Clinical notes are typically accompanied by medical codes, which describe the diagnosis and treatment. Model is developed for automatic ICD code assignment based on text discharge summaries from intensive care unit (ICU) stays. 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. To better adapt to the multi-label setting, employed a per-label attention mechanism, which allows model to learn distinct document representations for each label. Method is named as Convolutional Attention for Multi-Label classification (CAML).
Input variables : Clinical notes
Output Variables : ICD codes
| Statistical | : | Somers D | Accuracy | Precision and Recall | Confusion Matrix | F1 Score | Roc and Auc | Prevalence | Detection Rate | Balanced Accuracy | Cohen's Kappa | Concordance | Gini Coefficent | KS Statistic | Youden's J Index |
| Business | : | Population at High Risk of Disease | Risk by Geography | Risk by Demographics | Risk by Clinical Parameters |
| Infrastructure | : | Log Bytes | Logging/User/IAMPolicy | Logging/User/VPN | CPU Utilization | Memory Usage | Error Count | Prediction Count | Prediction Latencies | Private Endpoint Prediction Latencies | Private Endpoint Response Count |
Visit Model : github.com
Additional links : arxiv.org
| Model Category | : | Public |
| Date Published | : | December, 2019 |
| Healthcare Domain | : | Provider |
| Code | : | github.com |
| Clinical Information Extraction |
| Clinical Text Analysis |
| Disease Clinical Diagnosis and Treatment |
| Gaps in Care |
| Risk Progression |