# Deep survival analysis with longitudinal X-rays for COVID-19

arXiv: https://arxiv.org/abs/2108.09641 · HTML: https://mlsanity.com/paper/2108.09641/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 45 references that are in the map.
- First posted on arXiv 22 Aug 2021.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Network](https://mlsanity.com/paper/1606.00931/) (2016)
- [BIMCV COVID-19+: a large annotated dataset of RX and CT images from COVID-19 patients](https://mlsanity.com/paper/2006.01174/) (2020)
- [Deep Recurrent Survival Analysis](https://mlsanity.com/paper/1809.02403/) (2018)
- [A Critic Evaluation of Methods for COVID-19 Automatic Detection from X-Ray Images](https://mlsanity.com/paper/2004.12823/) (2020)
- [Predicting risk of late age-related macular degeneration using deep learning](https://mlsanity.com/paper/2007.09550/) (2020)
- [A Deep Recurrent Survival Model for Unbiased Ranking](https://mlsanity.com/paper/2004.14714/) (2020)

## Built on by (most cited first, 3 of 3)

- [Time-to-Event Pretraining for 3D Medical Imaging](https://mlsanity.com/paper/2411.09361/) (2024)
- [Dynamic Survival Prediction using Longitudinal Images based on Transformer](https://mlsanity.com/paper/2508.09328/) (2025)
- [Harnessing the power of longitudinal medical imaging for eye disease prognosis using Transformer-based sequence modeling](https://mlsanity.com/paper/2405.08780/) (2024)

## Abstract (arXiv)

Time-to-event analysis is an important statistical tool for allocating clinical resources such as ICU beds. However, classical techniques like the Cox model cannot directly incorporate images due to their high dimensionality. We propose a deep learning approach that naturally incorporates multiple, time-dependent imaging studies as well as non-imaging data into time-to-event analysis. Our techniques are benchmarked on a clinical dataset of 1,894 COVID-19 patients, and show that image sequences significantly improve predictions. For example, classical time-to-event methods produce a concordance error of around 30-40% for predicting hospital admission, while our error is 25% without images and 20% with multiple X-rays included. Ablation studies suggest that our models are not learning spurious features such as scanner artifacts. While our focus and evaluation is on COVID-19, the methods we develop are broadly applicable.