Abstract :

Combining Drugs Is Common In Treating Diseases But Raises The Risk Of Adverse Drug Reactions (ADRs). Early Detection Of ADRs Is Essential For Medication Safety. Social Media Has Emerged As A Valuable Source For Identifying ADRs, But Its Data Is Massive, Noisy, And Sparse, Making Extraction Challenging. Deep Learning Improves Detection Accuracy But Requires Heavy Computation. Quantum Computing, With Its Parallel Processing And Lower Resource Needs, Offers A Promising Alternative. A New Model, Quantum Bi-LSTM With Attention (QBi-LSTMA), Integrates Quantum Computing And Attention Mechanisms Into A Bi-LSTM Network For ADR Detection. The Model Uses Six Stacked Variable Quantum Circuit Components, Simplifies The Bi-LSTM Structure By Removing Gate Biases, And Efficiently Updates Network Parameters With Weight And Activation Qubits. Tested On The SMM4H Dataset, QBi-LSTMA Outperforms Traditional And Deep Learning-based Models, Showing Strong Potential For Large-scale ADR Detection. Keywords— Adverse Drug Reactions (ADRs), Social Media Big Data, Quantum Bi-LSTM With Attention (QBi-LSTMA), Bidirectional Long Short-term Memory (Bi-LSTM).

Published:

10-12-2025

Issue:

Vol. 25 No. 12 (2025)

Page Nos:

86-94

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite