Ai-Driven forecasting of tuberculosis cases: Enhancing medical education with predictive learning models
The advancement of artificial intelligence (AI) and machine learning has introduced alternative approaches to predictive modeling, particularly in data-driven fields such as medical forecasting. This study focuses on the fuzzy time series (FTS) model as an alternative to traditional statistical mode...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Proceedings |
| Language: | en |
| Published: |
Springer Verlag
2025
|
| Subjects: | |
| Online Access: | https://eprints.ums.edu.my/id/eprint/45821/1/FULLTEXT.pdf https://eprints.ums.edu.my/id/eprint/45821/ https://link.springer.com/chapter/10.1007/978-3-031-98003-9_24 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The advancement of artificial intelligence (AI) and machine learning has introduced alternative approaches to predictive modeling, particularly in data-driven fields such as medical forecasting. This study focuses on the fuzzy time series (FTS) model as an alternative to traditional statistical models for predicting tuberculosis (TB) case trends. Using monthly reported TB cases in Sabah, Malaysia, the study demonstrates the implementation of FTS in forecasting epidemic trends, emphasizing the methodological approach and its potential advantages over conventional statistical techniques. While this research highlights the predictive capability and technical aspects of the FTS model, its direct application in medical education remains an area for future exploration. The study suggests that integrating AI-driven forecasting techniques into medical education could provide valuable learning opportunities, such as engaging students with real-world epidemiological data and improving data interpretation skills. However, empirical validation of its impact on student learning has not yet been conducted. This study contributes to the ongoing discussion on AI-driven predictive modeling by demonstrating the feasibility of fuzzy time series in disease forecasting and suggesting its potential applicability in educational settings. |
|---|