This model uses FCN and supervised denoiser autoencoder to predict survival in patients with heart disease from their CMR imaging. Bello et. al. acquired image sequences of the heart using CMR (cardiac magnetic resonance) imaging and created time-resolved 3D segmentations using FCN (Fully convolutional network) trained upon anatomical shape priors. This model is used as input to a hybrid network called supervised denoising autoencoder. The autoencoder on being trained upon observed outcome data, learns a task-specific latent code representation and yields a latent representation that is optimized for survival prediction. The model has a significantly higher predictive accuracy than the human benchmark.
Input variables : Image sequences of the heart acquired using cardiac Magnetic Resonance Imaging
Output Variables : Survival prediction
| 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 | Optimized Hospital Resource Utilization | Decreased Cost of Care | Decreased Patient Visits |
| 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 : ncbi.nlm.nih.gov
Additional links : ncbi.nlm.nih.gov
| Model Category | : | Public |
| Date Published | : | February, 2019 |
| Healthcare Domain | : |
Medical Technology
Provider |
| Code | : | github.com |
| Health Risk Management |
| Health Risk Prediction |