# Adapting Pretrained Language Models for Solving Tabular Prediction Problems in the Electronic Health Record

arXiv: https://arxiv.org/abs/2303.14920 · HTML: https://mlsanity.com/paper/2303.14920/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 28 references that are in the map.
- First posted on arXiv 27 Mar 2023.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [TabTransformer: Tabular Data Modeling Using Contextual Embeddings](https://mlsanity.com/paper/2012.06678/) (2020)
- [TabLLM: Few-shot Classification of Tabular Data with Large Language Models](https://mlsanity.com/paper/2210.10723/) (2022)
- [Do NLP Models Know Numbers? Probing Numeracy in Embeddings](https://mlsanity.com/paper/1909.07940/) (2019)
- [LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks](https://mlsanity.com/paper/2206.06565/) (2022)
- [Did the Model Understand the Question?](https://mlsanity.com/paper/1805.05492/) (2018)
- [Transfer Learning with Deep Tabular Models](https://mlsanity.com/paper/2206.15306/) (2022)
- [Benchmarking emergency department triage prediction models with machine learning and large public electronic health records](https://mlsanity.com/paper/2111.11017/) (2021)
- [PTab: Using the Pre-trained Language Model for Modeling Tabular Data](https://mlsanity.com/paper/2209.08060/) (2022)

## Built on by (most cited first, 5 of 5)

- [Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Survey](https://mlsanity.com/paper/2402.17944/) (2024)
- [Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language Models](https://mlsanity.com/paper/2404.06209/) (2024)
- [Elephants Never Forget: Testing Language Models for Memorization of Tabular Data](https://mlsanity.com/paper/2403.06644/) (2024)
- [Language Modeling on Tabular Data: A Survey of Foundations, Techniques and Evolution](https://mlsanity.com/paper/2408.10548/) (2024)
- [SL-S4Wave: Self-Supervised Learning of Physiological Waveforms with Structured State Space Models](https://mlsanity.com/paper/2606.19888/) (2026)

## Abstract (arXiv)

We propose an approach for adapting the DeBERTa model for electronic health record (EHR) tasks using domain adaptation. We pretrain a small DeBERTa model on a dataset consisting of MIMIC-III discharge summaries, clinical notes, radiology reports, and PubMed abstracts. We compare this model's performance with a DeBERTa model pre-trained on clinical texts from our institutional EHR (MeDeBERTa) and an XGBoost model. We evaluate performance on three benchmark tasks for emergency department outcomes using the MIMIC-IV-ED dataset. We preprocess the data to convert it into text format and generate four versions of the original datasets to compare data processing and data inclusion. The results show that our proposed approach outperforms the alternative models on two of three tasks (p<0.001) and matches performance on the third task, with the use of descriptive columns improving performance over the original column names.