Nicholson, Brian D

Objectives The ‘tumour, node, metastasis’ (TNM) classification of colorectal cancer (CRC) predicts prognosis and so is vital to consider in analyses of patterns and outcomes of care when using electronic health records. Unfortunately, it is often only available in free-text reports. This study aimed to develop regex-based text-processing algorithms that identify the reports describing CRC and extract the TNM staging at a low computational cost. Methods The CRC and TNM extraction algorithms were iteratively developed using 58 634 imaging and pathology reports of patients with CRC from the Oxford University Hospitals (OUH) and Royal Marsden (RMH) NHS Foundation Trusts (FT), with additional input from Imperial College Healthcare and Christie NHS FTs. The algorithms were evaluated on a stratified random sample of 400 OUH development data reports and 400 newer ‘unseen’ OUH reports. The reports were annotated with the help of two clinicians. Results The CRC algorithm achieved at least 93.0% positive predictive value (PPV), 72.1% sensitivity, 64.0% negative predictive value (NPV) and 90.1% specificity for primary CRC on pathology reports. On imaging reports, it demonstrated at least 78.0% PPV, 91.8% sensitivity, 93.0% NPV and 80.9% specificity. For the main T/N/M categories, the TNM algorithm achieved PPVs of at least 93.9% (T), 97.7% (N) and 97.2% (M), and sensitivities of 63.6% (T), 89.6% (N) and 64.8% (M). NPVs were at least 45.0% (T), 91.1% (N), 88.4% (M), and specificities 95.7% (T), 98.1% (N), 99.3% (M). Reductions in performance were mostly due to implicit staging. For extracting explicit TNM stages, current or historical, the algorithm made no errors on 400 pathology reports and six errors on 400 imaging reports. Conclusion The TNM algorithm accurately extracts explicit TNM staging, but other methods are needed for retrieving implicit stages. The CRC algorithm is accurate on non-supplementary reports, but outputs need additional review if higher precision is required.

Faecal immunochemical testing (FIT) has a high sensitivity for the detection of colorectal cancer (CRC). In a symptomatic population FIT may identify those patients who require colorectal investigation with the highest priority. FIT offers considerable advantages over the use of symptoms alone, as an objective measure of risk with a vastly superior positive predictive value for CRC, while conversely identifying a truly low risk cohort of patients. The aim of this guideline was to provide a clear strategy for the use of FIT in the diagnostic pathway of people with signs or symptoms of a suspected diagnosis of CRC. The guideline was jointly developed by the Association of Coloproctology of Great Britain and Ireland/British Society of Gastroenterology, specifically by a 21-member multidisciplinary guideline development group (GDG). A systematic review of 13 535 publications was undertaken to develop 23 evidence and expert opinion-based recommendations for the triage of people with symptoms of a suspected CRC diagnosis in primary care. In order to achieve consensus among a broad group of key stakeholders, we completed an extended Delphi of the GDG, and also 61 other individuals across the UK and Ireland, including by members of the public, charities and primary and secondary care. Seventeen research recommendations were also prioritised to inform clinical management.