Related Experiment Video
Updated: Aug 9, 2025
A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
Published on: October 13, 2023
A hierarchical multilabel graph attention network method to predict the deterioration paths of chronic hepatitis B
Zejian Eric Wu1, Da Xu2, Paul Jen-Hwa Hu1
1Department of Operations and Information Systems, David Eccles School of Business, University of Utah, Salt Lake City, Utah, USA.
Insights
A new graph attention method accurately predicts chronic hepatitis B (CHB) patient deterioration paths by analyzing medication responses and diagnosis sequences. This approach offers significant improvements in prediction accuracy, aiding clinical decision-making.
Area of Science:
- Medical Informatics
- Artificial Intelligence in Healthcare
- Chronic Disease Management
Background:
- Estimating patient deterioration paths is crucial for effective clinical decision-making in chronic hepatitis B (CHB) management.
- Existing methods may not fully capture the complex dynamics of disease progression in CHB patients.
Purpose of the Study:
- To develop and evaluate a novel hierarchical multilabel graph attention-based method for predicting CHB patient deterioration paths.
- To enhance the accuracy and clinical utility of patient deterioration path prediction.
Main Methods:
- A hierarchical multilabel graph attention network was developed, incorporating patient responses to medications, diagnosis event sequences, and outcome dependencies.
- The method was applied to a large dataset of 177,959 CHB patients from Taiwan's electronic health records.
- Performance was evaluated against nine existing methods using precision, recall, F-measure, and AUC, with 20% holdout data.
Main Results:
- The proposed graph attention method significantly outperformed all benchmark methods in predicting CHB patient deterioration paths.
- Achieved the highest Area Under the Curve (AUC), with a 4.8% improvement over the best benchmark.
- Demonstrated substantial gains in precision (20.9%) and F-measure (11.4%) compared to existing methods.
Conclusions:
- The novel graph attention method effectively captures patient-medication interactions and temporal diagnosis patterns for predicting CHB deterioration.
- This approach provides physicians with a more holistic view of patient progression, enhancing clinical decision-making and management.
- The method shows strong predictive utility and significant clinical value for managing CHB patients.
Objective:
Estimating the deterioration paths of chronic hepatitis B (CHB) patients is critical for physicians' decisions and patient management. A novel, hierarchical multilabel graph attention-based method aims to predict patient deterioration paths more effectively. Applied to a CHB patient data set, it offers strong predictive utilities and clinical value.
Materials And Methods:
The proposed method incorporates patients' responses to medications, diagnosis event sequences, and outcome dependencies to estimate deterioration paths. From the electronic health records maintained by a major healthcare organization in Taiwan, we collect clinical data about 177 959 patients diagnosed with hepatitis B virus infection. We use this sample to evaluate the proposed method's predictive efficacy relative to 9 existing methods, as measured by precision, recall, F-measure, and area under the curve (AUC).
Results:
We use 20% of the sample as holdouts to test each method's prediction performance. The results indicate that our method consistently and significantly outperforms all benchmark methods. It attains the highest AUC, with a 4.8% improvement over the best-performing benchmark, as well as 20.9% and 11.4% improvements in precision and F-measures, respectively. The comparative results demonstrate that our method is more effective for predicting CHB patients' deterioration paths than existing predictive methods.
Discussion And Conclusion:
The proposed method underscores the value of patient-medication interactions, temporal sequential patterns of distinct diagnosis, and patient outcome dependencies for capturing dynamics that underpin patient deterioration over time. Its efficacious estimates grant physicians a more holistic view of patient progressions and can enhance their clinical decision-making and patient management.
More Related Videos
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
12:24A Three-Dimensional Spheroid Model to Investigate the Tumor-Stromal Interaction in Hepatocellular Carcinoma
Published on: September 30, 2021