# DeepRepViz: Identifying Confounders in Deep Learning Model Predictions

arXiv: https://arxiv.org/abs/2309.15551 · HTML: https://mlsanity.com/paper/2309.15551/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 28 references that are in the map.
- First posted on arXiv 27 Sep 2023.

## Builds on (most cited first, 6 of 6)

- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Risk of Training Diagnostic Algorithms on Data with Demographic Bias](https://mlsanity.com/paper/2005.10050/) (2020)
- [Algorithmic encoding of protected characteristics in image-based models for disease detection](https://mlsanity.com/paper/2110.14755/) (2021)
- [Statistical quantification of confounding bias in predictive modelling](https://mlsanity.com/paper/2111.00814/) (2021)
- [The Same Analysis Approach: Practical protection against the pitfalls of novel neuroimaging analysis methods](https://mlsanity.com/paper/1703.06670/) (2017)
- [Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research](https://mlsanity.com/paper/2301.08525/) (2023)

## Built on by (most cited first, 2 of 2)

- [Controlling for Omitted Variable Bias in Deep Neural Networks](https://mlsanity.com/paper/2608.25930/) (2026)
- [ICON decomposition: Multivariate concept auditing reveals shortcuts that neural networks rely on](https://mlsanity.com/paper/2608.26083/) (2026)

## Abstract (arXiv)

Deep Learning (DL) models have gained popularity in neuroimaging studies for predicting psychological behaviors, cognitive traits, and brain pathologies. However, these models can be biased by confounders such as age, sex, or imaging artifacts from the acquisition process. To address this, we introduce 'DeepRepViz', a two-part framework designed to identify confounders in DL model predictions. The first component is a visualization tool that can be used to qualitatively examine the final latent representation of the DL model. The second component is a metric called 'Con-score' that quantifies the confounder risk associated with a variable, using the final latent representation of the DL model. We demonstrate the effectiveness of the Con-score using a simple simulated setup by iteratively altering the strength of a simulated confounder and observing the corresponding change in the Con-score. Next, we validate the DeepRepViz framework on a large-scale neuroimaging dataset (n=12000) by performing three MRI-phenotype prediction tasks that include (a) predicting chronic alcohol users, (b) classifying participant sex, and (c) predicting performance speed on a cognitive task called 'trail making'. DeepRepViz identifies sex as a significant confounder in the DL model predicting chronic alcohol users (Con-score=0.35) and age as a confounder in the model predicting cognitive task performance (Con-score=0.3). In conclusion, the DeepRepViz framework provides a systematic approach to test for potential confounders such as age, sex, and imaging artifacts and improves the transparency of DL models for neuroimaging studies.