# An Empirical Evaluation of Deep Learning for ICD-9 Code Assignment using MIMIC-III Clinical Notes

arXiv: https://arxiv.org/abs/1802.02311 · HTML: https://mlsanity.com/paper/1802.02311/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2018.

## Built on by (most cited first, 16 of 16)

- [Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review](https://mlsanity.com/paper/2107.02975/) (2021)
- [Read, Attend, and Code: Pushing the Limits of Medical Codes Prediction from Clinical Notes by Machines](https://mlsanity.com/paper/2107.10650/) (2021)
- [Benchmark datasets driving artificial intelligence development fail to capture the needs of medical professionals](https://mlsanity.com/paper/2201.07040/) (2022)
- [Multi-Label Clinical Time-Series Generation via Conditional GAN](https://mlsanity.com/paper/2204.04797/) (2022)
- [Evaluating Differentially Private Synthetic Data Generation in High-Stakes Domains](https://mlsanity.com/paper/2410.08327/) (2024)
- [A Systematic Literature Review of Automated ICD Coding and Classification Systems using Discharge Summaries](https://mlsanity.com/paper/2107.10652/) (2021)
- [HiCu: Leveraging Hierarchy for Curriculum Learning in Automated ICD Coding](https://mlsanity.com/paper/2208.02301/) (2022)
- [Medical Code Prediction from Discharge Summary: Document to Sequence BERT using Sequence Attention](https://mlsanity.com/paper/2106.07932/) (2021)
- [Active learning for medical code assignment](https://mlsanity.com/paper/2104.05741/) (2021)
- [Improving Hospital Risk Prediction with Knowledge-Augmented Multimodal EHR Modeling](https://mlsanity.com/paper/2508.01970/) (2025)
- [Few-Shot Electronic Health Record Coding through Graph Contrastive Learning](https://mlsanity.com/paper/2106.15467/) (2021)
- [Time-aware Heterogeneous Graph Transformer with Adaptive Attention Merging for Health Event Prediction](https://mlsanity.com/paper/2404.14815/) (2024)
- [Temporal Entailment Pretraining for Clinical Language Models over EHR Data](https://mlsanity.com/paper/2504.18128/) (2025)
- [From Extreme Multi-label to Multi-class: A Hierarchical Approach for Automated ICD-10 Coding Using Phrase-level Attention](https://mlsanity.com/paper/2102.09136/) (2021)
- [Real-Time Mobile Video Analytics for Pre-arrival Emergency Medical Services](https://mlsanity.com/paper/2511.14119/) (2025)
- [Hybrid-Code v2: Zero-Hallucination Clinical ICD-10 Coding via Neuro-Symbolic Verification and Automated Knowledge Base Expansion](https://mlsanity.com/paper/2512.23743/) (2025)

## Abstract (arXiv)

Background and Objective: Code assignment is of paramount importance in many levels in modern hospitals, from ensuring accurate billing process to creating a valid record of patient care history. However, the coding process is tedious and subjective, and it requires medical coders with extensive training. This study aims to evaluate the performance of deep-learning-based systems to automatically map clinical notes to ICD-9 medical codes. Methods: The evaluations of this research are focused on end-to-end learning methods without manually defined rules. Traditional machine learning algorithms, as well as state-of-the-art deep learning methods such as Recurrent Neural Networks and Convolution Neural Networks, were applied to the Medical Information Mart for Intensive Care (MIMIC-III) dataset. An extensive number of experiments was applied to different settings of the tested algorithm. Results: Findings showed that the deep learning-based methods outperformed other conventional machine learning methods. From our assessment, the best models could predict the top 10 ICD-9 codes with 0.6957 F1 and 0.8967 accuracy and could estimate the top 10 ICD-9 categories with 0.7233 F1 and 0.8588 accuracy. Our implementation also outperformed existing work under certain evaluation metrics. Conclusion: A set of standard metrics was utilized in assessing the performance of ICD-9 code assignment on MIMIC-III dataset. All the developed evaluation tools and resources are available online, which can be used as a baseline for further research.