[object Object]

Article

Why is clean healthcare data the panacea for AI success?

By Jan Beger, Director Application Services, Healthcare Digital, GE Healthcare

Everyday there are new headlines on the rise of Artificial Intelligence (AI). It’s exciting and it’s inspiring. Is the saviour of our pressured healthcare systems nearly here? Behind the news and scholarly articles however, it’s slow going manipulating ideas and theories to create a market ready hero.

The success of AI is totally dependent on the size and quality of annotated data sets. Groups doing clinical research or developing algorithms need access to imaging data sets for training and validation. They are looking for very specific real-life cases that have been reported on by experts in their field to be able to ‘teach’ a computer algorithm to recognise the difference between healthy and diseased tissue or organs. Let’s take the example of lung nodule detection and classification algorithms. Rather than drowning developers in millions of random chest x-rays or scans, we should provide them with more specific data sets, such as, “non-smoker males diagnosed with lung cancer below the age of 40 years”. Extraction of the right data will accelerate the potential of AI.

Access to clean & diverse data helps re-imagine medicine

Healthcare is great at creating data. Hospitals store hundreds of millions of digital images and it has grown exponentially since CT and MRI took centre stage as a frontline diagnostic tool generating thinner and thinner slices of the body. But healthcare is poor at using all this data to create insights.

The solution would be to organise unruly data better, as the ability to survive in healthcare is increasingly based on how data is managed. We should consider having reports stored and demographics parsed into specific database fields so that the data can be queried and segmented in any and every way. This means searches and extraction of data can be run on patient population queries or on diagnosis type. This would help clinicians in hospitals now and support the future of innovations.

A Vendor Neutral Archive (VNA) can help. It houses medical images and files of clinical relevance from across the healthcare enterprise – drawing data from disparate systems, across multiple specialities using international standards such as DICOM. Accessed via a single standard interface, it can unify the clinical ‘ologies’ for a complete picture of patient data.

Interoperability: a bridge to AI

Creating an interoperable bridge between how we acquire and organize data coming from multiple sources, and the development of AI, will yield a new dimension for modern healthcare. Specialist staff resource pressures and the growing number of patients with complex conditions are set to stay. The amounts of data we see today is only a fraction of what will exist in five years. It is by managing patient data better and using analytics that we can turn the healthcare kaleidoscope to gain more control on the sequence of events and outcome patterns.

Interested to know more about AI?

Watch our webinar Embrace AI, don’t fear it!

During the live discussion our thought leaders answer key questions on analytics and artificial intelligence:

  • What’s the AI status compared to the hype?
  • How & where will AI most impact Healthcare?
  • How will we ensure the use of AI is a success?
Watch it now