AI gives shot in arm to patient health

By Ken Wieland

30 July 2019

LONDON — The headline figures are eye-catching. According to what consultancy Ernst & Young (EY) describes as an independent report, entitled Realising the Value of Healthcare Data, clever use of anonymised patient data – advanced datamining, for example, using AI and natural language processing – could lead to an annual £9.4 billion benefit to UK taxpayers. The figure is based on improved health outcomes for patients and greater operational efficiencies for the UK’s National Health Service (NHS).

To keep within the bounds of patient data confidentiality, the report provides a suggested framework in which the NHS can ethically harness and process patient data. In short, this means that the type of data collected is not individual patient records. “Only the processed output, which is linked data-sets run over an extended length of time — making it anonymous — are of use in the advancement of medical research and improved patient care,” said the report.

Related: The AI Will See You Now: Machine Learning in Healthcare

“Patient-level records will trace a complete story of a patient’s health, wellness, diagnosis, treatments, medical procedures and outcomes,” said Pamela Spence, EY partner and global health sciences and wellness industry leader. “This can only be delivered by unlocking the power of data. But value isn’t in the data itself — it’s in the power of the analytics and the clever insights that can be generated from algorithms, and the actions that can be taken as a result. Value will come to those who can innovate to produce health outcomes tailored to individuals, with high degrees of precision and personalisation.”

The EY report stressed that analytics and predictive models are helping address one of the biggest costs to health care, namely the treatment of chronic diseases. The main factors that influence the risk of developing chronic diseases include medical history, demographic and socioeconomic profiles. By aggregating data related to these factors, the idea is to sharpen predictive analytics to help identify those individuals who are at risk of suffering from these chronic conditions.

“Advanced data mining, such as AI and natural language processing, will help reveal patterns and trends that will allow health care providers and other stakeholders to improve diagnoses, treatments and operational effectiveness,” said the report.