# Inducing Causal Structure for Interpretable Neural Networks Applied to Glucose Prediction for T1DM Patients

arXiv: https://arxiv.org/abs/2503.14442 · HTML: https://mlsanity.com/paper/2503.14442/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 36 references that are in the map.
- First posted on arXiv 18 Mar 2025.

## Builds on (most cited first, 11 of 11)

- [Towards Causal Representation Learning](https://mlsanity.com/paper/2102.11107/) (2021)
- [Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations](https://mlsanity.com/paper/2303.02536/) (2023)
- [Inducing Causal Structure for Interpretable Neural Networks](https://mlsanity.com/paper/2112.00826/) (2021)
- [InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques](https://mlsanity.com/paper/2407.14494/) (2024)
- [Causal Distillation for Language Models](https://mlsanity.com/paper/2112.02505/) (2021)
- [Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention Training](https://mlsanity.com/paper/2212.09897/) (2022)
- [When accurate prediction models yield harmful self-fulfilling prophecies](https://mlsanity.com/paper/2312.01210/) (2023)
- [From algorithms to action: improving patient care requires causality](https://mlsanity.com/paper/2209.07397/) (2022)
- [Short Term Blood Glucose Prediction based on Continuous Glucose Monitoring Data](https://mlsanity.com/paper/2002.02805/) (2020)
- [GLYFE: Review and Benchmark of Personalized Glucose Predictive Models in Type-1 Diabetes](https://mlsanity.com/paper/2006.15946/) (2020)
- [The risks of risk assessment: causal blind spots when using prediction models for treatment decisions](https://mlsanity.com/paper/2402.17366/) (2024)

## Abstract (arXiv)

Causal abstraction techniques such as Interchange Intervention Training (IIT) have been proposed to infuse neural network with expert knowledge encoded in causal models, but their application to real-world problems remains limited. This article explores the application of IIT in predicting blood glucose levels in Type 1 Diabetes Mellitus (T1DM) patients. The study utilizes an acyclic version of the simglucose simulator approved by the FDA to train a Multi-Layer Perceptron (MLP) model, employing IIT to impose causal relationships. Results show that the model trained with IIT effectively abstracted the causal structure and outperformed the standard one in terms of predictive performance across different prediction horizons (PHs) post-meal. Furthermore, the breakdown of the counterfactual loss can be leveraged to explain which part of the causal mechanism are more or less effectively captured by the model. These preliminary results suggest the potential of IIT in enhancing predictive models in healthcare by effectively complying with expert knowledge.