AI-Driven Cardio-Oncology for Early Prediction of Chemotherapy-Induced Cardiotoxicity

Authors

  • Shima Ali Sadia, Sadia Jaman, Shamsunnahar Chadni, Sharmin Akter, Navila Sultana, Pritom Das, Mostofa Adib Shakib, Ramesh Khatri, Farhana Yeasmin Rita, Md Ahnaf Tajwar Kamal, Momtaz Akter Mitu Author

DOI:

https://doi.org/10.64149/

Keywords:

Artificial Intelligence (AI), Cardio-Oncology, Chemotherapy-Induced Cardiotoxicity, Early Prediction, Cardiac-Monitoring, Machine-Learning, Healthcare Technology, Cancer-Treatment, Patient-Survival, Predictive-Analytics..

Abstract

Background: Chemotherapy-induced cardiotoxicity is one of the most serious complications of cancer management that occurs in those with cancer either during or after treatment. Traditional modalities of diagnosis are not applicable in detecting early heart damage that can bring about severe heart issues. Artificial intelligence (AI) has already demonstrated itself as a promising healthcare technology, particularly in the sphere of cardio-oncology, as it may help in predicting diseases, diagnosing and planning individual treatment.

Objective: The key objective of the research was not merely to investigate the place of AI-powered cardio-based oncology systems in the early detection of chemotherapy-induced cardiotoxicity, but also to compare the perceptions of the research participants towards the efficacy, reliability and acceptability of AI technologies in health care.

Methodology: This study was done using a quantitative research design. A structured questionnaire was used to gather data with a five-point Likert scale, which was applied to 200 respondents. Demographic items and questions on AI in healthcare, cardiac monitoring and cardiotoxicity prediction were included in the questionnaire. The statistical analysis, which involved normality tests, reliability tests, and validity tests, an independent-samples t-test, a One-Way ANOVA, a Kruskal-Wallis Test, a Chi-Squared Test, a Pearson correlation, and a regression Analysis, was done using statistical software.

Results: The conclusions were that the data were normal and reliable, with Cronbach's alpha values exceeding 0.70. The high level of construct validity was supported by the test scores of KMO and the Bartlett test. The Correlation and regression analyses revealed that there were significant positive relationships between AI-based monitoring systems and improved predictability of cardiotoxicity with chemotherapy. The outcome of the hypothesis testing revealed statistically significant relationships and links between the demographics and the acceptance of AI. The respondents were more prone to express positive attitudes toward the effectiveness of AI technologies in fulfilling the role of cardiac monitoring and reducing the effect of human error, and beneficially affecting the results related to patient survival.

Conclusion:  The authors established that AI-based cardio-oncology systems have tremendous potential when it comes to better identifying, earlier detection and treatment of chemotherapy-related cardiotoxicity. It is possible that, with the assistance of artificial intelligence (AI) technologies, healthcare professionals will be able to keep track of a patient in real time, which allows predicting and planning treatment and improving patient safety and treatment effectiveness. Despite all the complexities related to data protection, its associated cost, and technical expertise, AI-based healthcare systems will be a great leap towards modern cancer care.

Downloads

Published

2022-12-28

How to Cite

AI-Driven Cardio-Oncology for Early Prediction of Chemotherapy-Induced Cardiotoxicity. (2022). Vascular and Endovascular Review, 5(1). https://doi.org/10.64149/