Knowledge Graph–Enhanced Deep Learning Model (H-SYSTEM) for Hypertensive Intracerebral Hemorrhage: Model Development and Validation

Abstract BackgroundAlthough much progress has been made in artificial intelligence (AI), several challenges remain substantial obstacles to the development and translation of AI systems into clinical practice. Even large language models, which show excellent performance on var...

Full description

Saved in:
Bibliographic Details
Main Authors: Yulong Xia, Jie Li, Bo Deng, Qilin Huang, Fenglin Cai, Yanfeng Xie, Xiaochuan Sun, Quanhong Shi, Wei Dan, Yan Zhan, Li Jiang
Format: Article
Language:English
Published: JMIR Publications 2025-06-01
Series:Journal of Medical Internet Research
Online Access:https://www.jmir.org/2025/1/e66055
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849689225178382336
author Yulong Xia
Jie Li
Bo Deng
Qilin Huang
Fenglin Cai
Yanfeng Xie
Xiaochuan Sun
Quanhong Shi
Wei Dan
Yan Zhan
Li Jiang
author_facet Yulong Xia
Jie Li
Bo Deng
Qilin Huang
Fenglin Cai
Yanfeng Xie
Xiaochuan Sun
Quanhong Shi
Wei Dan
Yan Zhan
Li Jiang
author_sort Yulong Xia
collection DOAJ
description Abstract BackgroundAlthough much progress has been made in artificial intelligence (AI), several challenges remain substantial obstacles to the development and translation of AI systems into clinical practice. Even large language models, which show excellent performance on various tasks, have progressed slowly in clinical practice tasks. Providing precise and explainable treatment plans with personalized details remains a big challenge for AI systems due to both the highly specialized medical knowledge required and patients’ complicated conditions. ObjectiveThis study aimed to develop an explainable and efficient decision support system named H-SYSTEM to assist neurosurgeons in diagnosing and treating patients with hypertensive intracerebral hemorrhage. The system was designed to address the limitations of existing AI systems by integrating a medical domain knowledge graph to enhance decision-making accuracy and explainability. MethodsThe H-SYSTEM consists of 3 main modules: the key named entity recognition (NER) module, the semantic analysis and representation module, and the reasoning module. Furthermore, we constructed a medical domain knowledge graph for hypertensive intracerebral hemorrhage, named HKG, which served as an external knowledge brain of the H-SYSTEM to enhance its text recognition and automated decision-making capability. The HKG was exploited to guide the training of the semantic analysis and representation module and reasoning module, which makes the output of the H-SYSTEM more explainable.To assess the performance of the H-SYSTEM, we compared it with doctors and different large language models. ResultsThe outputs based on HKG showed reliable performance as compared with neurosurgical doctors, with an overall accuracy of 94.87%. The bidirectional encoder representations from transformers, inflated dilated convolutional neural network, bidirectional long short-term memory, and conditional random fields (BERT-IDCNN-BiLSTM-CRF) model was used as the key NER module of the H-SYSTEM due to its fast convergence and efficient extraction of key named entities, achieved the highest performance among 7 key NER models (precision=92.03, recall=90.22, and F1PPP ConclusionsThe H-SYSTEM showed significantly high efficiency and generalization capacity in processing electronic medical records, and it provided explainable and elaborate treatment plans. Therefore, it has the potential to provide neurosurgeons with rapid and reliable decision support, especially in emergency conditions. The knowledge graph–enhanced deep-learning model exhibited excellent performance in the clinical practice tasks.
format Article
id doaj-art-89ebefb6e550498fade5bbde0872a783
institution DOAJ
issn 1438-8871
language English
publishDate 2025-06-01
publisher JMIR Publications
record_format Article
series Journal of Medical Internet Research
spelling doaj-art-89ebefb6e550498fade5bbde0872a7832025-08-20T03:21:42ZengJMIR PublicationsJournal of Medical Internet Research1438-88712025-06-0127e66055e6605510.2196/66055Knowledge Graph–Enhanced Deep Learning Model (H-SYSTEM) for Hypertensive Intracerebral Hemorrhage: Model Development and ValidationYulong Xiahttp://orcid.org/0009-0002-9531-9374Jie Lihttp://orcid.org/0000-0002-7075-4145Bo Denghttp://orcid.org/0009-0000-9674-6525Qilin Huanghttp://orcid.org/0009-0009-0033-3044Fenglin Caihttp://orcid.org/0000-0003-1043-5553Yanfeng Xiehttp://orcid.org/0000-0002-3932-4331Xiaochuan Sunhttp://orcid.org/0009-0005-9533-6758Quanhong Shihttp://orcid.org/0000-0003-1587-0001Wei Danhttp://orcid.org/0000-0001-9455-9566Yan Zhanhttp://orcid.org/0009-0009-3839-108XLi Jianghttp://orcid.org/0009-0001-5114-5731 Abstract BackgroundAlthough much progress has been made in artificial intelligence (AI), several challenges remain substantial obstacles to the development and translation of AI systems into clinical practice. Even large language models, which show excellent performance on various tasks, have progressed slowly in clinical practice tasks. Providing precise and explainable treatment plans with personalized details remains a big challenge for AI systems due to both the highly specialized medical knowledge required and patients’ complicated conditions. ObjectiveThis study aimed to develop an explainable and efficient decision support system named H-SYSTEM to assist neurosurgeons in diagnosing and treating patients with hypertensive intracerebral hemorrhage. The system was designed to address the limitations of existing AI systems by integrating a medical domain knowledge graph to enhance decision-making accuracy and explainability. MethodsThe H-SYSTEM consists of 3 main modules: the key named entity recognition (NER) module, the semantic analysis and representation module, and the reasoning module. Furthermore, we constructed a medical domain knowledge graph for hypertensive intracerebral hemorrhage, named HKG, which served as an external knowledge brain of the H-SYSTEM to enhance its text recognition and automated decision-making capability. The HKG was exploited to guide the training of the semantic analysis and representation module and reasoning module, which makes the output of the H-SYSTEM more explainable.To assess the performance of the H-SYSTEM, we compared it with doctors and different large language models. ResultsThe outputs based on HKG showed reliable performance as compared with neurosurgical doctors, with an overall accuracy of 94.87%. The bidirectional encoder representations from transformers, inflated dilated convolutional neural network, bidirectional long short-term memory, and conditional random fields (BERT-IDCNN-BiLSTM-CRF) model was used as the key NER module of the H-SYSTEM due to its fast convergence and efficient extraction of key named entities, achieved the highest performance among 7 key NER models (precision=92.03, recall=90.22, and F1PPP ConclusionsThe H-SYSTEM showed significantly high efficiency and generalization capacity in processing electronic medical records, and it provided explainable and elaborate treatment plans. Therefore, it has the potential to provide neurosurgeons with rapid and reliable decision support, especially in emergency conditions. The knowledge graph–enhanced deep-learning model exhibited excellent performance in the clinical practice tasks.https://www.jmir.org/2025/1/e66055
spellingShingle Yulong Xia
Jie Li
Bo Deng
Qilin Huang
Fenglin Cai
Yanfeng Xie
Xiaochuan Sun
Quanhong Shi
Wei Dan
Yan Zhan
Li Jiang
Knowledge Graph–Enhanced Deep Learning Model (H-SYSTEM) for Hypertensive Intracerebral Hemorrhage: Model Development and Validation
Journal of Medical Internet Research
title Knowledge Graph–Enhanced Deep Learning Model (H-SYSTEM) for Hypertensive Intracerebral Hemorrhage: Model Development and Validation
title_full Knowledge Graph–Enhanced Deep Learning Model (H-SYSTEM) for Hypertensive Intracerebral Hemorrhage: Model Development and Validation
title_fullStr Knowledge Graph–Enhanced Deep Learning Model (H-SYSTEM) for Hypertensive Intracerebral Hemorrhage: Model Development and Validation
title_full_unstemmed Knowledge Graph–Enhanced Deep Learning Model (H-SYSTEM) for Hypertensive Intracerebral Hemorrhage: Model Development and Validation
title_short Knowledge Graph–Enhanced Deep Learning Model (H-SYSTEM) for Hypertensive Intracerebral Hemorrhage: Model Development and Validation
title_sort knowledge graph enhanced deep learning model h system for hypertensive intracerebral hemorrhage model development and validation
url https://www.jmir.org/2025/1/e66055
work_keys_str_mv AT yulongxia knowledgegraphenhanceddeeplearningmodelhsystemforhypertensiveintracerebralhemorrhagemodeldevelopmentandvalidation
AT jieli knowledgegraphenhanceddeeplearningmodelhsystemforhypertensiveintracerebralhemorrhagemodeldevelopmentandvalidation
AT bodeng knowledgegraphenhanceddeeplearningmodelhsystemforhypertensiveintracerebralhemorrhagemodeldevelopmentandvalidation
AT qilinhuang knowledgegraphenhanceddeeplearningmodelhsystemforhypertensiveintracerebralhemorrhagemodeldevelopmentandvalidation
AT fenglincai knowledgegraphenhanceddeeplearningmodelhsystemforhypertensiveintracerebralhemorrhagemodeldevelopmentandvalidation
AT yanfengxie knowledgegraphenhanceddeeplearningmodelhsystemforhypertensiveintracerebralhemorrhagemodeldevelopmentandvalidation
AT xiaochuansun knowledgegraphenhanceddeeplearningmodelhsystemforhypertensiveintracerebralhemorrhagemodeldevelopmentandvalidation
AT quanhongshi knowledgegraphenhanceddeeplearningmodelhsystemforhypertensiveintracerebralhemorrhagemodeldevelopmentandvalidation
AT weidan knowledgegraphenhanceddeeplearningmodelhsystemforhypertensiveintracerebralhemorrhagemodeldevelopmentandvalidation
AT yanzhan knowledgegraphenhanceddeeplearningmodelhsystemforhypertensiveintracerebralhemorrhagemodeldevelopmentandvalidation
AT lijiang knowledgegraphenhanceddeeplearningmodelhsystemforhypertensiveintracerebralhemorrhagemodeldevelopmentandvalidation