New research project on post-market surveillance for medical devices relies on state-of-the-art artificial intelligence methods

7. August 2020

DHC Business Solutions is working with its partners on an innovative solution for medical product manufacturers: A new service platform to make post-market surveillance and risk assessment simpler and more reliable. State-of-the-art artificial intelligence (AI) technologies and methods are used in the process. The SmartVigilance research project is funded by the German Federal Ministry of Science and Research (Bundesministerium für Wissenschaft und Forschung) and has now started its work.

Medical product manufacturers are subject to strict regulations regarding the safety of their products. Regulations affect both product approval and the post-market phase. Companies are required to monitor their products on the market and in use as part of Post-Market Surveillance (PMS) and to take appropriate measures to eliminate possible defects or reduce risks.

“We know from many discussions with medium-sized companies that PMS causes a lot of expenses and can hardly be done satisfactorily by conventional means, i.e., a manual search in corresponding databases,” emphasizes Dr. Wolfgang Kraemer, Managing Director and partner of DHC Business Solutions. Yet the topic is eminently important. It is a matter of patient safety: “We want to automate the process as much as possible and rely on artificial intelligence processes and technologies.”

In the “SmartVigilance” project, an web-based service platform is being created that can automatically record and analyze dangerous incidents and product defects reported to the regulatory authorities and report them to the manufacturers. To this end, the project relies on artificial intelligence (AI), especially natural language processing, machine learning, deep learning and data analytics. SmartVigilance uses neural networks to pursue a sub-symbolic approach to AI and differentiates itself from much more elaborate, ontology-based approaches.

With this mix of technologies and methods, publicly accessible databases can be searched automatically, such as the Manufacturer and User Facility Device Experience (MAUDE) database of the US Food and Drug Administration (FDA), the PubMed database for scientific literature in the life sciences and biomedicine, ClinicalTrials and Cochrane CENTRAL as global registers for clinical trials, and from 2022 the European database EUDAMED (European Database on Medical Devices). International standards and terminological resources – including the International Classification of Diseases (ICD10), the Medical Dictionary for Regulatory Activities (MedDRA), Medical Subject Headings (MeSH) or the product classification eCl@ss – are also taken into account to achieve multilingualism, semantic normalization and standard conformity. SmartVigilance is funded by the Federal Ministry of Education and Research (Bundesministerium für Bildung und Forschung, BMBF), FKZ 01|S20028A.

“Those who work with the SmartVigilance platform in the future will automatically receive notifications of problem reports, identify trends in the marketplace, and receive analysis on medical devices that can be incorporated into safety and risk reports for regulators.” explains Dr. Rudi Herterich, Managing Director and partner of DHC. “That is our vision. And with this, we want to simplify environmental monitoring, make post-market surveillance more reliable and relieve medical device manufacturers of the mandatory regulatory task of PMS.” DHC Business Solutions’ project partners are the German Research Center for Artificial Intelligence (Deutsche Forschungszentrum für Künstliche Intelligenz, DFKI) in Saarbrücken and the Freiburg-based Averbis GmbH, a specialist in text mining, machine learning and terminology management.