CausalFlow-T
Cross-source consensus on CausalFlow-T from 1 sources and 8 claims.
1 sources · 8 claims
Uses
How it works
Benefits
Risks & contraindications
Comparisons
Highlighted claims
- CausalFlow-T uses a causal masked autoregressive normalizing flow conditioned on an LSTM-encoded patient history. — Joint Treatment Effect Estimation from Incomplete Healthcare Data: Temporal Causal Normalizing Flows with LLM-driven Evolutionary MNAR Imputation
- CausalFlow-T was the only causal estimator that satisfied all five reliability criteria across synthetic benchmarks. — Joint Treatment Effect Estimation from Incomplete Healthcare Data: Temporal Causal Normalizing Flows with LLM-driven Evolutionary MNAR Imputation
- CausalFlow-T had a mean rank of 1.83, outperforming NF without DAG, GNN-CVAE, CVAE, and TARNet. — Joint Treatment Effect Estimation from Incomplete Healthcare Data: Temporal Causal Normalizing Flows with LLM-driven Evolutionary MNAR Imputation
- CausalFlow-T maximizes exact likelihood with the change-of-variables formula instead of using an ELBO approximation. — Joint Treatment Effect Estimation from Incomplete Healthcare Data: Temporal Causal Normalizing Flows with LLM-driven Evolutionary MNAR Imputation
- CausalFlow-T computes counterfactuals through exact abduction-action-prediction by inverting observed variables, intervening on treatment, and decoding descendants in DAG order. — Joint Treatment Effect Estimation from Incomplete Healthcare Data: Temporal Causal Normalizing Flows with LLM-driven Evolutionary MNAR Imputation
- CausalFlow-T constrains autoregressive factorization to a topological ordering of the expert DAG. — Joint Treatment Effect Estimation from Incomplete Healthcare Data: Temporal Causal Normalizing Flows with LLM-driven Evolutionary MNAR Imputation
- CausalFlow-T estimates causal counterfactuals from completed longitudinal data. — Joint Treatment Effect Estimation from Incomplete Healthcare Data: Temporal Causal Normalizing Flows with LLM-driven Evolutionary MNAR Imputation
- CausalFlow-T uses dequantization for binary outcomes, which creates calibration costs on survival endpoints. — Joint Treatment Effect Estimation from Incomplete Healthcare Data: Temporal Causal Normalizing Flows with LLM-driven Evolutionary MNAR Imputation