It is a pretrained NER deep learning model for detecting clinical events in medical text, i.e. it can be used to predict DATE, TIME, PROBLEM, TEST, TREATMENT, OCCURENCE, CLINICAL_DEPT, EVIDENTIAL, DURATION, FREQUENCY, ADMISSION and DISCHARGE. It uses Bidirectional LSTM ad its base and is compatible with Spark NLP for Healthcare versions 3.0.0+.The model is trained on i2b2 events data with clinical_embeddings. The macro averaged f1 score for the model is 70.4%, while the micro averaged f1 score is 80.9%.
Input variables : Clinical text
Output Variables : DATE, TIME, PROBLEM, TEST, TREATMENT, OCCURENCE, CLINICAL_DEPT, EVIDENTIAL, DURATION, FREQUENCY, ADMISSION, DISCHARGE.
| 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 |
| 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 : nlp.johnsnowlabs.com
| Model Category | : | Commercial |
| Date Published | : | March, 2021 |
| Healthcare Domain | : |
Payer
Provider |
| Code | : | colab.research.google.com |
| Clinical Information Extraction |