ICS Events

Nonmedical opioid users were more likely to say they began abusing opioids after friends and family members offered them the drugs, not after their doctor prescribed them painkillers, according to researchers. Image: PXHere

“Semi-Supervised Learning Algorithm for Identifying High Priority Drug-Drug Interactions through Adverse Event Reports”

Date: Tuesday, November 5

Time: 10:30 a.m.–12:00 p.m.

Location: 233A HUB-Robeson Center and Streamed Live on Zoom

Watch the live stream on Zoom

Add to Calendar

Presenter: Soundar Kumara, Allen E. Pearce and Allen M. Pearce Professor of Industrial Engineering

Abstract: We will discuss few of the major studies conducted by LISA (Laboratory of Intelligent Systems and Analytics) in healthcare using AI and Machine Learning. We will detail the drug-to-drug interactions (DDIs) work. Identifying drug-drug interactions (DDIs) is a critical enabler for reducing adverse drug events and improving patient safety. Generating proper DDI alerts during patient prescription workflow has the potential to prevent DDI-related adverse events, and such an alerting system has received much attention worldwide. However, to improve the contents of DDI alerts without causing alert fatigue still remains a challenge. One strategy is to establish a list of high-priority DDIs for alerting purposes though it is a resource-intensive task. In this study, we propose a machine learning framework to extract useful features from the FDA adverse event reports, and then identify potential high-priority DDIs using an autoencoder-based semi-supervised learning algorithm. The experimental results demonstrate the effectiveness of using adverse event feature representations in differentiating high- and low-priority DDIs. Additionally, the proposed algorithm utilizes stacked autoencoders and weighted support vector machine to boost classification performance, which outperforms other competing methods in terms of F-measure and AUC score. This framework integrates multiple information sources, leverages domain knowledge and clinical evidence, and provides a practical approach to pre-screen high-priority DDI candidates for use in DDI alerting systems. The talk will be more application based.