Daily Arxiv

This is a page that curates AI-related papers published worldwide.
All content here is summarized using Google Gemini and operated on a non-profit basis.
Copyright for each paper belongs to the authors and their institutions; please make sure to credit the source when sharing.

Longitudinal Ensemble Integration for sequential classification with multimodal data

Created by
  • Haebom

Author

Aviad Susman, Rupak Krishnamurthy, Yan Chak Li, Mohammad Olaimat, Serdar Bozdag, Bino Varghese, Nasim Sheikh-Bahaei, Gaurav Pandey

Outline

This paper focuses on the effective modeling of multimodal longitudinal data, which is an important task in various application areas, especially in biomedicine. Pointing out the limitations of previous studies that do not sufficiently consider multimodality, we develop several configurations of Longitudinal Ensemble Integration (LEI), a novel multimodal longitudinal learning framework for sequential classification. We evaluate the performance of LEI and compare it with existing methods on the task of early diagnosis of dementia, and demonstrate that it outperforms existing methods by improving integration over time by utilizing intermediate baseline predictions generated from individual data modalities. In addition, it is designed to identify features that are consistently important for dementia-related diagnosis prediction. In conclusion, this study demonstrates the potential of LEI for sequential classification from multimodal longitudinal data.

Takeaways, Limitations

Takeaways:
We present LEI, a novel framework for effective modeling of multimodal longitudinal data.
Improved integration over time through leveraging intermediate predictions of individual modalities.
Achieved superior performance compared to existing methods in sequential classification problems such as early diagnosis of dementia.
Ability to identify consistently important features over time.
Limitations:
Further research is needed to determine the generalizability of the proposed LEI framework.
Additional experiments and validation on various multi-modal longitudinal datasets are needed.
Since these are research results for a specific disease (dementia), further research is needed on the applicability to other diseases.
👍