RECORDS, DATA & DOCUMENTS XXXX
How data analytics can improve patient care Sam McCaffrey reports on one of the big trends in healthcare.
‘B
ig data’ and ‘data analytics’ are not just abstract concepts: they have a solid real-
world application.
For example, in 2012, Mastodon C, part of the Open Data Institute, spent eight weeks analysing publicly-available NHS prescriptions data, looking at prescription patterns for statins. The current evidence shows that for most patients, all drugs from this class are equally safe and effective, so doctors are usually advised to use the cheapest. But the new analysis found that £27m a month was being spent on more expensive proprietary statins rather than cheaper generic alternatives. If the research had been done a year previously, more than £200m could have been saved.
Dr Mark Davies, former medical director of the Health and Social Care Information Centre, who now works in healthcare performance analytics in the private sector, believes real- world applications of data couldn’t be more important to the NHS.
He told NHE: “In health and social care, not only have we got significant financial challenges in terms of meeting what we need to do, we have reached a point where frankly we cannot keep doing things the way we are with the current model of provisions.
“So we need to go through significant changes of models of delivery: reconfiguration and service redesign. We are unable to do that without the evidence that backs up our decisions, and data is the way that we will build that evidence.”
Commissioners and providers have been using data analytics to streamline and save money for some time, but there is now a clearer focus on patient care.
East & North Hertfordshire CCG started to use data analytics in a more serious way three years ago, when it was a PCT. It started with
62 | national health executive Nov/Dec 14
data validation, but now uses analytics in a more rounded way across wider data sources, integrating with social care, community contact information and mental health data.
David Hodson, head of information at East & North Herts CCG, said one of the benefits of the MedeAnalytics software the CCG uses is that it is available in GP surgeries, so the clinicians can also use it to inform clinical decisions and care pathways.
“From our perspective – the CCG top level – we’re viewing the information in a scrambled way so we can’t identify the patient, but we can actually start seeing, monitoring and assessing how well the services we’re putting in place are doing,” he said. “But then at the clinical end they are able to identify the patient and then look at the individual pathway and see if the service they’re receiving is the best for that patient in that situation. So it’s actually setting up an integrated dataset that we’ve got those multiple different purposes for.”
Wayne Parslow says we are on the road to “unleashing the real power of big data”. Parslow, general manager of EMEA at MedeAnalytics, believes data can be used to personalise healthcare for every patient, with a focus on preventative healthcare.
Dr Davies said: “This is about moving away from a data model based around organisations and moving towards one based on patients. We [can] use data to actually build an integrated model of the experience that patients have.”
East & North Herts has a programme to achieve this: HomeFirst, a rapid response service supporting older people and those with long- term or complex conditions to remain at home rather than going into hospital or residential care.
Data analysis is used to identify patients
potentially at risk of being admitted, and a nurse-led team helps manage their care in their own home, often helping keep them there and avoiding hospital when and if their condition worsens or becomes acute. In one example, an 80-year-old patient was admitted to the HomeFirst team following his wife’s call to their GP. The patient had had a fall and become progressively more immobile and bedbound. The patient’s wife was housebound.
HomeFirst were at the patient’s house within 14 minutes of taking the referral call from the GP. The patient immediately got occupational therapy, physiotherapy and homecare services, which enabled him to stay at home and not be taken into hospital. He recovered and was discharged from HomeFirst after 10 days.
After a successful pilot stage, the scheme was rolled out across north Hertfordshire in July. Emergency activity in the pilot area reduced, against the national emergency activity.
trend of increasing
HomeFirst is an example of not just integrated care, but also of integrated data – with datasets from all the different agencies being pooled. Hodson said: “We want to roll [HomeFirst] out across a wider area, but once we start to produce a bigger integrated dataset, we then want to start to explore any additional schemes we can start putting in place.”
Parslow added: “We’re starting to see the data coming together from social services, from local authorities, from mental health trusts, from ambulance trusts and so on, which allows us to get the picture for the entire package of treatment that is applied to a particular patient, or a cohort of patients, or a disease type that will allow us in the future to treat them far more effectively.”
TELL US WHAT YOU THINK
opinion@nationalhealthexecutive.com
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96 |
Page 97 |
Page 98 |
Page 99 |
Page 100