Predatory Medicine: Exploring and Measuring the Vulnerability of Medical AI to Predatory Science

TL;DR

This paper investigates how predatory scientific publications can pollute medical AI systems, compromising their credibility and safety by contaminating their data sources and outputs.

Contribution

It is the first study to identify predatory publications in medical AI data sources and demonstrate their impact on AI output credibility.

Findings

Predatory publications are present in PubMed, SemMedDB, and Knowledge Graphs.

Pollution from predatory science affects the outputs of MedAI systems.

Vulnerabilities in MedAI can be exploited by predatory literature, risking real-world deployment.

Abstract

Medical Artificial Intelligence (MedAI) for diagnosis, treatment options, and drug development represents the new age of healthcare. The security, integrity, and credibility of MedAI tools are paramount issues because human lives are at stake. MedAI solutions are often heavily dependent on scientific medical research literature as a primary data source that draws the attacker's attention as a potential target. We present a first study of how the output of MedAI can be polluted with Predatory Publications Presence (PPP). We study two MedAI systems: mediKanren (disease independent) and CancerMine (Disease-specific), which use research literature as primary data input from the research repository PubMed, PubMed derived database SemMedDB, and NIH translational Knowledge Graphs (KGs). Our study has a three-pronged focus: (1) identifying the PPP in PubMed; (2) verifying the PPP in SemMedDB and the KGs; (3) demonstrating the existing vulnerability of PPP traversing to the MedAI output. Our contribution lies in identifying the existing PPP in the MedAI inputs and demonstrating how predatory science can jeopardize the credibility of MedAI solutions, making their real-life deployment questionable.