Research map / 3D vision / Depth and stereo
Deep Survival Analysis With Longitudinal X-Rays for COVID-19
Michelle Shu, Richard Strong Bowen, Charles Herrmann, Gengmo Qi, Michele Santacatterina, Ramin Zabih
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add time-dependent X-ray branch (ConvLSTM) to non-image model (ablation) | Non-Image (ours) · COVID-19 clinical dataset: Admit | concordance error: 0.247 -> 0.198 | Improved |
| add time-dependent X-ray branch (ConvLSTM) to non-image model (ablation) | Non-Image (ours) · COVID-19 clinical dataset: ICU Discharge | concordance error: 0.439 -> 0.385 | Improved |
| add time-dependent X-ray branch (ConvLSTM) to non-image model (ablation) | Non-Image (ours) · COVID-19 clinical dataset: Death | concordance error: 0.278 -> 0.246 | Improved |
| add non-image LSTM branch to image-only model (ablation) | Image-Only (ours) · COVID-19 clinical dataset: ICU Admit | concordance error: 0.408 -> 0.241 | Improved |
| use mini-batch stochastic gradient descent for DeepConvSurv instead of full-set gradient descent | DeepConvSurv · COVID-19 clinical dataset: Death | concordance error: 0.351 -> 0.435 | Hurt |
| obscure 100% of the X-ray image (ablation) | Image+labs (ours) · COVID-19 clinical dataset: Admit | concordance error: 0.198 -> 0.268 | Hurt |
| obscure 100% of the X-ray image (ablation) | Image+labs (ours) · COVID-19 clinical dataset: ICU Discharge | concordance error: 0.335 -> 0.437 | Hurt |
| obscure 80% of the X-ray image (ablation) | Image+labs (ours) · COVID-19 clinical dataset: Admit | concordance error: 0.198 -> 0.250 | Hurt |
| increase number of X-rays from k=1 to k=2 (ablation) | Image+labs (ours) · COVID-19 clinical dataset: Admit | concordance error: 0.072 | Improved |
| increase number of X-rays from k=1 to k=2 (ablation) | Image+labs (ours) · COVID-19 clinical dataset: ICU Discharge | concordance error: 0.048 | Improved |
| increase number of X-rays from k=1 to k=2 (ablation) | Image+labs (ours) · COVID-19 clinical dataset: Discharge | concordance error: 0.006 | Improved |
| reduce mini-batch size from B>=20 to B=10 (ablation) | Image+labs (ours) · COVID-19 clinical dataset | concordance error | Hurt |
Closest papers by meaning
- Time-to-Event Pretraining for 3D Medical Imaging (ICLR 2025 · similarity 0.81)
- Cumulative Difference Learning VAE for Time-Series with Temporally Correlated Inflow-Outflow (AAAI 2024 · similarity 0.81)
- XTSFormer: Cross-Temporal-Scale Transformer for Irregular-Time Event Prediction in Clinical Applications (AAAI 2025 · similarity 0.80)
- Integrating Sequence and Image Modeling in Irregular Medical Time Series Through Self-Supervised Learning (AAAI 2025 · similarity 0.80)
- Multimodal Disease Progression Modeling via Spatiotemporal Disentanglement and Multiscale Alignment (NeurIPS 2025 · similarity 0.80)
- HC-LLM: Historical-Constrained Large Language Models for Radiology Report Generation (AAAI 2025 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
