The Extraordinary Ways Elsevier Uses Artificial Intelligence Improving Healthcare And Cancer Diagnosis

Bernard Marr,
Founder & CEO, Bernard Mark & Co,

Elsevier started by digitising the vast troves of information it has generated in its 140-year history through publications such as The Lancet and Cell. These were then combined with new Big Data sources, such as user demographics and behavioural data, and more recently de-identified clinical data.

The final step was to build cutting-edge analytics tools capable of generating insights and creating products that make it easier for scientists, medical professionals, lawyers and researchers to put these insights to work.

In this article, I will focus specifically on artificial intelligence. Just a few years ago, AI might have been a phrase we were most likely to come across in science fiction. Today, however, it is used to describe an emerging breed of tools which are capable of ingesting large volumes of data, understanding it, and learning from it how to become more efficient at generating insights.

This has been made possible through advances in “smart” computing technologies such as machine learningand deep learning. The theory behind machine learning – software algorithms which are able to adapt themselves based on data they are fed – has been around for a while, at least since the 1960s. Only recently, however, has been enough data, as well as enough processing power, to put it to use.

As soon as those milestones were reached, it was immediately obvious how potentially powerful and useful this technology was. This is why ideas which just a few years ago would have been considered outlandishly futuristic, such as self-driving carsand real-time translation devices– are now a reality.

When Elsevier, as publishers of a significant amount of the world’s medical literature, considered how to make AI work for its customers, healthcare was an obvious starting point.

Elsevier’s mission is focused on building advanced clinical decision support solutions. These tools use information gathered from Elsevier’s extensive repository of clinical evidence, combined with clinical, financial and operational data, to suggest the best course of care. These “clinical pathways” support care standardisation and ensure that each patient receives the best evidence-based care.

“We get over 80% adherence to our pathways by clinicians, and when they do go off pathway, which is sometimes appropriate, we review the data and may revise our recommendations where necessary,” says Dr. John Danaher, president of Clinical Solutions at Elsevier.

Using AI for clinical decision support

The next step of the process is to augment these decision support systems with machine learning and deep learning. This should mean more accurate predictions, more efficient treatment and better patient outcomes.

Danaher explains it like this: “If you think about a healthcare enterprise like a hospital, you’ve got radiology departments, pathology departments – all these different areas which are running tests, doing studies; they’ve always generated a huge amount of data, but traditionally it’s all been paper-based.

“What we have now is this tremendous penetration of healthcare delivery systems capturing all of this information digitally: there’s administrative information, clinical information, insurance claims – and the whole area of genomic data.”Danaher tells me that when you aggregate this data, the value comes in two ways:

1. The large amounts of data increase predictability and produce more accurate models

2. Clinicians get a more accurate and holistic understanding of individual patients by bringing together their clinical history, their claims data, genomic data, etc.

Expanding on this, Elsevier is now leveraging artificial intelligence technology in its clinical decision support platform.

Based on all the information in their journal articles, books and databases, Elsevier uses natural language processing to generate disease to symptom models.

As Danaher explains: “We were able to train these predictive models on large patient databases. We built an application that generates a differential diagnosis based on a patient’s symptoms and medical history. It gives you a weighted differential: for example, it says, ‘With those symptoms in a person of this age and gender and existing conditions, there’s a 70% chance it’s one diagnosis and a 30% chance it’s another.’”

Based on what the models know from other cases they have been trained on, they will assess whether a particular set of symptoms warrants further testing.

“You can see the ramifications for how people will do clinical research in the future too,” Danaher says. “It’s going to be driven by routine medical data.”

Accelerating drug development with machine learning and Big Data

In addition to improving patient outcomes, widespread adoption of this technology will speed up the time it takes for new treatments and medicines to be made available.

This is currently a multi-year process; a timespan of 10 years is not uncommon from the first tests showing that a treatment is effective, to the drug being made widely available. It’s also very expensive, with a high failure rate.

Machine learning, driven by Big Data, gives us the potential to drastically cut the lag between discovery and deployment, Danaher tells me.

“What can happen now, based on aggregated patient data, is you can take 1,000 women treated in one hospital and 1,000 from another, and you can take that data, normalise it, and run analytics against it.

“So in the space of about a day, you’ve got actual patient data that you can make assertions on – and say, for example, ‘If you use this therapeutic drug, or do all of those things in a certain sequence, this cohort of 1,000 patients will live 20% longer and have 15% fewer side effects.”

Next step: Precision Medicine

Elsevier’s work is a prime example of how, once a business has passed the first hurdle on the road to digital transformation – the digitisation of its data assets – those assets can be repurposed through advanced analytics and AI to derive new value.

Elsevier is now in talks with leading academic medical centres to further improve and clinically validate the AI component of its decision support platform – known as the Precision Medicine Differential Diagnosis Tool.

This technology will lead to quicker and more accurate diagnosing while considerably shortening the journey from discovery to delivery of life-saving insights. It will also reduce unwarranted care variation, standardising care delivery with evidence-based practices.