Enhancing Systematic Literature Reviews for Adverse Events with AI

The primary pillar of the EU MDR is patient safety. Irrespective of the risk classification or nature of device, all devices are expected to meet rigorous safety standards to ensure that they do not cause any harm to patients. One of the most effective ways of ensuring device safety is through adverse event reporting. One of the primary sources of identifying adverse events related to device use is literature. A systematic literature review is a methodical, structured process for gathering, screening, extracting data and synthesizing research on a specific topic. The goal is to uncover patterns, gaps, and trends in the available evidence.

Unlike traditional reviews or essays, an SLR follows a set process that includes defining research questions, selecting studies, and assessing their quality and relevance. Systematic literature reviews are essential for compiling data on the safety and performance of the medical device into its Clinical Evaluation Reports (CER) to meet regulatory requirements. These reviews provide a thorough and unbiased assessment of the safety and performance of medical devices by analyzing data from multiple sources.

The process involves several key steps:

• Literature Search: Identifying relevant studies from various databases such as PubMed, Embase, and Cochrane. Identification is facilitated by defining a research objective and defining appropriate keywords and search strings to pull the most appropriate results on the topic of interest.
• Screening: Filtering studies based on predefined inclusion and exclusion criteria.
• Data Extraction: Extracting relevant data, including study type, study subjects, demographics, interventions used, performance outcomes of interest and adverse events.
• Data Synthesis: Summarizing and synthesizing the extracted data to draw meaningful conclusions.

Conducting systematic literature reviews is a time-consuming and labor-intensive process. It requires an elevated level of accuracy and attention to detail to ensure that all relevant studies are included and correctly evaluated. The sheer volume of literature to be reviewed can be overwhelming for regulatory professionals leading to inefficiencies, delays, and compliance risks especially when traditional manual methods are applied. Improperly analyzed and presented, specifically presenting missing or partial data, can create a skewed understanding of the true safety risks associated with a device, leading to gaps in safety assessment. Manual data extraction, since subjective, is also often associated with inconsistent interpretation of adverse events, especially when it comes to complex medical terminology or subtle details.

At Celegence, we leverage advanced tools like CAPTIS^® to streamline the SLR process. CAPTIS^® is an AI-powered platform that automates many of the labor-intensive tasks involved in SLRs. Here’s how CAPTIS^® enhances the SLR process:

• Automated Literature Search and Screening: CAPTIS^® quickly searches and de-duplicates identified literature from a multitude of different databases. CAPTIS^® allows for automatic download and storage of articles where the full text is available freely online making the analysis easier with immediate access to data. With the use of specific keywords CAPTIS^® can also highlight potentially relevant or irrelevant articles. This significantly reduces the time and effort required for the different stages of the review process.
• Data Extraction and Summarization: CAPTIS^® automatically extracts relevant information from research articles, such as study type, study subjects, demographics, interventions used, and adverse events. This information is summarized within seconds, allowing medical writers to be more efficient and consistently meet deadlines. CAPTIS^® also facilitates identification and extraction of adverse events in a way that reduces or eliminates the subjectivity and inconsistencies when handling large data sets manually.
• Enhanced Collaboration: CAPTIS^® enables seamless collaboration and communication among team members. From literature search to screening and appraisal, team members can collaborate and leave feedback on the platform itself

In a recent project, Celegence utilized CAPTIS^® to conduct an SLR for a medical device manufacturer. The AI-powered platform automated the literature search, facilitated faster screening, and automated the data extraction processes, reducing the time required for the review by an impressive 60%. The data extracted was also presented consistently despite being a large volume negating the need for additional time to be spent on standardizing the content prior to data analysis.

This allowed the regulatory team to focus on data synthesis and analysis, ensuring a thorough and accurate evaluation of adverse events.

Systematic literature reviews are a critical component of regulatory compliance for medical devices. By leveraging advanced tools like CAPTIS^®, regulatory professionals can streamline the SLR process, improve efficiency, and ensure compliance with regulatory requirements. At Celegence, we are committed to providing innovative solutions that enhance the safety and performance of medical devices, ultimately improving patient outcomes.

See how our AI-powered solutions can transform your regulatory processes. Contact us at info@celegence.com to learn more.