# Clinical Notes Reveal Physician Fatigue

arXiv: https://arxiv.org/abs/2312.03077 · HTML: https://mlsanity.com/paper/2312.03077/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 50 references that are in the map.
- First posted on arXiv 5 Dec 2023.

## Builds on (most cited first, 9 of 9)

- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes](https://mlsanity.com/paper/1711.08412/) (2017)
- [Do We Still Need Clinical Language Models?](https://mlsanity.com/paper/2302.08091/) (2023)
- [Natural Language Processing of Clinical Notes on Chronic Diseases: Systematic Review](https://mlsanity.com/paper/1908.05780/) (2019)
- [What's in a Summary? Laying the Groundwork for Advances in Hospital-Course Summarization](https://mlsanity.com/paper/2105.00816/) (2021)
- [Unsupervised Discovery of Implicit Gender Bias](https://mlsanity.com/paper/2004.08361/) (2020)
- [Write It Like You See It: Detectable Differences in Clinical Notes By Race Lead To Differential Model Recommendations](https://mlsanity.com/paper/2205.03931/) (2022)
- [Domain-Specific Pretraining for Vertical Search: Case Study on Biomedical Literature](https://mlsanity.com/paper/2106.13375/) (2021)

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

- [Sparse Autoencoders for Hypothesis Generation](https://mlsanity.com/paper/2502.04382/) (2025)

## Abstract (arXiv)

Physicians write notes about patients. In doing so, they reveal much about themselves. Using data from 129,228 emergency room visits, we train a model to identify notes written by fatigued physicians -- those who worked 5 or more of the prior 7 days. In a hold-out set, the model accurately identifies notes written by these high-workload physicians, and also flags notes written in other high-fatigue settings: on overnight shifts, and after high patient volumes. Model predictions also correlate with worse decision-making on at least one important metric: yield of testing for heart attack is 18% lower with each standard deviation increase in model-predicted fatigue. Finally, the model indicates that notes written about Black and Hispanic patients have 12% and 21% higher predicted fatigue than Whites -- larger than overnight vs. daytime differences. These results have an important implication for large language models (LLMs). Our model indicates that fatigued doctors write more predictable notes. Perhaps unsurprisingly, because word prediction is the core of how LLMs work, we find that LLM-written notes have 17% higher predicted fatigue than real physicians' notes. This indicates that LLMs may introduce distortions in generated text that are not yet fully understood.