The KNN algorithm, on the other hand, is more
sensitive to the balance of the data. In this study, it
can be observed that the uneven distribution of the
number of samples of certain types of eigenvalues,
such as gender, type of chest pain, etc., which is the
main problem that leads to the unsatisfactory
prediction accuracy of the model of this algorithm.
4 CONCLUSIONS
In this article, the study was conducted by using
different machine learning algorithms to make
predictions about heart disease. These six algorithms
include Logistic Regression, Decision Tree, Random
Forest, Naive Bayes, K-Nearest Neighbors, and
Support Vector Machines, and finally the best model
was found for this study, which is the Support Vector
Machines classifier model, whose accuracy reaches
89.01%.
In fact, there are some shortcomings in this study.
For example, the samples included in the dataset were
not balanced enough, the study did not reach the
expected accuracy of 95%, and only some machine
learning models were used in the training of the
model, and some deep learning algorithms were not
considered to be used to make predictions.
In the future, in order to have a more balanced
data sample, the study will continue to collect
relevant data for the machine's learning, and the
algorithmic model of the experiment to adjust the
parameters and optimization, and will start to try to
use some better algorithms to complete the
optimization of the prediction results, such as
XGBoost, CatBoost etc. Next, the research will
expand the heart prediction problem into a multi-
classification problem, classifying heart disease into
different types or severity levels to better assist
doctors in risk assessment and personalizing
treatment for patients.
REFERENCES
Kaggle. 2019. Heart disease dataset. Retrieved from https://
www.kaggle.com/datasets/johnsmith88/heart-disease-
dataset
Ouyang, D., He, B., Ghorbani, A. et al. 2020. Video-based
AI for beat-to-beat assessment of cardiac function.
Nature, 580, 252–256. https://doi.org/10.1038/s41586-
020-2145-8
Qiu, Y., Wang, J., Jin, Z., Chen, H., Zhang, M., & Guo, L.
2022. Pose-guided matching based on deep learning for
assessing quality of action on rehabilitation training.
Biomedical Signal Processing and Control, 72, 103323.
Qiu, Y., Hui, Y., Zhao, P., Cai, C. H., Dai, B., Dou, J., ... &
Yu, J. 2024. A novel image expression-driven modeling
strategy for coke quality prediction in the smart
cokemaking process. Energy, 130866.
Sun, G., Zhan, T., Owusu, B.G., Daniel, A.M., Liu, G., &
Jiang, W. 2020. Revised reinforcement learning based
on anchor graph hashing for autonomous cell activation
in cloud-RANs. Future Generation Computer Systems,
104, 60-73.
Topol, E. J. 2023. As artificial intelligence goes
multimodal, medical applications multiply. Science,
381, eadk6139. DOI:10.1126/science.adk6139
Wu, Y., Jin, Z., Shi, C., Liang, P., & Zhan, T. 2024.
Research on the Application of Deep Learning-based
BERT Model in Sentiment Analysis. arXiv preprint
arXiv:2403.08217.
Yang, Y. et al. 2022. Artificial intelligence-enabled
detection and assessment of Parkinson's disease using
nocturnal breathing signals. Nature Medicine.
doi:10.1038/s41591-022-01932-x
Zhang, X., Wu, C., Zhang, Y. et al. 2023. Knowledge-
enhanced visual-language pre-training on chest
radiology images. Nat Commun, 14, 4542.
https://doi.org/10.1038/s41467-023-40260-7
Zhou, Y., Osman, A., Willms, M., Kunz, A., Philipp, S.,
Blatt, J., & Eul, S. 2023. Semantic Wireframe
Detection. publica.fraunhofer.de.