Public Funding for Advanced Expert Systems Limited

Faecal immunochemical testing (FIT) measures faecal haemoglobin concentration (f-Hb). FIT can be used to manage patients presenting in primary care with unexplained lower gastrointestinal (GI) symptoms that may be indicative of bowel cancer in primary care prior to (or alongside) an urgent referral, or for triaging in secondary care to guide the management of referred patients. The threshold for a positive FIT result in symptomatic patients is 10µg Hb/g faeces. Any participant exceeding this pre-set FIT threshold value is referred for endoscopic services (e.g., sigmoidoscopy or colonoscopy) to identify any medically actionable cause of bleeding i.e., colorectal cancer (CRC) or a precancerous adenoma (polyp). Coupled to increased sensitivity of FIT vs. traditional guaiac-based f-Hb detection, the number of referrals from primary care for endoscopic procedures is rising. A 2021 study determined the positive predictive value of FIT in a low-risk symptomatic population was 7.0%. This indicates a false-positive rate of 93%, meaning 13 patients with f-Hb \>10 μg Hb/g faeces underwent sigmoidoscopy or colonoscopy to identify one CRC. There is an immediate and pressing **unmet need** to improve FIT's diagnostic yield for detecting bowel cancer. This will reduce endoscopy referrals, protecting patients from unnecessary invasive screening that can cause bowel perforation (a serious adverse event that can be lethal), and costs £322**-**£548 per procedure. Data already collected by the clinical collaborators to this project has revealed scope to modulate personalised FIT thresholds for symptomatic patients based on specific individual data variables that could help to refine onward referrals. **SOLUTION:** Advanced Expert Systems Ltd (AES) have joined clinical specialists from University Hospitals Coventry & Warwickshire Midlands NHS Trust, York and Scarborough Teaching Hospital NHS Foundation Trust (York), and University Hospitals of Leicester NHS Trust (Leicester) to develop an AI-based software platform 'BowelSys' to interpret FIT result in the context of other clinical and non-clinical risk factors associated with the development of bowel cancer. As a multivariate stratification model, BowelSys enables a personalised interpretation of FIT result and optimises clinical resources by risk. High-risk patients are fast-tracked for further investigation, whilst patients with low-to-no risk have further investigations delayed. This will enable clinical resources to be used more efficiently, with high-risk patients fast-tracked for endoscopy, enabling earlier and better detection of neoplasias. **TIMELINESS:** Due to Covid-19, there is now additional impetus to reduce unnecessary endoscopy referrals to comply with infection control measures, tackle long waiting lists, improve NHS efficiency, and reduce costs.

**NEED:** The UK's Bowel Cancer Screening Programme (BCSP) has been revolutionised by improved diagnostic methodology, the Faecal Immunochemical Test (FIT). FIT is easy to undertake (only one sample required), and so screening participation has increased from 59.4% to 67.5% of eligible adults aged \>50 years. Any participant exceeding a pre-determined FIT threshold value that is universally applied to all samples screened is referred for colonoscopy to identify any medically actionable cause of bleeding i.e., colorectal cancer (CRC) or a precancerous adenoma (polyp). Coupled to increased sensitivity of FIT vs. traditional guaiac-based faecal haemoglobin (f-Hb) detection, the number of referrals to colonoscopy is rising. There are recognised weaknesses with FIT; ~45% of participants undergoing colonoscopy have neither CRC nor adenomas. More worryingly however is that interval cancers (cancers that are detected between FIT screening rounds) account for ~50% of diagnosed bowel cancers. The high proportion of interval cancers can be explained by the high positive f-Hb FIT threshold (120 µg/g in England: 80 µg/g in Scotland). Recent modelling suggests that the NHS England FIT threshold of 120 µg/g could mean over 52% of CRC and 75% of high-risk adenomas may be missed. Bowel Cancer UK and leading clinicians have recommended that the FIT threshold should be lowered to 20 µg/g to facilitate earlier detection of CRC, but this could increase the number of colonoscopies being performed from 650,000 to as many as 1.5 million procedures annually. Colonoscopy is a costly, invasive procedure (c.£550 per colonoscopy). Moreover, during the Covid-19 pandemic, there is additional impetus to reduce unnecessary procedures and staff/patient hospital interactions for infection control, whilst making the NHS more efficient by using critical resources more wisely. There is thus a significant and pressing **unmet need** for improving the diagnostic yield from FIT and avoiding unnecessary colonoscopy. **SOLUTION:** Advanced Expert Systems Ltd (AES) have joined clinical academics from the University of Dundee and University Hospitals Coventry & Warwickshire Midlands NHS Trust to develop an AI-based software platform 'ColonSys' to interpret FIT result in the context of other risk factors. As a multivariate stratification model, ColonSys optimises clinical resources by risk, with a gradient from high-risk patients being fast-tracked for further investigation, to patients with no risk having their next FIT screen delayed. ColonSys will make BCSPs more efficient, with only high-risk patients requiring colonoscopy. **TIMELINESS:** Due to Covid-19, there is additional impetus to reduce unrequired hospital visits and improve NHS efficiency.

"Bowel cancer screening services invite asymptomatic persons aged \>60 years to conduct guaiac-based Faecal Occult Blood testing (gFOBt) every two years. From Autumn 2018, NHS England's Bowel Cancer Screening Programme (BCSP; commissioned by Public Health England; PHE) will roll-out Faecal Immunochemical Test (FIT) to replace gFOBt. FIT is simpler, more sensitive, and improves neoplasia detection However, FIT is less specific than gFOBT, increasing the number of 'false positive' patients being referred for colonoscopy. FIT results will be interpreted manually by a Bowel Cancer Specialist Screening Practitioner. To improve the overall efficiency of the BCSP, and to optimise the interpretation of the FIT result, Advanced Expert Systems Ltd (AES), experts in Artificial Intelligence (AI) and Machine Learning (ML) software, propose a feasibility assessment of a new system (using similar principles to an AI-based system they have developed for the MoD) that 1. Automates the interpretation of FIT-results, considering them within a framework of other data variables within the electronic patient record; 2. Automates the wider BCSP as much as possible, from invitation of patients to delivery of results and onward forwarding of patients, where required."