The model provides an actor-critic approach for temporal predictive clustering, AC-TPC, in which, a neural etworks are used as an encoder, a selector, and a predictor for clustering time-series EHR data, where each cluster comprises patients who share similar future outcomes of interest (e.g., adverse events, the onset of comorbidities).The model has been tested on two real world datasets UK Cystic Fibrosis registry (UKCF),Alzheimer’s Disease Neuroimaging Initiative (ADNI) and the experiments have shown it's superior clustering performance over state-of-the-art benchmarks and identifies meaningful clusters that can be translated into actionable information for clinical decision-making.
Input variables : EHR
Output Variables : Patient Clusters
| Statistical | : | Fowlkes Mallows Index | Homogenity Score | Reconstruction Error | Cohesion | Separation | Silhouette coefficient | Calisnki-Harabasz coefficient | Dunn index | Xie-Beni score | Hartigan index | Jaccard Similarity | Mutual Information | Twin Sample Validation |
| 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 : proceedings.mlr.press
| Model Category | : | Public |
| Date Published | : | July, 2020 |
| Healthcare Domain | : | Provider |
| Code | : | github.com |
| Health Risk Management |
| Risk Progression |