# Counterfactual Formulation of Patient-Specific Root Causes of Disease

arXiv: https://arxiv.org/abs/2305.17574 · HTML: https://mlsanity.com/paper/2305.17574/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 19 references that are in the map.
- First posted on arXiv 27 May 2023.

## Builds on (most cited first, 8 of 8)

- [Consistent Individualized Feature Attribution for Tree Ensembles](https://mlsanity.com/paper/1802.03888/) (2018)
- [Causal Discovery with Continuous Additive Noise Models](https://mlsanity.com/paper/1309.6779/) (2013)
- [Causal structure based root cause analysis of outliers](https://mlsanity.com/paper/1912.02724/) (2019)
- [Identifying Patient-Specific Root Causes with the Heteroscedastic Noise Model](https://mlsanity.com/paper/2205.13085/) (2022)
- [Why did the distribution change?](https://mlsanity.com/paper/2102.13384/) (2021)
- [Backtracking Counterfactuals](https://mlsanity.com/paper/2211.00472/) (2022)
- [Identifying Patient-Specific Root Causes of Disease](https://mlsanity.com/paper/2205.11627/) (2022)
- [Sample-Specific Root Causal Inference with Latent Variables](https://mlsanity.com/paper/2210.15340/) (2022)

## Built on by (most cited first, 8 of 8)

- [Root Cause Analysis of Outliers with Missing Structural Knowledge](https://mlsanity.com/paper/2406.05014/) (2024)
- [The role of causality in explainable artificial intelligence](https://mlsanity.com/paper/2309.09901/) (2023)
- [A tutorial on discovering and quantifying the effect of latent causal sources of multimodal EHR data](https://mlsanity.com/paper/2510.16026/) (2025)
- [Root Cause Analysis of Measurement and Mechanistic Anomalies](https://mlsanity.com/paper/2601.23026/) (2026)
- [Causal explanations of outliers in systems with lagged time-dependencies](https://mlsanity.com/paper/2602.04667/) (2026)
- [Extracting Root-Causal Brain Activity Driving Psychopathology from Resting State fMRI](https://mlsanity.com/paper/2602.07233/) (2026)
- [DAGverse: Building Document-Grounded Semantic DAGs from Scientific Papers](https://mlsanity.com/paper/2603.25293/) (2026)
- [Beyond Conditional Independence: Root Cause Analysis with Deep Causal Models](https://mlsanity.com/paper/2609.36771/) (2026)

## Abstract (arXiv)

Root causes of disease intuitively correspond to root vertices that increase the likelihood of a diagnosis. This description of a root cause nevertheless lacks the rigorous mathematical formulation needed for the development of computer algorithms designed to automatically detect root causes from data. Prior work defined patient-specific root causes of disease using an interventionalist account that only climbs to the second rung of Pearl's Ladder of Causation. In this theoretical piece, we climb to the third rung by proposing a counterfactual definition matching clinical intuition based on fixed factual data alone. We then show how to assign a root causal contribution score to each variable using Shapley values from explainable artificial intelligence. The proposed counterfactual formulation of patient-specific root causes of disease accounts for noisy labels, adapts to disease prevalence and admits fast computation without the need for counterfactual simulation.