People with autism and learning disabilities are being denied their right to live “independent, free and fulfilled lives” in the community, a House of Commons committee has concluded.
The House of Commons Health and Social Care Committee inquiry into the treatment of people with autism and learning disabilities published its report in July, saying a lack of community care provision was to blame, caused by insufficient funding. The MPs heard how more than 2,000 people with a learning disability or autism are stuck in inpatient care settings and the average length of stay in an Assessment and Treatment Unit (ATU) is now six years, largely because there is no suitable community care to move on to.
Such care is never cheap when delivered to the high standard everybody wants. While the UK government’s new National Disability Strategy promises investment in housing and accessibility, no immediate answer to the financial difficulties is likely in the wake of the pandemic. It means care providers will have to be more innovative, especially when it comes to using technology.
Some are already embracing technology-based solutions that improve outcomes without extra resources. In the NHS, for example, the South West region has used remote monitoring and digital capabilities to help people with learning disabilities manage their long-term conditions such as diabetes and heart problems.
In the supported accommodation and residential care sector, advanced technology is proving its potential to improve lives while alleviating the pressure on resources. Machine learning (ML) and behavioural analytics combined with remote monitoring sensors enable service-users to live with greater independence, handing providers the power to focus their staff’s efforts where they are most needed.
This offers significant gains for everyone at a time when the care sector is facing a shortage of learning disability professionals. Long-term low pay combined with Covid and Brexit are also responsible for difficulties in recruiting care and support workers.
What makes these ML-based solutions uniquely relevant is their ability to learn from masses of service-user data, spot patterns and flag up when an individual might need help to prevent more serious deterioration. In a home or residential care setting this has huge potential.
In a service-user’s accommodation, ML solutions use data from sensors monitoring movement, energy use or biometric data to establish their pattern of behaviour. The source of data could be a Fitbit-type wearable device monitoring heart rate, or sensors registering the use of power and domestic appliances. Most service-users tend to have established routines, making it possible to establish an individual’s behavioural baseline of normality.
Organisations can set thresholds appropriate to a client’s condition, creating a “flightpath” of what normally happens. ML will spot when the client’s behaviour moves away from the norm, alerting care providers so they can intervene early. That could initially be a phone or intercom call or a visit to establish why the client is behaving differently, offering the opportunity to take preventive measures before a problem develops into something that demands more complex treatment.
The accuracy of the data and the insights extracted reduces unnecessary call-outs and visits, while providing firm evidence on which to base decisions about care and resource allocation. Whereas service-users may be unable to discuss symptoms of a new problem, the insights from the data provide care-givers and clinicians with firm evidence they could never obtain otherwise.
Since cloud-based ML solutions work on a wide range of unobtrusive devices, including smartphones, they eliminate the need for large and often very unpopular medical hardware and monitoring technology.
This is a far more sophisticated, preventive approach than traditional hardware-based, reactive systems that rely on alarms or use rigid rules that cannot adapt to individual behaviour and cause false alerts. Rather than waiting for critical incidents, such as trips and falls to flag deterioration, ML can spot the minor changes in behaviour that could indicate a new symptom. It is then open to care professionals to decide whether intervention is required. A simple example would be less frequent use of taps, kettle or toilet, indicating a potential problem with hydration, even though the client may be maintaining mobility.
The days when such data was hard to understand have gone. Today’s behavioural ML technology is not only capable of analysing vast amounts of data, its insights are immediately comprehensible to providers and care-givers. In a more sophisticated platform, the data will be formatted so different organisations in unified care pathways and networks can also access it, as appropriate.
The huge potential for this technology is why it is already undergoing trials within local authorities and the NHS where it is cutting care costs through reduced visits by carers and lower rates of hospital admission. A trial of an ML behavioural analytics solution in Dorset, for example, is saving nearly £4,000 per person annually through reduced visiting of elderly people and those with long-term conditions.
Free from ties with specific device-manufacturers, and with low costs of implementation, ML-driven behavioural analytics systems have major potential to help solve the significant problems care-providers face when trying to give people with learning disabilities a better quality of life.
If we are to rise to the challenge of providing high quality care, coupled with a sense of independence, to those who need it most, organisations need to be open to these innovations, now more than ever given the current strains on the system. Advances in technology such as behavioural analytics enable people with learning disabilities to live with greater independence and dignity, which is what any society should be striving for.
By Nick Weston, CCO, Lilli
