mlsanityData to 14 Oct 2026

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

arXiv 2406.08958 ↗First posted 13 Jun 2024cs.LGcited by 12

Not on the map. Why?

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.

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

30 of 60 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  4. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  5. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
  6. 2019Attention is not Explanationcited by 929
  7. 2018Robustness May Be at Odds with Accuracycited by 880
  8. 2020Quantifying Attention Flow in Transformerscited by 775
  9. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 599
  10. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 547
  11. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 530
  12. 2019Quantifying the Carbon Emissions of Machine Learningcited by 521
18 more
  1. 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
  2. 2018Explainable Prediction of Medical Codes from Clinical Textcited by 234
  3. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 130
  4. 2019On the Connection Between Adversarial Robustness and Saliency Map Interpretabilitycited by 80
  5. 2021Towards Improving Adversarial Training of NLP Modelscited by 79
  6. 2021Incorporating Residual and Normalization Layers into Analysis of Masked Language Modelscited by 51
  7. 2023Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Studycited by 49
  8. 2022GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformerscited by 44
  9. 2020A case for new neural network smoothness constraintscited by 43
  10. 2018Multimodal Machine Learning for Automated ICD Codingcited by 41
  11. 2020Explainable Automated Coding of Clinical Notes using Hierarchical Label-wise Attention Networks and Label Embedding Initialisationcited by 38
  12. 2023DecompX: Explaining Transformers Decisions by Propagating Token Decompositioncited by 31
  13. 2023MDACE: MIMIC Documents Annotated with Code Evidencecited by 19
  14. 2021Description-based Label Attention Classifier for Explainable ICD-9 Classificationcited by 12
  15. 2023Ignorance is Bliss: Robust Control via Information Gatingcited by 10
  16. 2023Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretabilitycited by 10
  17. 2022Can Current Explainability Help Provide References in Clinical Notes to Support Humans Annotate Medical Codes?cited by 7
  18. 2023Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Trainingcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 6; 2026: 4.

12 papers.

  1. 2025A General Knowledge Injection Framework for ICD Codingcited by 7
  2. 2025The Anatomy of Evidence: An Investigation Into Explainable ICD Codingcited by 3
  3. 2025MedDCR: Learning to Design Agentic Workflows for Medical Codingcited by 3
  4. 2024Similarity-Dissimilarity Loss for Multi-label Supervised Contrastive Learningcited by 2
  5. 2025Explainable ICD Coding via Entity Linkingcited by 1
  6. 2025Evaluation and LLM-Guided Learning of ICD Coding Rationalescited by 1
  7. 2025Complete Evidence Extraction with Model Ensembles: A Case Study on Medical Codingcited by 1
  8. 2026A medical coding language model trained on clinical narratives from a population-wide cohort of 1.8 million patientscited by 1
  9. 2026Symphony for Medical Coding: A Next-Generation Agentic System for Scalable and Explainable Medical Codingcited by 1
  10. 2024Don't Pay Attention, PLANT It: Pretraining Attention via Learning-to-Rankcited by 0
  11. 2026From Documents to Spans: Span-Centric Learning for LLM-based Explainable Medical Codingcited by 0
  12. 2026Bridging the Version Gap: Multi-version Training Improves ICD Code Prediction, Especially for Rare Codescited by 0