Heart failure is a common event in Cardiovascular Diseases(CVD). Early detection and proper management can be a great help to people with CVD. Model states that Serum Creatinine and ejection fraction are the features which can predict heart failure alone. In the analysis several machine learning techniques are applied to data to predict the patient survival and rank the features associated with the risk factor. Features are ranked using traditional biostatistics tests as well and the results are compared with machine learning results. serum creatinine and ejection fraction are ranked most relevant by both the methods, hence model for heart failure prediction is built using these two factors alone.
Input variables : Gender, Smoking status, Diabetes status, BP, Anaemia, Age, Ejection fraction, Sodium, Creatinine, Platelets
Output Variables : Heart failure event
| 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 : bmcmedinformdecismak.biomedcentral.com
| Model Category | : | Public |
| Date Published | : | February, 2020 |
| Healthcare Domain | : | Provider |
| Code | : | github.com |
| Health Risk Management |
| Risk Progression |