# SHIFT: Survival Prediction from Incomplete and Heterogeneous Genomic Data

arXiv: https://arxiv.org/abs/2607.07725 · HTML: https://mlsanity.com/paper/2607.07725/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 43 references that are in the map.
- First posted on arXiv 4 Jul 2026.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Self-Normalizing Neural Networks](https://mlsanity.com/paper/1706.02515/) (2017)
- [DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Network](https://mlsanity.com/paper/1606.00931/) (2016)
- [Generative Adversarial Network in Medical Imaging: A Review](https://mlsanity.com/paper/1809.07294/) (2018)
- [Distribution Matching Losses Can Hallucinate Features in Medical Image Translation](https://mlsanity.com/paper/1805.08841/) (2018)
- [Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction](https://mlsanity.com/paper/2304.06819/) (2023)
- [Deep Learning for Survival Analysis: A Review](https://mlsanity.com/paper/2305.14961/) (2023)
- [Not Another Imputation Method: A Transformer-based Model for Missing Values in Tabular Datasets](https://mlsanity.com/paper/2407.11540/) (2024)
- [Review for Handling Missing Data with special missing mechanism](https://mlsanity.com/paper/2404.04905/) (2024)
- [Unlocking the Power of Multi-institutional Data: Integrating and Harmonizing Genomic Data Across Institutions](https://mlsanity.com/paper/2402.00077/) (2024)

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

- [MIST: Multimodal Survival Prediction with Genomic-Guided Histology Attention](https://mlsanity.com/paper/2609.21811/) (2026)

## Abstract (arXiv)

Genomic prediction models often fail to transfer across institutions because sequencing panels differ across sites, creating structural feature missingness at deployment. Existing approaches to this challenge typically restrict analysis to genes shared across cohorts, exclude patients with incomplete profiles, or rely on test-time imputation, all of which can reduce robustness and limit the use of multi-center data. We propose Survival prediction Handling Incomplete Features using Transformer (SHIFT), a missingness-aware survival model that directly predicts from incomplete genomic inputs without test-time imputation. SHIFT represents each genomic feature separately and uses masked self-attention, along with a feature-availability mask, so that predictions are based only on observed inputs. Further, we introduce variable-rate feature masking during training to improve robustness to heterogeneous missingness patterns. We evaluate the approach on glioblastoma and lung squamous cell carcinoma with external validation across multiple cohorts, including a challenging setting with severe cross-cohort panel mismatch. Across these settings, SHIFT shows strong generalization and compares favorably with standard survival baselines and imputation-based approaches, while using a single model across differing feature sets. We also find that incorporating patients from incomplete cohorts during development can improve performance on external data, suggesting that partially observed cohorts need not be excluded from model building. These results support missingness-aware modeling as a practical strategy for multi-center survival prediction in precision oncology.