Large model-driven hyperscale healthcare data fusion analysis in complex multi-sensors

•We propose a novel large model-driven approach for hyperscale healthcare data fusion analysis in complex multi-sensor multi-sensors.•We use large models for semantic feature extraction in unstructured medical text and utilize them alongside structured data features through a hierarchical residual c...

Full description

Saved in:
Bibliographic Details
Published in:Information fusion Vol. 115; p. 102780
Main Authors: Lv, Jianhui, Kim, Byung-Gyu, Parameshachari, B.D., Slowik, Adam, Li, Keqin
Format: Journal Article
Language:English
Published: Elsevier B.V 01.03.2025
Subjects:
Complex multi-sensors
Dynamic ReLU
Hyperscale healthcare data fusion
Large model
Residual connection
Residual connection
Dynamic ReLU
Large model
Complex multi-sensors
Hyperscale healthcare data fusion
ISSN:1566-2535
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•We propose a novel large model-driven approach for hyperscale healthcare data fusion analysis in complex multi-sensor multi-sensors.•We use large models for semantic feature extraction in unstructured medical text and utilize them alongside structured data features through a hierarchical residual connected LSTM network.•We propose a dynamic ReLU activation function that can adjust the depths of the network dynamically depending on input data to allow the model to capture more complicated patterns without compromising computational efficiency.•We adopt an attention mechanism focusing on relevant information to increase accuracy and interpretability while suppressing noise. In the era of big data and artificial intelligence, healthcare data fusion analysis has become difficult because of the large amounts and different types of sources involved. Traditional methods are ineffective at processing and examination procedures for such complex multi-sensors of hyperscale healthcare data. To address this issue, we propose a novel large model-driven approach for hyperscale healthcare data fusion analysis in complex multi-sensor multi-sensors. Our method integrates data from various medical sensors and sources, using large models to extract and fuse information from structured and unstructured healthcare data. Then, we integrate these features with structured data using a hierarchical residual connected LSTM network, enhancing the model's ability to capture local and global context. Furthermore, we introduce a dynamic ReLU activation function and attention mechanism that allow us to adjust the depth of our networks dynamically while focusing only on relevant information. The experiments on MIMIC-III and eICU-CRD datasets demonstrate the superiority of the proposed method in terms of accuracy, efficiency, and robustness compared to state-of-the-art methods. Therefore, the proposed method provides valuable insights into the potential of large model-driven approaches for tackling the challenges of hyperscale healthcare data fusion analysis in complex multi-sensors. [Display omitted]
ISSN:1566-2535
DOI:10.1016/j.inffus.2024.102780