# Improving generalization of machine learning-identified biomarkers with causal modeling: an investigation into immune receptor diagnostics

arXiv: https://arxiv.org/abs/2204.09291 · HTML: https://mlsanity.com/paper/2204.09291/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 137 references that are in the map.
- First posted on arXiv 20 Apr 2022.

## Builds on (most cited first, 17 of 17)

- [Causality for Machine Learning](https://mlsanity.com/paper/1911.10500/) (2019)
- [Towards Causal Representation Learning](https://mlsanity.com/paper/2102.11107/) (2021)
- [Causality matters in medical imaging](https://mlsanity.com/paper/1912.08142/) (2019)
- [Understanding the Failure Modes of Out-of-Distribution Generalization](https://mlsanity.com/paper/2010.15775/) (2020)
- [Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions](https://mlsanity.com/paper/1707.06422/) (2017)
- [A Unified View of Label Shift Estimation](https://mlsanity.com/paper/2003.07554/) (2020)
- [An introduction to domain adaptation and transfer learning](https://mlsanity.com/paper/1812.11806/) (2018)
- [External Validity: From Do-Calculus to Transportability Across Populations](https://mlsanity.com/paper/1503.01603/) (2015)
- [A Review of Challenges and Opportunities in Machine Learning for Health](https://mlsanity.com/paper/1806.00388/) (2018)
- [A Modification of the Halpern-Pearl Definition of Causality](https://mlsanity.com/paper/1505.00162/) (2015)
- [A Review of Generalizability and Transportability](https://mlsanity.com/paper/2102.11904/) (2021)
- [Preventing dataset shift from breaking machine-learning biomarkers](https://mlsanity.com/paper/2107.09947/) (2021)
- [Preventing Failures Due to Dataset Shift: Learning Predictive Models That Transport](https://mlsanity.com/paper/1812.04597/) (2018)
- [Directed Acyclic Graphs and causal thinking in clinical risk prediction modeling](https://mlsanity.com/paper/2002.09414/) (2020)
- [Rethinking clinical prediction: Why machine learning must consider year of care and feature aggregation](https://mlsanity.com/paper/1811.12583/) (2018)
- [Averaging causal estimators in high dimensions](https://mlsanity.com/paper/1906.09303/) (2019)
- [Data science is science's second chance to get causal inference right: A classification of data science tasks](https://mlsanity.com/paper/1804.10846/) (2018)

## Built on by (most cited first, 1 of 1)

- [DagSim: Combining DAG-based model structure with unconstrained data types and relations for flexible, transparent, and modularized data simulation](https://mlsanity.com/paper/2205.11234/) (2022)

## Abstract (arXiv)

Machine learning is increasingly used to discover diagnostic and prognostic biomarkers from high-dimensional molecular data. However, a variety of factors related to experimental design may affect the ability to learn generalizable and clinically applicable diagnostics. Here, we argue that a causal perspective improves the identification of these challenges and formalizes their relation to the robustness and generalization of machine learning-based diagnostics. To make for a concrete discussion, we focus on a specific, recently established high-dimensional biomarker - adaptive immune receptor repertoires (AIRRs). Through simulations, we illustrate how major biological and experimental factors of the AIRR domain may influence the learned biomarkers. In conclusion, we argue that causal modeling improves machine learning-based biomarker robustness by identifying stable relations between variables and by guiding the adjustment of the relations and variables that vary between populations.