Home Industries Healthcare CTOs must not turn a blind eye to Natural Language Processing

Healthcare CTOs must not turn a blind eye to Natural Language Processing

by jcp

By Andreas Rindler, Managing Director at BCG Platinion

Artificial Intelligence (AI) technologies have gained serious momentum in the past five years and Natural Language Processing (NLP) – a form of AI which is essentially the computational decomposition of language – has seen tremendous growth.

In fact, a report from IBM found that NLP has emerged as the type of AI that appeals the most to organisations that want to automate processes. The same report also found that 52% of global IT professionals report that their company is using or considering using NLP solutions to improve customer experience, with 43% using it to increase cost efficiency.

And these benefits extend to many industries – but none more so than healthcare, where putting ‘human’ language into a form that computers can understand is extremely beneficial to the industry. This is because NLP offers the ability to improve areas of the business such as assisting with operations, customer service, and R&D. What’s more, it can provide summarisation of media and text, as well as acting as a transformative asset for hiring and HR.

While healthcare is a very human-to-human industry, it’s only just starting to explore NLP use cases. This investment must continue, and when taking into consideration that the healthcare sector traditionally lags behind in digital transformation, it’s a technology that healthcare CTOs shouldn’t overlook.

The linguistics perplexity 

There are roughly 6,500 languages around the world, with their own accents and dialects. This means it is considerably difficult to process them all effectively.

Thankfully, the power of NLP helps take this information and turn it into something that computers can understand, regardless of language. Ultimately, language is extremely complex, but technology can sail through this, enabling healthcare professionals to better interact with patients, but also give back employees more time to care for patients.

As it stands, NLP use cases are quite broad. There’s email or text classification, machine translation, virtual agents for customer service, call center automation or analysis and search of complex documents – and all can revolutionise the healthcare industry.

Activate lifesaving capabilities 

Powered by NLP, algorithms are able to recognise and answer patient’s questions online. In fact, the World Health Organisation’s site search does exactly that. By extracting key points and putting them into electronic health records within seconds, NLP can recognise doctors’ questions and patients’ answers, thus reducing doctor’s workload and enabling them to give patients more one-to-one personal care.

While it may seem that in the healthcare industry today the main use of NLP is an ability to process information, its benefits can even stretch beyond that. NLP can provide a greater degree of personalisation when providing care for patients.

NLP has the ability to offer much more empathetic treatment. Forms, such as feedback surveys can utilise sentiment analysis by understanding the different language used. For example, for patients with HIV, doctors will often focus on the efficacy of drugs and blood counts, but there can be some awful side effects to the drugs. Using NLP, if someone is recording how they’re feeling, getting sick, going to the toilet etc. then this can become a conversation between the patient and the clinician. NLP opens up the conversation that can go on to alleviate a patient’s problems.

And it doesn’t stop there. When NLP is combined with machine learning (ML) in healthcare it can help physicians make better decisions and aid clinicians in checking symptoms and diagnosis.  One study in 2018 used NLP to predict suicide attempts by monitoring social media. The system had a 70% prediction rate with only a 10% false positive rate.

While the statistics appear quite remarkable, the process is simple. It deconstructs language down into data, making sense of it.

Unbind and release the value of data

Ten years ago, we wouldn’t have thought of the number of steps we take or our heartrates as data. That’s changing thanks to activity trackers. In fact, 40% of consumers now have access smartwatches and fitness bands. The healthcare industry is able to make use of this data; for instance, Vitality is able to provide members with deals and offers based on their activity level, so why not use language data to also benefits patients?

Until recently doctors wrote all their notes by hand and then input very precise information into a computer. Now, doctors can tell a system to capture all the information they’re inputting, even if it has a very rigid input of data that may be restrictive.

NLP can extract relevant information like notes, diagnoses, patients records, typing up all the handwriting – essentially all the time consuming tasks. There are already several health start-ups offering this to healthcare organisations with transcription technologies that capture text and use a remote human transcriber to edit the automated text and produce a “structured” set of notes from patient visits.

Just like other industries, healthcare can go from the ingestion of data – who the patient is, their medical history – to classification which transforms data into something useful.

This means that there’s strong potential to start taking pretext data to predictive. This will offer healthcare professionals an understanding of what might happen in the future and required patient treatments. This isn’t a structured concept because humans are difficult to predict. NLP can help understand the most likely future issues and include data from example health profiles. That means, with preconceived information, NLP is able to generate a more precise diagnosis as it has more accurate, recent data.

It must be combined with human intelligence 

The benefits of NLP are endless. That’s not, however, to say that the healthcare industry should just be applying NLP without understanding how experts will use it. Until healthcare CTOs clearly understand the inputs and outputs then it will not be as useful.

Like any technology, we must combine its power with human capabilities. Many healthcare AI companies are run by white Anglo-Saxon males; understanding cultural nuance and inclusivity is crucial to improve each and every patient’s benefits.

That means NLP cannot be a substitute for human intelligence. It needs bionic-thinking – the synergy between human and machine, to allow NLP to really shine and give it a central role. Only then can it power innovation, efficiency, resilience, and most of all, allow healthcare professionals the opportunity to provide a greater level of care for patients.

You may also like