Readmission is an adverse outcome observed among some critically ill patients.In this model we predict the risk of patient readmission based on the Medical records. Patients at high risk of readmission can be carefully evaluated and steps can be taken to avoid possible readmission.The dataset used in the model is MIMIC-III and features like patient Demographics, Diagnoses, procedures, medications, and vital signs were used for prediction.Recurrnet Neural networks shows higher accuracy but Attention based networks can be used to get easily interpretable output.
Input variables : Patient Demographics, ICD-9 Diagnoses, ICD-9 Procedures , Medications, Vital signs
Output Variables : Readmission Risk
| 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 : nature.com
| Model Category | : | Public |
| Date Published | : | January, 2020 |
| Healthcare Domain | : | Provider |
| Code | : | github.com |
| Utilization Management |
| ED Admission |