There is a question of detecting a an abnormality out of a radiology image – then a single data type is probably sufficient for making a diagnosis but how about more complex clinical problems? How we can address them?

Collecting multiple types of data
Another challenge is even if you got your hands on enough data, it’s generally going to be only one type of data, such as image data. But only a certain number of medical problems are solvable by looking only at images.
Single data type is probably sufficient. But many problems need data from more than just a single modality. Particularly in problems like a clinical prediction, more context about the patients provided by medical records data and pathology is usually needed.

As soon as you start talking about getting your hands on multiple types of data, the challenge is of getting that data in large scale explodes tremendously, especially when talking about multiple modalities. This is much more difficult because you need linked data across data types in each patient. Patient data is fragmented: e.g. images are stored in one place, and clinical data in another system entirely. Linking them all together requires enormous institutional effort. When that is scaled up across multiple institutions, it becomes extraordinarily challenging.

In your opinion, how could image analysis using AI help you decipher immunotherapy treatment response using high multiplex images and relevant statistics analysis?

KEEN EYE is the AI Platform company dedicated to deliver accurate, standardised and undiscovered tissue insights in research and clinical development using Deep Learning, for biomarker discovery, biomarker quantification and drug discovery.
KEEN EYE has strong expertise in image analysis in a wide range of therapeutic areas and enables its customers to use its solutions as tools for research & discovery purposes, in pre-clinical & clinical studies, translational research and diagnostics.
www.keeneye.ai

Neotherix has a patented wound sampling technology designed to allow biomarkers indicative of the healing status of a chronic or problem wound to be captured and then analysed and quantified. We would like to identify a suitable diagnostic technology for this task (lateral flow assay, quantum dot-based technology, or others we are not yet aware of) that could perform this analysis and rapidly and simultaneously quantify selected biomarkers to provide clinicians with data on the healing status of the wound. Which academic groups have suitable candidate diagnostic systems?

RegeneriTherix is a theranostic system combining the therapeutic benefit of a tissue repair scaffold with a novel wound sampling approach that allows removal of small aliquots containing biomarkers released by reparative cells involved in the wound healing process. These biomarkers can then be quantified to gain an insight into the healing/non-healing status of the wound (diagnostic component). Through funding from Innovate UK and National Institute of Health Research, we have gained Proof of Concept and have designed (and gained approval for) a clinical trial to gather evidence of safety and overall performance. We would like to identify and select the most appropriate diagnostic system to partner with our technology that could provide the clinician with data on an array of biomarkers that could be used to guide treatment decisions and the selection of the most appropriate wound management product for a particular wound and patient.

Is there any interest in the development of a validated more cost effective method for measuring therapeutic drug levels in serum?

Therapeutic drug monitoring is a major restrictive factor currently in the UK with many antimicrobial medications. For several medications there are only several sites that can provide these specific TDM services but they are costly. This has an effect on the number of treatment options for many clinicians that do not have access to these services or who deem them too costly. An increase in available more cost effective TDM methods would in theory have a positive effect clinically.

With regards to the development and standardisation of real-time PCR assays, what efforts have been made into incorporating additional RAM detection (resistance associated mechanism) that confer azole acquired resistance to A.fumigatus and other filamentous fungi?

In the interest of antifungal stewardship and patient care, a key issue that many of the tools we have for fungal diagnostics such as microscopy and imaging, lack direct resistance data. Although we have culture this is a slow process with varying sensitivities.

Developing trends following the COVID-19

With the changes due to COVID-19, what are the main trends in developing prognostic and CDx kits?

Which indication area would be best suitable for our personalized Diagnostic system for Oncology?

We are now working on a system for personalized diagnostics for lung cancer. We would like to discuss which indication area should we look at next? Any indication where we can obtain a tissue sample is an option. What is hard to diagnose, where is there an urgent need and patient benefit