Stroke is one of the leading causes of adult disability and mortality worldwide. Stroke reoccurrence is predominant in survivors. Complications like pneumonia, falls, UTIs are also very likely in patients with stroke and as a result readmission after stroke is observed in major proportions of stroke survivors. Hung et. al. have developed ML models for predicting readmission or mortality in patients admitted for TIA or stroke. This study identified factors like age, pre-stroke functional status, prior ED visits in one year, BMI, consciousness level and usage of nasogastric tube which are important in predicting the risk of mortality or readmission. The models can be useful in identifying patients with higher risk of mortality or readmission immediately after hospitalization.
Input variables : Patient demographic data, EHR features-initial vital signs, Laboratory results, Medical history and comorbidities
Output Variables : Combined outcome of readmission or mortality within 90 days after discharge from the index hospitalization
| 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 : osf.io
Additional links : mdpi.com
| Model Category | : | Public |
| Date Published | : | September, 2020 |
| Healthcare Domain | : | Provider |
| Code | : | osf.io |
| Health Risk Management |
| Utilization Management |
| ED Admission |
| Risk Progression |