Year: 2025
Type: article
Abstract: The healthcare sector is rapidly evolving with the integration of big data and machine learning. Predictive analytics enables early diagnosis, risk assessment, and efficient patient management. However, traditional data mining techniques are often static and cannot adapt to the continuous flow of medical data from wearable sensors, hospital systems, and remote diagnostics. This paper explores adaptive data mining approaches, emphasizing incremental learning, concept drift handling, and ensemble strategies. The study evaluates the performance of these approaches using real-world healthcare datasets, demonstrating their superiority in accuracy, speed, and adaptability compared to static models.
Author: Ashi Kushwah
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4409838289