Automatic Cardiac Risk Management Classification using large-context Electronic Patients Health Records

2026-03-10

AI Summary

This study addresses the inefficiency and error-proneness of manual coding in cardiovascular risk assessment for older adults by proposing an automated risk stratification framework that integrates unstructured electronic health records with structured medication and anthropometric data from longitudinal Dutch clinical texts of 3,482 patients. The core innovation lies in a customized Transformer architecture incorporating a hierarchical attention mechanism to effectively capture long-range dependencies in clinical narratives, combined with a late fusion strategy to harmonize multimodal information sources. Experimental results demonstrate that the proposed approach significantly outperforms conventional machine learning methods, zero-shot general-purpose large language models, and other deep learning baselines in terms of both F1 score and Matthews correlation coefficient, thereby substantially enhancing the performance of automated risk classification.

Technology Category

Natural Language Processing: Code Generation / Program Synthesis from Natural LanguageMachine Learning: Multimodal LearningCognitive Modeling & Cognitive Systems: (Computational) Cognitive Architectures

Application Category

Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasetsSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingResponsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

To overcome the limitations of manual administrative coding in geriatric Cardiovascular Risk Management, this study introduces an automated classification framework leveraging unstructured Electronic Health Records (EHRs). Using a dataset of 3,482 patients, we benchmarked three distinct modeling paradigms on longitudinal Dutch clinical narratives: classical machine learning baselines, specialized deep learning architectures optimized for large-context sequences, and general-purpose generative Large Language Models (LLMs) in a zero-shot setting. Additionally, we evaluated a late fusion strategy to integrate unstructured text with structured medication embeddings and anthropometric data. Our analysis reveals that the custom Transformer architecture outperforms both traditional methods and generative \acs{llm}s, achieving the highest F1-scores and Matthews Correlation Coefficients. These findings underscore the critical role of specialized hierarchical attention mechanisms in capturing long-range dependencies within medical texts, presenting a robust, automated alternative to manual workflows for clinical risk stratification.

Problem

• Cardiovascular Risk Management
• Electronic Health Records
• Automated Classification
• Geriatric Care
• Clinical Risk Stratification

Innovation

• large-context EHR
• custom Transformer
• hierarchical attention
• automated risk stratification
• late fusion