# From algorithms to action: improving patient care requires causality

arXiv: https://arxiv.org/abs/2209.07397 · HTML: https://mlsanity.com/paper/2209.07397/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 30 references that are in the map.
- First posted on arXiv 15 Sep 2022.

## Builds on (most cited first, 3 of 3)

- [Identifying Causal Effects With Proxy Variables of an Unmeasured Confounder](https://mlsanity.com/paper/1609.08816/) (2016)
- [Prediction meets causal inference: the role of treatment in clinical prediction models](https://mlsanity.com/paper/2004.06998/) (2020)
- [Conditional average treatment effect estimation with marginally constrained models](https://mlsanity.com/paper/2204.13975/) (2022)

## Built on by (most cited first, 5 of 5)

- [When accurate prediction models yield harmful self-fulfilling prophecies](https://mlsanity.com/paper/2312.01210/) (2023)
- [Inducing Causal Structure for Interpretable Neural Networks Applied to Glucose Prediction for T1DM Patients](https://mlsanity.com/paper/2503.14442/) (2025)
- [Time After Time: Deep-Q Effect Estimation for Interventions on When and What to do](https://mlsanity.com/paper/2503.15890/) (2025)
- [What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs](https://mlsanity.com/paper/2606.28615/) (2026)
- [Optimizing for the decision not the prediction: an exploration of Smooth Net Benefit as a training objective](https://mlsanity.com/paper/2609.12752/) (2026)

## Abstract (arXiv)

In cancer research there is much interest in building and validating outcome predicting outcomes to support treatment decisions. However, because most outcome prediction models are developed and validated without regard to the causal aspects of treatment decision making, many published outcome prediction models may cause harm when used for decision making, despite being found accurate in validation studies. Guidelines on prediction model validation and the checklist for risk model endorsement by the American Joint Committee on Cancer do not protect against prediction models that are accurate during development and validation but harmful when used for decision making. We explain why this is the case and how to build and validate models that are useful for decision making.