Top

Saving lives: 5 ways data science is transforming modern healthcare

From remote diagnosis to personalised treatments, data science is starting to give healthcare and Life Sciences the shot in the arm they desperately need.

Healthcare has come a long way over the last couple of centuries. We’ve gone from cleaning blood with leeches and biting sticks for pain relief, to an age of advanced medicine, anaesthesia and preventative treatments.

But there’s still a long way to go.

Today, practitioners are feeling the pressure of ageing populations, patients with multiple chronic conditions and underfunded infrastructures. The only way to overcome these problems is to make diagnosis, treatments and hospital operations more efficient and effective. And to this end, data science might be just what the doctor ordered.

Here are five ways analytics and data science are transforming healthcare today – and creating a better future for us all.

Data-driven diagnosis

In many cases, early diagnosis is the key to successful treatment. But, with doctors’ surgeries stretched to breaking point and hospital communications still relying on fax machines, it’s not always possible. Things get missed, caught late, or sometimes not identified at all.

In an effort to address this, some hospitals have started using big data analytics to fuel diagnostics. And they have no shortage of data to play with. In fact, the healthcare industry holds an estimated 30% of the world’s warehoused data.

The results have seen patients diagnosed days and sometimes weeks faster – and with greater accuracy too, which is vital when you consider that diagnostic errors result in up to 80,000 annual deaths in the US alone.

This data-driven approach can be seen at Seattle Children’s Hospital, where data from 10 different source systems provides staff with a holistic, on-demand view of essential patient care information. Meanwhile, at University College London, AI has recently been able to diagnose heart disease in just four seconds.

Personalised medicine

Any conversation about healthcare and data science usually includes the subject of personalised healthcare, or ‘precision medicine’ as it’s often known.

The principle behind precision medicine is simple: we’re all born with a different biological makeup and raised in different environments, so a one-size-fits-all approach to treatment makes little sense.

Thankfully, technological advances mean truly personalised treatments may not be too far away. It all comes down to how easy it’s become to look at someone’s genetic makeup. Where the first human genome took 13 years to sequence, we can now achieve the same thing in a matter of hours. And genetic information that cost around £2 billion to extract in 1990 can now be attained for less than £200.

With this technology now far more accessible, pharmaceutical companies can start showing insurance companies and governing bodies the value of more tailored and therefore more effective treatments—which means we may be seeing them on the market in the very near future. Life Sciences companies are also leveraging real world evidence and real world data to prove efficacy of drugs and new treatments such as gene therapy.

Precision medicine may not be a universal panacea, but it certainly throws up some exciting possibilities. For example, a personalised approach to healthcare could see us identifying and removing genes known to pass on diseases from future generations.

Improved hospital efficiency

Hospitals are busy places, and when it comes to emergencies, there’s no room for error. Understaff a ward or keep people waiting too long and the consequences can be significant – which is why some hospitals have started using data to make sure this doesn’t happen.

Currently, four Paris hospitals are using data from 10 years of admissions records to predict peaks in demand, and leveraging the insights to staff their wards accordingly. If it proves successful, another 40 hospitals will soon follow suit.

Similarly, at the University of Chicago Medical Center, predictive analytics is being used to make operating rooms as efficient as possible. Forbes reports that these improvements are expected to save the hospital $600,000 a year – a vital saving when you consider the spiralling costs of healthcare. The other big benefit, of course, is healthier patients and happier staff.

Self-service healthcare

Booking a doctor’s appointment today is far from easy. But the good news is, soon you may not need one.

Mobile health apps have tripled in popularity over the last four years, and as it becomes easier to share and analyse data, they may soon be able to diagnose health problems faster than a visit to your doctor.

One trailblazer in this market is UK-based Babylon Health, which partnered with the NHS and Bupa to develop a healthcare app that now has 1.4 million members across Europe, Asia and Africa.

It uses a combination of AI and remote consultations to identify illnesses, deliver health status assessments and triage necessary actions. Assuming the UK government makes good on its promised £250 million investment in healthcare AI, applications like this could do a great deal to alleviate the strain on both GPs and hospitals in the near future.

Pharmaceutical companies stand to benefit, too. These applications can prove a valuable source of data, resulting in more informed drug development, improved clinical trial recruitment and better quality of life for patients—not to mention million-pound savings.

Faster drug discovery

According to Springboard, it typically takes $2.6 billion and 12 years to bring a new drug to market. Big data analytics and machine learning can significantly expedite the clinical research process, in turn dramatically reducing R&D costs.

In recent tests, data has been used to simulate the body’s reaction to drugs under different conditions, resulting in faster approvals from governing bodies and more effective treatments.

With returns on pharmaceutical R&D investments at their lowest in decades, this technology could be vital. In fact, McKinsey estimates that big data and machine learning in pharmaceuticals and medicine could generate a value of up to $100 billion a year.

A brighter healthcare future for all

From diagnosis and treatment, to hospital operations and aftercare, there’s almost no end to the ways data science can enhance the healthcare industry and augment the efforts of the talented individuals who work within it. And it looks like analytics may hold a lot of the answers struggling practitioners and institutions need.

  • Prasad Kothari

    Prasad Kothari is an analytics and data science leader who has worked extensively building high-performing teams for various organizations and has provided consulting to many fortune 500 clients. As vice president of analytics and client solutions at The Smart Cube, he focuses on helping clients realize the value of data science to solve priority business problems, including customer analytics, marketing analytics, RWE/RWD, and supply chain analytics. Prasad has published healthcare data science research papers across leading journals, as well as books on AI. He has collaborated with several universities in the US and given guest lectures on Quantum Machine Learning, NLP/NLU, topological data analysis and computer vision research. He spends his weekends reading AI books and listening to Indian classical music.

  • Prasad Kothari

    Prasad Kothari is an analytics and data science leader who has worked extensively building high-performing teams for various organizations and has provided consulting to many fortune 500 clients. As vice president of analytics and client solutions at The Smart Cube, he focuses on helping clients realize the value of data science to solve priority business problems, including customer analytics, marketing analytics, RWE/RWD, and supply chain analytics. Prasad has published healthcare data science research papers across leading journals, as well as books on AI. He has collaborated with several universities in the US and given guest lectures on Quantum Machine Learning, NLP/NLU, topological data analysis and computer vision research. He spends his weekends reading AI books and listening to Indian classical music.