# Training Large Language Models to Predict Clinical Events

arXiv: https://arxiv.org/abs/2605.12817 · HTML: https://mlsanity.com/paper/2605.12817/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 9 references that are in the map.
- First posted on arXiv 12 May 2026.

## Builds on (most cited first, 7 of 7)

- [ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission](https://mlsanity.com/paper/1904.05342/) (2019)
- [Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease prediction](https://mlsanity.com/paper/2005.12833/) (2020)
- [BEHRT: Transformer for Electronic Health Records](https://mlsanity.com/paper/1907.09538/) (2019)
- [Future-as-Label: Scalable Supervision from Real-World Outcomes](https://mlsanity.com/paper/2601.06336/) (2026)
- [Large Language Models for Medical Forecasting -- Foresight 2](https://mlsanity.com/paper/2412.10848/) (2024)
- [Foresight Learning for SEC Risk Prediction](https://mlsanity.com/paper/2601.19189/) (2026)
- [Forecasting Supply Chain Disruptions with Foresight Learning](https://mlsanity.com/paper/2604.01298/) (2026)

## Abstract (arXiv)

Longitudinal clinical notes contain rich evidence of how patients evolve over time, but converting this signal into training supervision for clinical prediction remains challenging. We extend Foresight Learning to clinical prediction by converting time-ordered MIMIC-III notes into examples consisting of past patient context, a natural-language question about a possible future event, and a label resolved from later documentation. This process yields 6,900 prediction examples from 702 admissions across medications, procedures, organ support, microbiology, and mortality. A small LoRA adapter trained on these examples improves over the prompted base model, reducing expected calibration error from 0.1269 to 0.0398 and Brier score from 0.199 to 0.145, while slightly outperforming GPT-5 point estimates on held-out questions. The approach enables reusable clinical prediction supervision from longitudinal notes without hand-engineered structured features or endpoint-specific classifiers.