# An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records

arXiv: https://arxiv.org/abs/2406.08958 · HTML: https://mlsanity.com/paper/2406.08958/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 60 references that are in the map.
- First posted on arXiv 13 Jun 2024.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Quantifying the Carbon Emissions of Machine Learning](https://mlsanity.com/paper/1910.09700/) (2019)
- [Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients](https://mlsanity.com/paper/1711.09404/) (2017)
- [Explainable Prediction of Medical Codes from Clinical Text](https://mlsanity.com/paper/1802.05695/) (2018)
- [Towards Faithful Model Explanation in NLP: A Survey](https://mlsanity.com/paper/2209.11326/) (2022)
- [On the Connection Between Adversarial Robustness and Saliency Map Interpretability](https://mlsanity.com/paper/1905.04172/) (2019)
- [Towards Improving Adversarial Training of NLP Models](https://mlsanity.com/paper/2109.00544/) (2021)
- [Incorporating Residual and Normalization Layers into Analysis of Masked Language Models](https://mlsanity.com/paper/2109.07152/) (2021)
- [Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study](https://mlsanity.com/paper/2304.10909/) (2023)
- [GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers](https://mlsanity.com/paper/2205.03286/) (2022)
- [A case for new neural network smoothness constraints](https://mlsanity.com/paper/2012.07969/) (2020)
- [Multimodal Machine Learning for Automated ICD Coding](https://mlsanity.com/paper/1810.13348/) (2018)
- [Explainable Automated Coding of Clinical Notes using Hierarchical Label-wise Attention Networks and Label Embedding Initialisation](https://mlsanity.com/paper/2010.15728/) (2020)
- [DecompX: Explaining Transformers Decisions by Propagating Token Decomposition](https://mlsanity.com/paper/2306.02873/) (2023)
- [MDACE: MIMIC Documents Annotated with Code Evidence](https://mlsanity.com/paper/2307.03859/) (2023)
- [Description-based Label Attention Classifier for Explainable ICD-9 Classification](https://mlsanity.com/paper/2109.12026/) (2021)
- [Ignorance is Bliss: Robust Control via Information Gating](https://mlsanity.com/paper/2303.06121/) (2023)
- [Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability](https://mlsanity.com/paper/2307.15007/) (2023)
- [Can Current Explainability Help Provide References in Clinical Notes to Support Humans Annotate Medical Codes?](https://mlsanity.com/paper/2210.15882/) (2022)
- [Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training](https://mlsanity.com/paper/2312.17591/) (2023)

## Built on by (most cited first, 12 of 12)

- [A General Knowledge Injection Framework for ICD Coding](https://mlsanity.com/paper/2505.18708/) (2025)
- [The Anatomy of Evidence: An Investigation Into Explainable ICD Coding](https://mlsanity.com/paper/2507.01802/) (2025)
- [MedDCR: Learning to Design Agentic Workflows for Medical Coding](https://mlsanity.com/paper/2511.13361/) (2025)
- [Similarity-Dissimilarity Loss for Multi-label Supervised Contrastive Learning](https://mlsanity.com/paper/2410.13439/) (2024)
- [Explainable ICD Coding via Entity Linking](https://mlsanity.com/paper/2503.20508/) (2025)
- [Evaluation and LLM-Guided Learning of ICD Coding Rationales](https://mlsanity.com/paper/2508.16777/) (2025)
- [Complete Evidence Extraction with Model Ensembles: A Case Study on Medical Coding](https://mlsanity.com/paper/2511.07055/) (2025)
- [A medical coding language model trained on clinical narratives from a population-wide cohort of 1.8 million patients](https://mlsanity.com/paper/2603.00221/) (2026)
- [Symphony for Medical Coding: A Next-Generation Agentic System for Scalable and Explainable Medical Coding](https://mlsanity.com/paper/2603.29709/) (2026)
- [Don't Pay Attention, PLANT It: Pretraining Attention via Learning-to-Rank](https://mlsanity.com/paper/2410.23066/) (2024)
- [From Documents to Spans: Span-Centric Learning for LLM-based Explainable Medical Coding](https://mlsanity.com/paper/2603.15270/) (2026)
- [Bridging the Version Gap: Multi-version Training Improves ICD Code Prediction, Especially for Rare Codes](https://mlsanity.com/paper/2605.17755/) (2026)

## Abstract (arXiv)

Electronic healthcare records are vital for patient safety as they document conditions, plans, and procedures in both free text and medical codes. Language models have significantly enhanced the processing of such records, streamlining workflows and reducing manual data entry, thereby saving healthcare providers significant resources. However, the black-box nature of these models often leaves healthcare professionals hesitant to trust them. State-of-the-art explainability methods increase model transparency but rely on human-annotated evidence spans, which are costly. In this study, we propose an approach to produce plausible and faithful explanations without needing such annotations. We demonstrate on the automated medical coding task that adversarial robustness training improves explanation plausibility and introduce AttInGrad, a new explanation method superior to previous ones. By combining both contributions in a fully unsupervised setup, we produce explanations of comparable quality, or better, to that of a supervised approach. We release our code and model weights.