Digital health apps offer new technologies to help a growing and aging population self-manage increasingly complex conditions and comorbidities. Patients demand empowerment to enable them to manage their treatment more independently. Such developments, from the very straightforward to more indepth solutions, can result in lower treatment costs to the patient and the NHS.
This series of blog posts will focus on behavioural activation and the way that the adoption of digital health applications can assist with such an approach to treatment. We will consider:
- the rise of app-reliant health support – how Healthcare Professionals manage and navigate through the apps available, clinician prescribed VS patient choice
- how developers build apps that conform to standards
- the difference between informing and changing – striking the balance between giving accurate and useful information
- providing the means to help patients change behaviours based on ‘The States of Change’ model
The first part in the series will focus on the increasing number of apps available on the market and how HCP’s are dealing with this.
Conforming To the New Norm
Smartphones allow the industry to create apps that are an extension of patient treatments, outside of the doctor’s surgery. They’re designed to push the right information to the right person at the right time.
App developers must conform to health app criteria as outlined by gov.uk. There must be evidence that the apps improves outcomes for patients and users, provides value for money, meets user needs, and is stable and simple to use.
“All apps must be clinically safe: this means that they they’re safe for people to use – not just for healthcare professionals and patients but everyone involved in creation, testing and approval of the apps.”
Apps must capture and handle data sensitively, legally and securely, and usability and accessibility must be considered to mean the app is inclusive of those with disabilities or those with a limited technical knowledge.
Should Healthcare Providers Prescribe Apps or Let Patients choose? Or both?
On the other side of the coin is the recommendation and administration of such apps from HCP’s. The NHS released the NHS Apps Library last year, accessible to the public to help them make informed choices about the apps they choose. This is the one of the early stages of patient empowerment during treatment as the notion of choice stimulates positive behaviour activation.
HCP’s can refer to the Apps Library to help provide better informed recommendations, as each app has been quality standardised and is compliant according to the NHS.
Some apps are labelled, NHS Approved meaning those select few meet NHS quality standards for clinical effectiveness, safety, usability and accessibility and are backed by strong evidence supporting improvement of patient outcomes
However with over 165000 health apps currently in circulation in app stores it’s equally as easy for a patient to “self-diagnose” which can of course present many dangers.
Some HCP’s remain reluctant to adopt their use in clinical practice
The vast majority of digital health apps available from app stores aren’t certified by the NHS, therefore they’re without the thorough understanding of risks and benefits. A patient might discover an app that they’re confident will assist with their treatment. The purpose of an app is to provide quality and safety with accurate information and guidance to the end user in order to improve patient outcomes, but unlike medication such treatments aren’t scientifically measured, so if it’s not approved by the NHS, it’s generally at the HCP’s discretion whether to approve its use for their patient, which can be problematic.
Disruptive. In a Good Way
Mobile Health – AKA “mHealth”- has notable benefits globally, especially in developing areas of the world. Countries such as Africa are emerging with “ a great deal of innovation, because the need for low-cost solutions for pressing health issues has generated much experimentation and research that is likely to play a role in more advanced economies in the coming years
The distribution of a physical pill as part of a patient’s treatment, despite rigorous scientific testing, can still never assist with certainty in improving patient outcomes. As the world becomes immune to antibiotics it seems practical and imperative that another solution be brought to the doctor’s office. Unlike traditional medication, mobile apps have greater potential to assist with behaviour activation, as it encourages the patient to educate themselves by becoming actively engaged with a non-invasive treatment method.
In a previous blog post we discussed interoperability in healthcare and why electronic data such as EHR’s need communication improvements in order to function more effectively. We also discussed the NHS at 70 and the ways in which digital can be adopted into the wider healthcare sector to ensure another successful 70 years of the National Health Service.
“Interoperability is the extent to which systems and devices can exchange and interpret shared data. In healthcare, effective interoperability occurs when IT and software systems exchange shared data to create information that can be used to assist clinicians and other medical professions with patient care.”
Digital health apps have the potential to improve interoperability, as longer as there’s focus on training efforts, and apps that need to communicate with clinical systems must be compliant with the relevant technical standards.
At Bitjam we’ve recently developed an app called BeAble, with Combined Healthcare that bridges the gap between one-to-one appointments and discharge, enabling mental health patients to effectively manage their aftercare without the need for more appointments. The app is in phase two of testing, and each user has been given adequate training to use and administer it to the patient. Find out more here.
Next week we’ll be following up with a discussion about the difference between informing and changing patient outcomes, providing the means to help patients change behaviours based on The Transtheoretical model.
In the meantime if you want to discuss any of the matters surrounding patient empowerment, behaviour activation and digital health applications drop us an email for a chat.
What Is Interoperability in Healthcare
Interoperability is the extent to which systems and devices can exchange and interpret shared data. In healthcare, effective interoperability occurs when IT and software systems to exchange shared data to create information that can be used to assist clinicians and other medical professions with patient care.
Issues Healthcare Staff Are Currently Facing
“Staff suffer from increasing workload and stricter performance measures with less flexibility. This has caused psychological and physical stress…” Science Daily.com
It’s no secret that digitising healthcare IT systems has been a slow and frustrating process for all stakeholders involved, especially the end users who have the responsibility of delivering safe patient care in a secure manner. This adds further pressure to staff who are already suffering from increased workloads and limited resources.
“We physicians have the longest training time of any profession, yet we now spend roughly two-thirds of our workday as data-entry clerks, tending to digital paperwork and administrative burdens” – WSJ.com
How Is Data Currently Manifesting Itself in Healthcare?
- Notes entered into the EHR (electronic health record)
- Documents that have been scanned as image files or pdf documents
- Discrete data such as lab test results.
“The data arrives from many different sources and systems and in multiple formats. It has to be parsed into a format that everyone understands and has been trained to act upon in an appropriate manner” Alan Brookstone
- The Tech
Data presentation can negatively influence decision making if it is presented in an illogical or intuitive way
- Human Skills
The computer skills of all staff members and knowledge of their EHR has a significant impact on data interpretation. There are many reasons why some people are less digitally literate than others.
- Upgrades and Disruption
According to AmericanEHR one of the most frequent complaints of users is that their EHR does not have the necessary tools or capabilities to perform a certain function. Sometimes the staff are unaware that their EHR has the functionality as they haven’t been trained to use the product properly. In other cases their system may require an upgrade. Upgrades can be complex and entire servers may need to be shut down for maintenance. Consequently, upgrades are often delayed because of the disruption.
How Can We Succeed?
Lack of interoperability leads to poor outcomes, therefore the issue must be tackled to ensure quality control.
We believe merging simple-to-use, reliable technology and adequate human support and training will result in the ultimate success of any EHR implementation.
So a move towards cloud-based systems will have a definite advantage as the software is updated centrally by the vendor with limited need to update technology at the user end.
The most significant impact would become apparent with changes to government regulations. G Cloud is an initiative that assists with the procurement by public sector departments in the UK of cloud based commodity IT services. Traditionally, vendors have to be certified as compliant by the Department of Health which inhibits better products and slows down new system implementation. G Cloud is a way of shifting away from more primitive systems and offers a positive step towards improving the efficiency of EHR software and communication tools.
At Bitjam we pride ourselves on finding continuous ways to improve developer documentation, with cloud-based systems and use of more consistent data design at the forefront of what we do. Our mission is to use technology for social good, so if you have a digital healthcare problem that you’d like to solve, email us at [email protected] to find out more about our previous work.
Yesterday we introduced you to the latest project at Bitjam: ANNA. A learning algorithm that analyses poetry and audibly delivers it in an old-fashioned regional Potteries dialect, the project has been inspired by the bid for Stoke-on-Trent as the next UK City of Culture. We interviewed Liam Mountford, Senior Developer at Bitjam, about the technical elements of creating artificial intelligence (AI) that is able to independently learn.
Why did you have the idea to create a computerised system that creates poetry and delivers it in a potteries dialect?
The initial idea came about from a discussion between me and Carl. Carl knew I had an interest in machine learning from the work I did for my dissertation, I created a neuro-evolutionary algorithm that was to predict the results of the 2015 general election. I have had a number of discussions about neural networks and similar machine learning and AI algorithms with Carl, where I tended to ramble on about some of the more interesting aspects such as trying to create a Neural Network (NN) that could produce pieces of art. Carl liked the sound of a creative learning machine and formed the idea of using it to create potteries poetry.
From a more technical point of view, how does ANNA actually work?
Once we had our idea we sat down and had a discussion about the possible complexity of the project. A fully fledged bespoke neural network is quite a lot of work so we decided to try to find some existing neural networks to base our work off of. With the help of Jacob we found a Recursive Neural Network (RNN) designed to take text input and after a large number of training cycles we then tried to get ANNA to output some meaningful ‘learned’ poetry.
So, tell us more about neural networks.
In it’s simplest form a NN consists of 3 layers. The input layer accepts various inputs. In theory, as many or as few as you need. Next the hidden layer, this is the heart and soul of a NN and helps to create the correlating links between the various inputs supplied at the input layer. Finally the output layer, is the part of the NN that spits out – hopefully! – some sort of meaningful information. Where a RNN differs is that there is a recursive link between the output and hidden layer, this part is important as it helps the RNN to learn the structure of the language supplied. In turn this means that the particularly interesting part with the RNN is that it is able to learn dialects such as potteries.
How does ANNA learn poetry?
ANNA is a python script based on a simple RNN, we feed in around 200 pages worth of potteries dialect poetry aiming to produce some sort of meaningful poetry. Anna runs through about 500 recursive cycles of the input text per “epoch” of learning for a total of around 30 epochs. An epoch is essentially a single full training cycle.
What were the challenges of this project?
One problem that always rears it’s head is a shortage of data to feed into the RNN. So the next step for us was to source plenty of potteries dialect based poetry from poets past and present. First we tried to source as much poetry as possible from an online source, the main works we used were by Arnold Bennett. We then tried sourcing further poetry from Wilfred Bloor‘s sons Roger & Ian. Wilfred Bloor wrote over 400 Jabez tales in Potteries dialect (the Jabez character is a countryman living in the shadows of industrial Potteries). We also spoke to Alan Barrett, Stoke-born writer, storyteller, poet, and actor. Thanks to the kind contributions of these people we managed to collect plenty of poetry that has been fed into ANNA.
Come and see ANNA in action at the ACAVA Studios: Spode Works open studios event on Saturday 7th / Sunday 8th October from 12pm at Bitjam, studio number 22.