Deep Learning Applied to Chest X-Rays: Exploiting and Preventing Shortcuts

by   Sarah Jabbour, et al.

While deep learning has shown promise in improving the automated diagnosis of disease based on chest X-rays, deep networks may exhibit undesirable behavior related to shortcuts. This paper studies the case of spurious class skew in which patients with a particular attribute are spuriously more likely to have the outcome of interest. For instance, clinical protocols might lead to a dataset in which patients with pacemakers are disproportionately likely to have congestive heart failure. This skew can lead to models that take shortcuts by heavily relying on the biased attribute. We explore this problem across a number of attributes in the context of diagnosing the cause of acute hypoxemic respiratory failure. Applied to chest X-rays, we show that i) deep nets can accurately identify many patient attributes including sex (AUROC = 0.96) and age (AUROC >= 0.90), ii) they tend to exploit correlations between such attributes and the outcome label when learning to predict a diagnosis, leading to poor performance when such correlations do not hold in the test population (e.g., everyone in the test set is male), and iii) a simple transfer learning approach is surprisingly effective at preventing the shortcut and promoting good generalization performance. On the task of diagnosing congestive heart failure based on a set of chest X-rays skewed towards older patients (age >= 63), the proposed approach improves generalization over standard training from 0.66 (95 proposed approach has the potential to improve the performance of models across populations by encouraging reliance on clinically relevant manifestations of disease, i.e., those that a clinician would use to make a diagnosis.



page 12

page 13


Combining chest X-rays and EHR data using machine learning to diagnose acute respiratory failure

When patients develop acute respiratory failure, accurately identifying ...

Deep Learning for Automated Screening of Tuberculosis from Indian Chest X-rays: Analysis and Update

Background and Objective: Tuberculosis (TB) is a significant public heal...

An ensemble-based approach by fine-tuning the deep transfer learning models to classify pneumonia from chest X-ray images

Pneumonia is caused by viruses, bacteria, or fungi that infect the lungs...

Age prediction using a large chest X-ray dataset

Age prediction based on appearances of different anatomies in medical im...

Effectiveness of LSTMs in Predicting Congestive Heart Failure Onset

In this paper we present a Recurrent neural networks (RNN) based archite...

CheXclusion: Fairness gaps in deep chest X-ray classifiers

Machine learning systems have received much attention recently for their...

Predictive Modeling in the Presence of Nuisance-Induced Spurious Correlations

Deep predictive models often make use of spurious correlations between t...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.