XOmiVAE is an interpretable deep learning model for cancer classification using high-dimensional omics data. It provides contribution of each input molecular feature and latent dimension to the prediction. It is also revealed that XOmiVAE can explain both the supervised classification and the unsupervised clustering results from the deep learning network. XOmiVAE explanations of the downstream prediction when evaluated by biological annotation and literature, aligned with current domain knowledge. The top XOmiVAE selected genes and dimensions show significant influence to the performance of cancer classification. XOmiVAE shows great potential for novel biomedical knowledge discovery from deep learning models.
Input variables : Gene experssions for various tumor types
Output Variables : Cancer contribution values of each gene and latent dimension for a specific 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 : github.com
Additional links : arxiv.org
| Model Category | : | Public |
| Date Published | : | May, 2021 |
| Healthcare Domain | : |
Life Sciences
Provider |
| Code | : | github.com |
| Health Risk Management |
| Health Risk Prediction |