A Natural Language processing (NLP) model which uses clinical notes from Electronic Health Records(EHR) to predict misuse of opioids. This model compares prediction performance with and without Protected Health Information(PHI) Data. Data cohort for this model was inpatient encounters at a health system which was divided into positive and negative cases of opioid misuse. As clinical notes contain lot of sensitive information it is encoded into a standard medical vocabulary during modelling. Neural network based model is designed for the task of opioid misuse classification and compared against traditional methods.
Input variables : Clinical Notes from EHR related to Opioid misuse
Output Variables : Opioid Misuse
| 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 : github.com
Additional links : ncbi.nlm.nih.gov
| Model Category | : | Public |
| Date Published | : | April, 2020 |
| Healthcare Domain | : | Payer |
| Code | : | github.com |
| Member Experience |
| Behavioral Health |