Using an algorithm to improve interpretation of liver function tests
Liver function tests (LFTs) are frequently-requested blood tests which may indicate liver disease. LFTs are commonly abnormal, the causes of which can be complex and are frequently under-investigated. This can lead to missed opportunities to diagnose and treat liver disease at an early stage. NHS Tayside aimed to develop an automated investigation pathway which would maximise early diagnosis of liver-related diseases while remaining cost effective.
NHS Tayside wanted to detect liver disease at an early stage, potentially saving thousands of lives. They wanted to explore automated diagnosis and staging of liver disease in primary care.
Professor John Dillon, consultant gastroenterologist and hepatologist, and Dr Ellie Dow, consultant in biochemical medicine, worked with colleagues from NHS Tayside and the University of Dundee to develop the intelligent liver function testing pathway (iLFTs) to detect liver disease at an early stage, potentially saving thousands of lives. This uses the automated blood sciences laboratory infrastructure, the laboratory information management system (LIMS) and order communications system (electronic test ordering) at Ninewells Hospital.
Solution and impact
Using advances in laboratory technology, Professor Dillon and Dr Dow’s team created the new iLFTs which see more tests automatically carried out on a patient’s blood sample if there is a suspected liver disorder, or abnormal results with no clear explanation.
The team developed an automated, algorithm-driven system (the ‘intelligent Liver Function Testing (iLFT) pathway) that further investigates abnormal LFTs on initial testing samples. They integrated investigation algorithms based on minimal diagnostic criteria, liver fibrosis scores, and reflex testing for causes of liver disease into the LIMS. These algorithms generate a diagnosis and/or management plan which is returned electronically to the GP.
A stepped-wedge trial (a type of randomised controlled trial which is structured to reduce bias when testing new medical treatments, social interventions, or other testable hypotheses) design was used to compare LFT outcomes in general practices in the 6 months before and after introduction of the iLFT system. Diagnostic outcomes were collated and compared.
Use of iLFT increased diagnosis of liver disease by 44%. It was cost effective with a low initial incremental cost-effectiveness ratio (ICER) of £284 per correct diagnosis, and a saving to the NHS of £3,216 per patient lifetime.
GPs receive the results along with 32 potential outcomes, making it easier to identify the cause of liver dysfunction and give a firm diagnosis. This is complemented with lifestyle advice for those who need it, while those with advanced or complex disease are referred for further treatment.
The initial rapid 44% increase in diagnosis of liver disease due to iLFT gives patients earlier access to treatment.
Since being launched as routine service in NHS Tayside, more than 7,500 patients have been tested. The tests have now been made standard practice across NHS Tayside and the Scottish government’s Modern Outpatient Programme is considering the opportunities this might present, with work underway to roll this out more widely across Scotland. It has already been established in sites in England.
- The system combines patient demographics, clinical details and blood test results using advanced computer algorithms
- Results are compared with liver disease criteria produced by expert hepatologists and this allows a probable diagnosis, investigation and management plan to be generated
Additional tests are automatically undertaken to investigate suspected liver disorder or abnormal LFT results based on the initial samples from GPs and hospitals.
The laboratory information management system (LIMS) runs the algorithm to select which of the 32 outcomes the LFT has, and then sends those results, along with the interpretation, back to the GP. It all happens in under 4 hours.
Key learning points
iLFT increases liver diagnosis, improves quality of care, and is highly cost effective. This was achieved with minor changes to working practices and exploitation of functionality existing within modern laboratory diagnostics systems. This multi-award winning system is now live across NHS Tayside and has been used in more than 7,000 cases.
“Given the prevalence of liver disease, the implications for this test across the UK are significant. I am proud to be colleagues with the team and cannot emphasise enough the impact that this innovation has on diagnosis and management of liver disease.”
Dr Neil Greig, consultant clinical biochemist and clinical lead for biochemistry, NHS Tayside
Find out more
Dr Ellie Dow, Department of Clinical Sciences, Ninewells Hospital and Medical School
Professor John Dillon, clinical professor (Teaching and Research), University of Dundee
These case studies summarise user and patient experiences with digital solutions along the relevant care pathway. Unless expressly stated otherwise, the apps and digital tools referenced are not supplied, distributed or endorsed by NHSX, NHS England and NHS Improvement or the Department of Health and Social Care and such parties are not liable for any injury, loss or damage arising from their use.
All playbook case studies have either passed, or are currently undergoing the Digital Technology Assessment Criteria (DTAC) assessment.
Please note the full legal disclaimer: NHSX playbook disclaimer