Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Sep 12, 2024
Date Accepted: Apr 28, 2025
(closed for review but you can still tweet)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
An External Knowledge Brain Enhanced Decision Support System for Hypertensive Intracerebral Hemorrhage
ABSTRACT
Background:
Although much progress has been made in AI, several challenges remain substantial obstacles to the development and translation of AI systems into clinical practice. Even the LLMs (Large Language Models) which show excellent performance on various tasks, have progressed slowly in clinical practice task. Providing precise and "explainable" treatment plans with personalized details remains a big challenge for AI systems due to both the highly professional medical knowledge and the patient’s complicated condition. In this study, we develop a knowledge graph-enhanced and explainable automatic decision support system based on multiple-center data, named H-SYSTEM, hoping provide substantial assistance for neurosurgeons in dealing with HICH cases.
Objective:
During the past decade, much progress has been made in artificial intelligence (AI), but there are still two main challenges represent substantial obstacles to the development and translation of medical AI systems into clinical practice. The first important challenge is access to large and well-annotated datasets. The second important challenge is that the inner workings and decision-making processes of machine-learning algorithms remain opaque, which is also "black-box" effects. Therefore, in this study, we developed a novel clinical decision support system (CDSS) based on multiple-center data, called H-SYSTEM, attempting to address the two main challenges.
Methods:
The H-SYSTEM consists of three main modules, the key-named entity identification module, the semantic analysis and representation module, and the reasoning module. Furthermore, we constructed a medical domain knowledge graph for HICH, named HKG, which is served as an “external knowledge brain” of H-SYSTEM to enhance its text recognition and automated decision-making capability. The HKG is exploited to guide the training of semantic analysis and representation module and reasoning module, which makes the output of H-SYSTEM more “explainable”. To assess the performance of the H-SYSTEM, we compared it with doctors and different LLMs.
Results:
The outputs based on HKG showed a reliable performance as compared with the neurosurgical doctor (ND). The BERT-IDCNN-BiLSTM-CRF model was used as the key-named entity identification module of H-SYSTEM because of its excellent performance in terms of fast convergence and efficient extraction of key named entities. Furthermore, the H-SYSTEM showed high reliability and efficiency when compared to doctors, ChatGPT and ChatDoctor. Additionally, it also demonstrated both high accuracy and generalization capacity in the cases from diffrent medical centers.
Conclusions:
The H-SYSTEM shows significantly high efficiency and generalization capacity in processing EMRs, and provides 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 can exhibit excellent performance in the clinical practice task. Clinical Trial: This research is not an clinical trial.
Citation
