AI-Driven Cardiac Lymphedema Prediction Using Clinical Data
DOI:
https://doi.org/10.52783/jns.v14.3558Keywords:
N\AAbstract
Cardiac lymphedema represents a condition where there is dysfunction in the lymphatic drainage system of the heart, leading to the accumulation of lymph fluid, which can contribute to a variety of cardiovascular complications, including heart failure, myocardial inflammation, and arrhythmias. These complications, when not managed effectively, pose significant risks to patient health. Early diagnosis of cardiac lymphedema remains a significant challenge due to its subtle clinical presen- tation, which often leads to misdiagnosis or delayed diagnosis, as well as the limitations of traditional diagnostic methods. This research presents an innovative approach to predicting cardiac lymphedema through the application of a gradient- boosting algorithm integrated into a web-based decision support system designed to aid clinicians in diagnosing the condition. The model utilizes a carefully curated dataset, including a range of clinical and physiological parameters, to achieve high accuracy in performing binary classification tasks. The web-based application provides a user-friendly interface that enables clinicians to input patient-specific data and receive predictive insights regarding the likelihood of cardiac lymphedema, which can significantly improve clinical decision-making. The integration of machine learning into the diagnostic process highlights its potential to bridge existing gaps in healthcare diagnostics and offers a promising tool for enhancing early detection and treatment outcomes in patients with cardiac lymphedema.
Index Terms—Cardiac Lymphedema, Lymphatic Drainage System, Heart Failure, Myocardial Inflammation, Arrhythmias, Cardiovascular Complications, Early Diagnosis, Clinical Pre- sentation, Traditional Diagnostic Methods, Gradient-Boosting Algorithm, Web-Based Decision Support System, Binary Classifi- cation, Clinical and Physiological Parameters, Machine Learning in Healthcare, Predictive Analytics, Healthcare Diagnostics, Early Detection, Treatment Outcomes, User-Friendly Interface, Patient- Specific Data
Downloads
Metrics
References
Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer.
Breiman, L. (2001). ”Random Forests.” Machine Learning, 45(1), 5-32.
Chawla, N. V., Bowyer, K. W. (2002). ”SMOTE: Synthetic Minority Over-sampling Technique.” Journal of Artificial Intelligence Research, 16, 321-357.
Chen, T., Guestrin, C. (2016). ”XGBoost: A Scalable Tree Boosting System.” Proceedings of the 22nd ACM SIGKDD International Confer- ence on Knowledge Discovery and Data Mining, 785-794.
Dhar, V. (2018). ”Data Science and Prediction Models in Healthcare.” Journal of Data Science, 16(4), 35-48.
Gonza´lez, R. C., Woods, R. E. (2002). Digital Image Processing. Prentice Hall.
He, H., Wu, D. (2020). ”Cardiac Disease Diagnosis Using Machine Learning Algorithms.” Computational and Mathematical Methods in Medicine, 2020, 1-10.
Khan, A. H., Chellappan, M. (2019). ”Machine Learning Techniques in Healthcare: A Survey and Classification.” Procedia Computer Science, 152, 117-124.
Ng, A. Y. (2011). ”Machine Learning Yearning: Technical Strategy for AI Engineers.” Self-published.
Peng X, Lu Z. Development and Validation of Upper Limb Lym- phedema in Patients After Breast Cancer Surgery Using a Practicable Machine Learning Model: A Retrospective Cohort Study. Int J Gen Med. 2024;17:3799-3812 https://doi.org/10.2147/IJGM.S478573.
Rao, P. S., Thakur, M. (2019). ”Challenges and Trends in Machine Learning for Healthcare.” Journal of Healthcare Engineering, 2019, 1- 12.
Sutton, R.T., Pincock, D., Baumgart, D.C. et al. An overview of clinical decision support systems: benefits, risks, and strategies for success. npj Digit. Med. 3, 17 (2020). https://doi.org/10.1038/s41746-020-0221-y
Wang, Z., Gu, Y., Huang, L. et al. Construction of machine learning diagnostic models for cardiovascular pan-disease based on blood routine and biochemical detection data. Cardiovasc Diabetol 23, 351 (2024). https://doi.org/10.1186/s12933-024-02439-0
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
