How clinicians can use AI in healthcare to improve patient outcomes

How clinicians can use AI in healthcare to improve patient outcomes

What is the problem you are trying to solve?

Professor Christian Guttmann from the School of Science and Engineering at UNSW and Nordic Artificial Intelligence Institute, and the Karolinska Institute (Sweden), suggests that all business cases need to start simply with this question.

For those who work in healthcare, he suggests that the solutions could potentially be Artificial Intelligence (AI). ‘Even if you don’t have a deep understanding of the technology, you need to have an understanding of what your problem is and how AI could potentially solve that problem for you.’

He also suggested that clinicians need to have a very clear understanding of how they define  health. Citing the World Health Organisation, he emphasises that health isn’t just the absence of disease, it’s about actively promoting the entire wellbeing of the person.

A thriving healthcare ecosystem, he argues, should seek to treat people in an efficient, accurate way, alleviating their suffering but also working to prevent illness and disease from occurring in the first place.

Prof. Guttmann is starting to see AI play a bigger role in how it can alleviate some of the problems affecting our healthcare systems, ‘the tedious complexities’ as well as ‘creating a personalised service that will scale.’

For example, he cited that in the UK, ‘half of all strokes and heart attacks occur in people who haven’t been flagged as “at risk.”’ The NSH used EHR data to predict which patients could potentially be ‘at risk.’ The result was that the model predicted 4,998 patients who went on to have a heart attack or stroke out of 7,404 actual cases, which was 355 more cases than the ‘standard doctor’s method.’

In another example, Prof. Guttmann’s company Healthihabits found that people newly diagnosed with diabetes are often left alone after that initial consultation and given limited guidance and support as to diet and maintaining wellbeing. His team created a network that could predict which patients would be most likely to support each other, which saw a vast improvement in long-term behaviour and management of the disease.

How to move forward

Prof. Guttmann acknowledges that AI is still very much in its infancy. He says, ‘that there are 106 start-ups that are transforming healthcare with AI.’ He predicts that the role of AI in healthcare and in business is going to become so vital, that he suggests that businesses start to think about introducing a Chief Artificial Intelligence Officer (CAIO), in the same way to advocate and keep businesses up-to-date with the latest developments in the area.

Quoting US Chairman of Kaiser Permanente, Bernard Tyson, he summed up AI in healthcare by saying, ‘I don’t think any physician today should be practicing without Artificial Intelligence assisting in their practice. It’s just impossible (otherwise) to pick up on patterns, to pick up on trends, to really monitor care.’

As the technology develops, it seems that AI could very well be the solution to the problem you are trying to solve.

Register your interest for CeBIT Australia 2018