Authors:
Ralph Shad, Brown Klinton, Kaledio Potter

Addresses:
Department of Computer Science, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States of America. Department of Applied Mathematics and Theoretical Physics and Department of Engineering, Widener University, Chester, Pennsylvania, United States of America. Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, Ithaca, New York, United States of America.

Abstract:

Artificial Intelligence (AI) is rapidly transforming the landscape of modern healthcare, offering innovative solutions for early disease detection. This study provides a comprehensive review of current AI applications in early diagnosis, focusing on machine learning, deep learning, and natural language processing techniques. It explores how AI systems analyse large and complex datasets such as medical images, electronic health records, and genomic data to identify early signs of diseases, including cancer, cardiovascular disorders, and diabetes. A qualitative research approach was adopted, using expert interviews and document analysis to investigate real-world implementations of AI tools in clinical settings. The findings reveal that AI significantly enhances diagnostic accuracy, reduces time to detection, and supports clinical decision-making. However, challenges remain, including data bias, lack of interpretability in AI models, limited diversity in training datasets, and ethical concerns regarding privacy and accountability. The paper concludes with recommendations for future research, including the need for more inclusive datasets, the development of explainable AI models, and the exploration of AI’s potential in underserved healthcare settings. Overall, AI holds immense promise for revolutionising early disease detection and improving patient outcomes globally.

Keywords: Artificial Intelligence; Healthcare Systems; Early Disease Detection; Medical Diagnostics; AI Technologies; Noncommunicable Diseases; Precision and Consistency; Machine Learning; Deep Learning Models.

Received on: 15/07/2024, Revised on: 09/10/2024, Accepted on: 16/11/2024, Published on: 03/03/2025

DOI: 10.69888/FTSHSL.2025.000361

FMDB Transactions on Sustainable Health Science Letters, 2025 Vol. 3 No. 1, Pages: 11-31

• Views : 92
• Downloads : 7

Download PDF