhang, Haibo |
| المساهمون: | Fundamental Research Funds for the Central Universities, sichuan key r&d project |
| المصدر: | BMC Medical Informatics and Decision Making ; volume 21, issue S9 ; ISSN 1472-6947 |
| بيانات النشر: | Springer Science and Business Media LLC |
| سنة النشر: | 2021 |
| الوصف: | Background Clinical notes are unstructured text documents generated by clinicians during patient encounters, generally are annotated with International Classification of Diseases (ICD) codes, which give formatted information about the diagnosis and treatment. ICD code has shown its potentials in many fields, but manual coding is labor-intensive and error-prone, lead to researches of automatic coding. Two specific challenges of this task are (1) given an annotated clinical notes, the reasons behind specific diagnoses and treatments are implicit; (2) explainability is important for practical automatic coding method, the method should not only explain its prediction output but also have explainable internal mechanics. This study aims to develop an explainable CNN approach to address these two challenges. Method Our key idea is that for the automatic ICD coding task, the presence of informative snippets in the clinical text that correlated with each code plays an important role in the prediction of codes, and an informative snippet can be considered as a local and low-level feature. We infer that there exists a correspondence between a convolution filter and a local and low-level feature. Base on the inference, we come up with the Shallow and Wide Attention convolutional Mechanism (SWAM) to improve the CNN-based models’ ability to learn local and low-level features for each label. Results We evaluate our approach on MIMIC-III, an open-access dataset of ICU medical records. Our approach substantially outperforms previous results on top-50 medical code prediction on MIMIC-III dataset, the precision of the worst-performing 10% labels in previous works is increased from 0% to 53% on average. We attribute this improvement to SWAM, by which the wide architecture with attention mechanism gives the model ability to more extensively learn the unique features of different codes, and we prove it by an ablation experiment. Besides, we perform manual analysis of the performance imbalance between different codes, and ... |
| نوع الوثيقة: | article in journal/newspaper |
| اللغة: | English |
| DOI: | 10.1186/s12911-021-01615-6 |
| DOI: | 10.1186/s12911-021-01615-6.pdf |
| DOI: | 10.1186/s12911-021-01615-6/fulltext.html |
| الاتاحة: | http://dx.doi.org/10.1186/s12911-021-01615-6 https://link.springer.com/content/pdf/10.1186/s12911-021-01615-6.pdf https://link.springer.com/article/10.1186/s12911-021-01615-6/fulltext.html |
| Rights: | https://creativecommons.org/licenses/by/4.0 ; https://creativecommons.org/licenses/by/4.0 |
| رقم الانضمام: | edsbas.70E97B4 |
| قاعدة البيانات: | BASE |
| DOI: | 10.1186/s12911-021-01615-6 |
|---|