Multimodal Machine Learning for Automated ICD Coding
Not on the map. Why?
Abstract (arXiv)
This study presents a multimodal machine learning model to predict ICD-10 diagnostic codes. We developed separate machine learning models that can handle data from different modalities, including unstructured text, semi-structured text and structured tabular data. We further employed an ensemble method to integrate all modality-specific models to generate ICD-10 codes. Key evidence was also extracted to make our prediction more convincing and explainable. We used the Medical Information Mart for Intensive Care III (MIMIC -III) dataset to validate our approach. For ICD code prediction, our best-performing model (micro-F1 = 0.7633, micro-AUC = 0.9541) significantly outperforms other baseline models including TF-IDF (micro-F1 = 0.6721, micro-AUC = 0.7879) and Text-CNN model (micro-F1 = 0.6569, micro-AUC = 0.9235). For interpretability, our approach achieves a Jaccard Similarity Coefficient (JSC) of 0.1806 on text data and 0.3105 on tabular data, where well-trained physicians achieve 0.2780 and 0.5002 respectively.
Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Oct 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 11; 2022: 10; 2023: 5; 2024: 8; 2025: 3; 2026: 3.
40 papers.
Sort:
- 2021MultiBench: Multiscale Benchmarks for Multimodal Representation Learningcited by 143
- 2022MultiViz: Towards Visualizing and Understanding Multimodal Modelscited by 36
- 2021Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Reviewcited by 35
- 2022DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanationscited by 34
- 2022Automated Clinical Coding: What, Why, and Where We Are?cited by 33
- 2022A Unified Review of Deep Learning for Automated Medical Codingcited by 26
- 2021Imbalanced Big Data Oversampling: Taxonomy, Algorithms, Software, Guidelines and Future Directionscited by 21
- 2024HEMM: Holistic Evaluation of Multimodal Foundation Modelscited by 21
- 2024An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Recordscited by 12
- 2021A Systematic Literature Review of Automated ICD Coding and Classification Systems using Discharge Summariescited by 10
- 2024Large language models are good medical coders, if provided with toolscited by 8
- 2021Attack-agnostic Adversarial Detection on Medical Data Using Explainable Machine Learningcited by 7
28 more
- 2021Machine Learning for Multimodal Electronic Health Records-based Research: Challenges and Perspectivescited by 7
- 2022Classifying Unstructured Clinical Notes via Automatic Weak Supervisioncited by 7
- 2024SimSUM: Simulated Benchmark with Structured and Unstructured Medical Recordscited by 6
- 2023MuG: A Multimodal Classification Benchmark on Game Data with Tabular, Textual, and Visual Fieldscited by 5
- 2023TreeMAN: Tree-enhanced Multimodal Attention Network for ICD Codingcited by 5
- 2022Brainish: Formalizing A Multimodal Language for Intelligence and Consciousnesscited by 4
- 2023MultiZoo & MultiBench: A Standardized Toolkit for Multimodal Deep Learningcited by 4
- 2024Examining Imbalance Effects on Performance and Demographic Fairness of Clinical Language Modelscited by 4
- 2021Multimodal Feature Fusion for Video Advertisements Tagging Via Stacking Ensemblecited by 3
- 2022Multimodal Machine Learning in Precision Healthcited by 3
- 2022HieNet: Bidirectional Hierarchy Framework for Automated ICD Codingcited by 3
- 2021A Meta-embedding-based Ensemble Approach for ICD Coding Predictioncited by 2
- 2024Large Language Model in Medical Informatics: Direct Classification and Enhanced Text Representations for Automatic ICD Codingcited by 2
- 2021Few-Shot Electronic Health Record Coding through Graph Contrastive Learningcited by 1
- 2022A Scalable Workflow to Build Machine Learning Classifiers with Clinician-in-the-Loop to Identify Patients in Specific Diseasescited by 1
- 2022Automated Fidelity Assessment for Strategy Training in Inpatient Rehabilitation using Natural Language Processingcited by 1
- 2025RuCCoD: Towards Automated ICD Coding in Russiancited by 1
- 2021From Extreme Multi-label to Multi-class: A Hierarchical Approach for Automated ICD-10 Coding Using Phrase-level Attentioncited by 0
- 2021Multimodal Classification: Current Landscape, Taxonomy and Future Directionscited by 0
- 2023Is In-hospital Meta-information Useful for Abstractive Discharge Summary Generation?cited by 0
- 2023Autoencoder-based prediction of ICU clinical codescited by 0
- 2024Multi-modal Masked Siamese Network Improves Chest X-Ray Representation Learningcited by 0
- 2024Improving ICD coding using Chapter based Named Entities and Attentional Modelscited by 0
- 2025Predictive Multimodal Modeling of Diagnoses and Treatments in EHRcited by 0
- 2025Patient-level Information Extraction by Consistent Integration of Textual and Tabular Evidence with Bayesian Networkscited by 0
- 2026A General Multimodal Probing Framework for Data Fusion and Prediction with Frozen Large Language Models: Evidence from Multimodal EHR Datacited by 0
- 2026Deep Label-Wise Attentive Temporal Convolutional Networks Improve Medical Codingcited by 0
- 2026xMICD: Explainable Representation of Multiple ICD Codescited by 0
- 2026xMICD: Explainable Representation of Multiple ICD Codes2 Aug 2026
- 2026Deep Label-Wise Attentive Temporal Convolutional Networks Improve Medical Coding27 Jul 2026
- 2026A General Multimodal Probing Framework for Data Fusion and Prediction with Frozen Large Language Models: Evidence from Multimodal EHR Data27 Jun 2026
- 2025Patient-level Information Extraction by Consistent Integration of Textual and Tabular Evidence with Bayesian Networks21 Nov 2025
- 2025Predictive Multimodal Modeling of Diagnoses and Treatments in EHR14 Aug 2025
- 2025RuCCoD: Towards Automated ICD Coding in Russian28 Feb 2025
- 2024Examining Imbalance Effects on Performance and Demographic Fairness of Clinical Language Models23 Dec 2024
- 2024Large Language Model in Medical Informatics: Direct Classification and Enhanced Text Representations for Automatic ICD Coding11 Nov 2024
- 2024SimSUM: Simulated Benchmark with Structured and Unstructured Medical Records13 Sep 2024
- 2024Improving ICD coding using Chapter based Named Entities and Attentional Models24 Jul 2024
- 2024Large language models are good medical coders, if provided with tools6 Jul 2024
- 2024Multi-modal Masked Siamese Network Improves Chest X-Ray Representation Learning5 Jul 2024
28 more
- 2024HEMM: Holistic Evaluation of Multimodal Foundation Models3 Jul 2024
- 2024An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records13 Jun 2024
- 2023MultiZoo & MultiBench: A Standardized Toolkit for Multimodal Deep Learning28 Jun 2023
- 2023TreeMAN: Tree-enhanced Multimodal Attention Network for ICD Coding29 May 2023
- 2023Autoencoder-based prediction of ICU clinical codes8 May 2023
- 2023Is In-hospital Meta-information Useful for Abstractive Discharge Summary Generation?10 Mar 2023
- 2023MuG: A Multimodal Classification Benchmark on Game Data with Tabular, Textual, and Visual Fields6 Feb 2023
- 2022HieNet: Bidirectional Hierarchy Framework for Automated ICD Coding9 Dec 2022
- 2022Automated Fidelity Assessment for Strategy Training in Inpatient Rehabilitation using Natural Language Processing14 Sep 2022
- 2022MultiViz: Towards Visualizing and Understanding Multimodal Models30 Jun 2022
- 2022Classifying Unstructured Clinical Notes via Automatic Weak Supervision24 Jun 2022
- 2022A Scalable Workflow to Build Machine Learning Classifiers with Clinician-in-the-Loop to Identify Patients in Specific Diseases18 May 2022
- 2022Brainish: Formalizing A Multimodal Language for Intelligence and Consciousness14 Apr 2022
- 2022Multimodal Machine Learning in Precision Health10 Apr 2022
- 2022Automated Clinical Coding: What, Why, and Where We Are?21 Mar 2022
- 2022DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations3 Mar 2022
- 2022A Unified Review of Deep Learning for Automated Medical Coding8 Jan 2022
- 2021Machine Learning for Multimodal Electronic Health Records-based Research: Challenges and Perspectives9 Nov 2021
- 2021Multimodal Classification: Current Landscape, Taxonomy and Future Directions18 Sep 2021
- 2021Multimodal Feature Fusion for Video Advertisements Tagging Via Stacking Ensemble2 Aug 2021
- 2021Imbalanced Big Data Oversampling: Taxonomy, Algorithms, Software, Guidelines and Future Directions24 Jul 2021
- 2021MultiBench: Multiscale Benchmarks for Multimodal Representation Learning15 Jul 2021
- 2021A Systematic Literature Review of Automated ICD Coding and Classification Systems using Discharge Summaries12 Jul 2021
- 2021Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review7 Jul 2021
- 2021Few-Shot Electronic Health Record Coding through Graph Contrastive Learning29 Jun 2021
- 2021Attack-agnostic Adversarial Detection on Medical Data Using Explainable Machine Learning5 May 2021
- 2021A Meta-embedding-based Ensemble Approach for ICD Coding Prediction26 Feb 2021
- 2021From Extreme Multi-label to Multi-class: A Hierarchical Approach for Automated ICD-10 Coding Using Phrase-level Attention18 Feb 2021
- 2021MultiBench: Multiscale Benchmarks for Multimodal Representation Learningcited by 143
- 2022MultiViz: Towards Visualizing and Understanding Multimodal Modelscited by 36
- 2021Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Reviewcited by 35
- 2022DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanationscited by 34
- 2022Automated Clinical Coding: What, Why, and Where We Are?cited by 33
- 2022A Unified Review of Deep Learning for Automated Medical Codingcited by 26
- 2021Imbalanced Big Data Oversampling: Taxonomy, Algorithms, Software, Guidelines and Future Directionscited by 21
- 2024HEMM: Holistic Evaluation of Multimodal Foundation Modelscited by 21
- 2024An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Recordscited by 12
- 2021A Systematic Literature Review of Automated ICD Coding and Classification Systems using Discharge Summariescited by 10
- 2024Large language models are good medical coders, if provided with toolscited by 8
- 2021Attack-agnostic Adversarial Detection on Medical Data Using Explainable Machine Learningcited by 7
12 most cited of 40 All 40 (JSON)
- 2026xMICD: Explainable Representation of Multiple ICD Codes2 Aug 2026
- 2026Deep Label-Wise Attentive Temporal Convolutional Networks Improve Medical Coding27 Jul 2026
- 2026A General Multimodal Probing Framework for Data Fusion and Prediction with Frozen Large Language Models: Evidence from Multimodal EHR Data27 Jun 2026
- 2025Patient-level Information Extraction by Consistent Integration of Textual and Tabular Evidence with Bayesian Networks21 Nov 2025
- 2025Predictive Multimodal Modeling of Diagnoses and Treatments in EHR14 Aug 2025
- 2025RuCCoD: Towards Automated ICD Coding in Russian28 Feb 2025
- 2024Examining Imbalance Effects on Performance and Demographic Fairness of Clinical Language Models23 Dec 2024
- 2024Large Language Model in Medical Informatics: Direct Classification and Enhanced Text Representations for Automatic ICD Coding11 Nov 2024
- 2024SimSUM: Simulated Benchmark with Structured and Unstructured Medical Records13 Sep 2024
- 2024Improving ICD coding using Chapter based Named Entities and Attentional Models24 Jul 2024
- 2024Large language models are good medical coders, if provided with tools6 Jul 2024
- 2024Multi-modal Masked Siamese Network Improves Chest X-Ray Representation Learning5 Jul 2024
12 newest of 40 All 40 (JSON)