Multi-instance Domain Adaptation for Vaccine Adverse Event Detection

Abstract

Detection of vaccine adverse events is crucial to the discovery and improvement of problematic vaccines. To achieve it, traditionally formal reporting systems like VAERS support accurate but delayed surveillance, while recently social media have been mined for timely but noisy observations. Utilizing the complementary strengths of these two domains to boost the detection performance looks good but cannot be effectively achieved by existing methods due to significant differences between their data characteristics, including: 1) formal language v.s. informal language, 2) single-message per user v.s. multi-messages per user, and 3) one class v.s. binary class. In this paper, we propose a novel generic framework named Multi-instance Domain Adaptation (MIDA) to maximize the synergy between these two domains in the vaccine adverse event detection task for social media users. Specifically, we propose a generalized Maximum Mean Discrepancy (MMD) criterion to measure the semantic distances between the heterogeneous messages from these two domains in their shared latent semantic space. Then these message-level generalized MMD distances are synthesized by newly proposed mixed instance kernels to user-level distances. We finally minimize the distances between the samples of the partially-matched classes from these two domains. In order to solve the non-convex optimization problem, an efficient Alternating Direction Method of Multipliers (ADMM) based algorithm combined with the Convex-Concave Procedure (CCP) is developed to optimize parameters accurately. Extensive experiments demonstrated that our model outperformed the baselines by a large margin under six metrics. Case studies showed that formal reports and extracted adverse-relevant tweets by MIDA shared a similarity of keyword and description patterns.

Individual-Level Fatality Prediction of COVID-19 Patients Using AI Methods

“…By using keywords, they eliminate many irrelevant Tweets and categorically find tweets that strictly relate to the discussion of a drug and its symptoms. This study was furthered improved in the detection of adverse effects from vaccines (22). Using Multi-instance Domain Adaptation (MIDA) model on Twitter data, they were able to identify symptoms and align them with formal reports of symptoms to identify adverse effects in the use of a vaccine.…”

“…Wang et al (27) was able to identify potential adversarial effects through a multi-instance logistic regression model (MILR) by scanning Tweets and using VAERS information. Wang et al (22) also uses deep learning with sSSM and nSSM models to classify the discussion of symptoms within tweets that relate to the flu. Symptoms such as arm pain and headaches could be identified in tweets related to the flu accurately under their model.…”

Event Prediction in the Big Data Era

“…The goal here is usually to predict the time before an event occurs, although some researchers have attempted to predict the type of event. The data sources are usually the electronic health records of individual patients [145] and other user-generated health-related reports [181]. Recently, social media, forum, and mobile data has also been utilized for predicting drug adverse events [157] and events that arise during chronic disease (e.g., chemical radiation and surgery) [51].…”

DynGraph2Seq: Dynamic-Graph-to-Sequence Interpretable Learning for Health Stage Prediction in Online Health Forums

“…A number of studies have focused on the analysis and utilization of online health communities data. Popular social media is good for aggregate level pattern mining tasks [8], [9]. However, their power is limited for discovering individuallevel health stages and health network patterns due to the privacy issues involved and data scarcity.…”