Iris.ai presents:

Post Market Surveillance Automation

Post Market Surveillance is for many pharmaceutical and medical device companies required, essential, highly regulated – but rarely value-creating. It is tedious, time-consuming, repetitive and systematic – which is bad news for the highly skilled and educated people performing the work. However, the good news is that this also means it lends itself very well to automation.

We have developed a set of modules to bring machine learning automation to the bottlenecks of PMS. Systematic literature reviews, including continued surveillance, advanced categorization and classification of all papers as well as extraction of the key data for continued surveillance means the future of PMS looks nothing like the manual past.

AUTOMATION OF YOUR PROCESS

You have your unique products, decades of expertise, your own internal manual processes for the Post Market Surveillance work, a set of formal requirements from the governing bodies of your jurisdictions and industry.

We have a large set of smart, machine learning-based modules all based on machine understanding of scientific text and data, which is essential for Post Market Surveillance Automation. The system is trained for science and can easily be custom trained on your specific domain for high precision.

Together we identify the most time-consuming, error-prone, and tedious parts of the process, and incorporate the automation modules into your existing workflow – sometimes with novel machine-enabled visualizations to help the human reviewer even further.

OUR PMS MODULES INCLUDE:

Literature matching from product description.

Our powerful engine for text similarity can rapidly match your product description with thousands of papers that are contextually relevant and similar, to build the starting point for your classification.

Dynamic document evaluation.

When you need to include/exclude documents without well-formulated criteria, the machine learns from your initial evaluations and dynamically reorders your review list in prioritized order.

Advanced literature list refinement.

When you need to narrow down large literature collections with advanced criteria requiring contextual understanding, this module allows a powerful combination of Context description and Entity tracking criteria.

Document and document
group summarization.

Summarization of groups of documents allows for rapid overview for the researcher, to know where to place their focus.

Highlighting of relevant information in documents.

Whether highlighting specific key terms and combinations from the advanced categorization, or whole paragraphs of i.e. disease descriptions, visual aid radically speeds up humans’ ability to process documents.

Extraction of all key data points from a large set of documents.

Automatic extraction of any key data points from text and tables into an excel sheet or database allows weeks or months of labor to be done in minutes.

Ongoing surveillance, monitoring and alerts.

After the human and machine has collaborated on a review, automatic rerunning of the review can be set up on a regular basis, complete with alert systems where needed.

Custom modules to solve your exact challenge.

Have a specific, scientific or medical text related problem you’re not seeing the solution to? Get in touch – we love a challenge!

WEBINAR:

How to automate post market surveillance with AI

DOMAIN SUPPORT

Our core engine is trained on a general scientific corpus, which provides an excellent starting base for further domain specialization. This means we will take a collection of ≈2,000 documents (usually research papers) from the field your company operates within, and train the machine on them. In this way, the tool has a more specific understanding of the terminology of the research you will be reviewing.

Pharmaceuticals

Our machine is already well versed in the chemical domain, and can understand context down to the chemical components. It will be further trained on your field of expertise.

Medical Devices

The machine has solid interdisciplinary understanding spanning electronics to mechanical engineering to diseases and chemistry and will be further trained on your field of expertise.

WHY IRIS.AI?

We have spent the last 5 years building an award-winning AI engine for scientific text understanding. Our algorithms for text similarity, tabular data extraction, domain-specific entity representation learning and entity disambiguation and linking measure up to the best in the world. On top of that our machine builds a comprehensive knowledge graph containing all entities and their linkages to allow humans to learn from it, use it and also give feedback to the system. Applying these on scientific and technical text is a complicated challenge few others can achieve.