# Language Model Classifier Aligns Better with Physician Word Sensitivity than XGBoost on Readmission Prediction

arXiv: https://arxiv.org/abs/2211.07047 · HTML: https://mlsanity.com/paper/2211.07047/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 17 references that are in the map.
- First posted on arXiv 13 Nov 2022.

## Builds on (most cited first, 6 of 6)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission](https://mlsanity.com/paper/1904.05342/) (2019)
- [Tune: A Research Platform for Distributed Model Selection and Training](https://mlsanity.com/paper/1807.05118/) (2018)
- [Fast WordPiece Tokenization](https://mlsanity.com/paper/2012.15524/) (2020)
- [Perturbation Sensitivity Analysis to Detect Unintended Model Biases](https://mlsanity.com/paper/1910.04210/) (2019)

## Built on by (most cited first, 2 of 2)

- [Generalist Foundation Models Are Not Clinical Enough for Hospital Operations](https://mlsanity.com/paper/2511.13703/) (2025)
- [Making the Most Out of the Limited Context Length: Predictive Power Varies with Clinical Note Type and Note Section](https://mlsanity.com/paper/2307.07051/) (2023)

## Abstract (arXiv)

Traditional evaluation metrics for classification in natural language processing such as accuracy and area under the curve fail to differentiate between models with different predictive behaviors despite their similar performance metrics. We introduce sensitivity score, a metric that scrutinizes models' behaviors at the vocabulary level to provide insights into disparities in their decision-making logic. We assess the sensitivity score on a set of representative words in the test set using two classifiers trained for hospital readmission classification with similar performance statistics. Our experiments compare the decision-making logic of clinicians and classifiers based on rank correlations of sensitivity scores. The results indicate that the language model's sensitivity score aligns better with the professionals than the xgboost classifier on tf-idf embeddings, which suggests that xgboost uses some spurious features. Overall, this metric offers a novel perspective on assessing models' robustness by quantifying their discrepancy with professional opinions. Our code is available on GitHub (https://github.com/nyuolab/Model_Sensitivity).