We are excited to announce that Spectra Analytics (now Patchs Health) has won an InnovateUK grant to develop AI triage for primary care in collaboration the University of Manchester. The aim is to reduce GP workload and alleviate the mounting pressures on NHS primary care.
Primary care is the foundation of the NHS, accounting for 90% of all NHS contacts; over 340m consultations per year. Over recent years it has come under significant strain due to increasing demand, a hiring/retention crisis, and budget constraints. These pressures are exacerbated by avoidable GP consultations: in many cases, patients would be better attended to by other healthcare professionals, such as a nurse or pharmacist, or else with appropriately-guided self-care.
Such unnecessary consultations put GP practices under needless strain. They also endanger other patients with more urgent needs, who find they cannot see a GP when required. In fact, an estimated 27% of consultations are avoidable, with 6% of patients seen by another professional within the practice and 4% seeing pharmacists or using self-care [1].
The problem is caused by the lack of effective triage processes (deciding where to send patients). Currently, triage often relies on non-clinical staff such as receptionists, which does not optimise patient safety. Patchs’ work begins in the conviction that the implementation of more effective triage processes could dramatically reduce the workload on GP practices.
There have been a number of attempts to improve triage in the past. One in particular, ‘Telephone First Triage,’ asked GPs to triage patients during a telephone callback each time an appointment was requested. However, new research has found that whilst face-to-face appointments fell 38% on average using this approach, telephone consultations increased 12-fold – and ultimately, GP workload was actually increased by an average of 8% [2]. In addition to this questionable effectiveness, telephone triage is not scalable. This is because it requires constant support from GPs.
An alternative solution is to use Artificial Intelligence (AI)-based triage. This is Patchs’ approach. We believe that AI triage is well-suited to primary care due to the large amount of patient data available, which allows the algorithm to identify both common and more unusual ailments. With our grant from InnovateUK, we intend to evaluate the feasibility, efficacy and impact of AI triage in primary care.
[1] Primary Care Foundation & NHS Alliance, 2015, Making Time in General Practice
[2] BMJ, 2017, Evaluation of telephone first approach to demand management in English general practice
