# TEMPO: Transformers for Temporal Disease Progression from Cross-Sectional Data

arXiv: https://arxiv.org/abs/2604.23368 · HTML: https://mlsanity.com/paper/2604.23368/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 35 references that are in the map.
- First posted on arXiv 25 Apr 2026.

## Builds on (most cited first, 3 of 3)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Unscrambling disease progression at scale: fast inference of event permutations with optimal transport](https://mlsanity.com/paper/2410.14388/) (2024)
- [Bayesian Event-Based Model for Disease Subtype and Stage Inference](https://mlsanity.com/paper/2512.03467/) (2025)

## Abstract (arXiv)

Event-Based Models (EBMs) infer biomarker progression from cross-sectional data but typically only as ordinal sequences and rely on rigid model assumptions. We propose textscTempo, a Transformer architecture that learns both ordinal and continuous event sequences through simulation-based supervised learning. textscTempo uses two Transformer modules: one treats biomarkers as tokens to infer event sequencing; the other treats patients as tokens, representing each by their per-biomarker abnormality profile, to infer patients' disease stages. On synthetic benchmarks, textscTempo reduces normalized Kendall's Tau distance by 52.89% and staging MAE by 25.33% compared to state-of-the-art SA-EBM, with larger reductions in high-dimensional settings (58.88% and 61.10%). Applied to ADNI, textscTempo recovers a biologically plausible Alzheimer's progression: early medial temporal atrophy, followed by amyloid accumulation and cognitive decline, and late-stage tau pathology with terminal acceleration of global neurodegeneration -- broadly consistent with established disease models. textscTempo also eliminates the need to derive custom inference algorithms and enables rapid empirical comparison of generative hypotheses.