CTP:A Causal Interpretable Model for Non-Communicable Disease Progression Prediction

TL;DR

The paper introduces CTP, a novel causal trajectory prediction model that combines trajectory forecasting and causal discovery to improve interpretability and treatment effect estimation in non-communicable disease progression prediction.

Contribution

It presents a new model that integrates causal graphs with trajectory prediction, enabling causal interpretability and treatment effect estimation in disease progression modeling.

Findings

Achieves accurate disease progression predictions on real datasets.

Provides bounds on treatment effects even with unmeasured confounders.

Enhances interpretability of machine learning models in clinical settings.

Abstract

Non-communicable disease is the leading cause of death, emphasizing the need for accurate prediction of disease progression and informed clinical decision-making. Machine learning (ML) models have shown promise in this domain by capturing non-linear patterns within patient features. However, existing ML-based models cannot provide causal interpretable predictions and estimate treatment effects, limiting their decision-making perspective. In this study, we propose a novel model called causal trajectory prediction (CTP) to tackle the limitation. The CTP model combines trajectory prediction and causal discovery to enable accurate prediction of disease progression trajectories and uncover causal relationships between features. By incorporating a causal graph into the prediction process, CTP ensures that ancestor features are not influenced by the treatment of descendant features, thereby enhancing the interpretability of the model. By estimating the bounds of treatment effects, even in the presence of unmeasured confounders, the CTP provides valuable insights for clinical decision-making. We evaluate the performance of the CTP using simulated and real medical datasets. Experimental results demonstrate that our model achieves satisfactory performance, highlighting its potential to assist clinical decisions. Source code is in \href{https://github.com/DanielSun94/CFPA}{here}.