Artificial intelligence and inflammatory bowel disease: practicalities and future prospects.

Artificial intelligence (AI) is an emerging technology predicted to have significant applications in healthcare. This review highlights AI applications that impact the patient journey in inflammatory bowel disease (IBD), from genomics to endoscopic applications in disease classification, stratification and self-monitoring to risk stratification for personalised management. We discuss the practical AI applications currently in use while giving a balanced view of concerns and pitfalls and look to the future with the potential of where AI can provide significant value to the care of the patient with IBD.

Ferric maltol Real-world Effectiveness Study in Hospital practice (FRESH): clinical characteristics and outcomes of patients with inflammatory bowel disease receiving ferric maltol for iron-deficiency anaemia in the UK.

OBJECTIVE: To assess outcomes in patients with iron-deficient inflammatory bowel disease (IBD) treated with ferric maltol in UK real-world practice. DESIGN/METHOD: This observational, multicentre, retrospective cohort study included adults with IBD and iron-deficiency anaemia (IDA; haemoglobin ≥95 to <120 g/L (women) or ≥95 to <130 g/L (men) plus serum ferritin <30 µg/L or transferrin saturation <20%) who received ferric maltol. Data were extracted from patient records. The primary analysis was the proportion of patients with normalised haemoglobin (≥120 g/L (women); ≥130 g/L (men)) over 12 weeks. Iron indices and safety were assessed. RESULTS: Thirty of 59 patients had data for the primary outcome, 19 of whom (63%) achieved haemoglobin normalisation at week 12. Mean±SD haemoglobin was 127±16 g/L at week 12 (increase of 14±17 g/L from baseline). Overall, 27 patients achieved haemoglobin normalisation by the end of the observation period; mean±SD time to normalisation was 49.5±25.6 days. Nine of 17 patients had normalised serum ferritin (30-300 µg/L) at week 12, and 16 patients had normalised ferritin at the end of the observation period; mean±SD time to normalisation was 71.3±27.6 days. Twenty-four adverse events occurred in 19 patients (32%); most frequent adverse events were abdominal pain or discomfort (n=9) and constipation (n=3). CONCLUSION: Ferric maltol increases haemoglobin and iron indices and is generally well tolerated in patients with IBD and IDA treated in clinical practice. These real-world data support findings from randomised controlled trials.

Interventions for treating iron deficiency anaemia in inflammatory bowel disease.

BACKGROUND: Inflammatory bowel disease affects approximately seven million people globally. Iron deficiency anaemia can occur as a common systemic manifestation, with a prevalence of up to 90%, which can significantly affect quality of life, both during periods of active disease or in remission. It is important that iron deficiency anaemia is treated effectively and not be assumed to be a normal finding of inflammatory bowel disease. The various routes of iron administration, doses and preparations present varying advantages and disadvantages, and a significant proportion of people experience adverse effects with current therapies. Currently, no consensus has been reached amongst physicians as to which treatment path is most beneficial. OBJECTIVES: The primary objective was to evaluate the efficacy and safety of the interventions for the treatment of iron deficiency anaemia in people with inflammatory bowel disease. SEARCH METHODS: We searched CENTRAL, MEDLINE, Embase, and two other databases on 21st November 2019. We also contacted experts in the field and searched references of trials for any additional trials. SELECTION CRITERIA: Randomised controlled trials investigating the effectiveness and safety of iron administration interventions compared to other iron administration interventions or placebo in the treatment of iron deficiency anaemia in inflammatory bowel disease. We considered both adults and children, with studies reporting outcomes of clinical, endoscopic, histologic or surgical remission as defined by study authors. DATA COLLECTION AND ANALYSIS: Two review authors independently conducted data extraction and 'Risk of bias' assessment of included studies. We expressed dichotomous and continuous outcomes as risk ratios and mean differences with 95% confidence intervals. We assessed the certainty of the evidence using the GRADE methodology. MAIN RESULTS: We included 11 studies (1670 randomised participants) that met the inclusion criteria. The studies compared intravenous iron sucrose vs oral iron sulphate (2 studies); oral iron sulphate vs oral iron hydroxide polymaltose complex (1 study); oral iron fumarate vs intravenous iron sucrose (1 study); intravenous ferric carboxymaltose vs intravenous iron sucrose (1 study); erythropoietin injection + intravenous iron sucrose vs intravenous iron sucrose + injection placebo (1 study); oral ferric maltol vs oral placebo (1 study); oral ferric maltol vs intravenous ferric carboxymaltose (1 study); intravenous ferric carboxymaltose vs oral iron sulphate (1 study); intravenous iron isomaltoside vs oral iron sulphate (1 study); erythropoietin injection vs oral placebo (1 study). All studies compared participants with CD and UC together, as well as considering a range of disease activity states. The primary outcome of number of responders, when defined, was stated to be an increase in haemoglobin of 20 g/L in all but two studies in which an increase in 10g/L was used. In one study comparing intravenous ferric carboxymaltose and intravenous iron sucrose, moderate-certainty evidence was found that intravenous ferric carboxymaltose was probably superior to intravenous iron sucrose, although there were responders in both groups (150/244 versus 118/239, RR 1.25, 95% CI 1.06 to 1.46, number needed to treat for an additional beneficial outcome (NNTB) = 9). In one study comparing oral ferric maltol to placebo, there was low-certainty evidence of superiority of the iron (36/64 versus 0/64, RR 73.00, 95% CI 4.58 to 1164.36). There were no other direct comparisons that found any difference in the primary outcomes, although certainty was low and very low for all outcomes, due to imprecision from sparse data and risk of bias varying between moderate and high risk. The reporting of secondary outcomes was inconsistent. The most common was the occurrence of serious adverse events or those requiring withdrawal of therapy. In no comparisons was there a difference seen between any of the intervention agents being studied, although the certainty was very low for all comparisons made, due to risk of bias and significant imprecision due to the low numbers of events. Time to remission, histological and biochemical outcomes were sparsely reported in the studies. None of the other secondary outcomes were reported in any of the studies. An analysis of all intravenous iron preparations to all oral iron preparations showed that intravenous administration may lead to more responders (368/554 versus 205/373, RR 1.17, 95% CI 1.05 to 1.31, NNTB = 11, low-certainty due to risk of bias and inconsistency). Withdrawals due to adverse events may be greater in oral iron preparations vs intravenous (15/554 versus 31/373, RR 0.39, 95% CI 0.20 to 0.74, low-certainty due to risk of bias, inconsistency and imprecision). AUTHORS' CONCLUSIONS: Intravenous ferric carboxymaltose probably leads to more people having resolution of IDA (iron deficiency anaemia) than intravenous iron sucrose. Oral ferric maltol may lead to more people having resolution of IDA than placebo. We are unable to draw conclusions on which of the other treatments is most effective in IDA with IBD (inflammatory bowel disease) due to low numbers of studies in each comparison area and clinical heterogeneity within the studies. Therefore, there are no other conclusions regarding the treatments that can be made and certainty of all findings are low or very low. Overall, intravenous iron delivery probably leads to greater response in patients compared with oral iron, with a NNTB (number needed to treat) of 11. Whilst no serious adverse events were specifically elicited with any of the treatments studied, the numbers of reported events were low and the certainty of these findings very low for all comparisons, so no conclusions can be drawn. There may be more withdrawals due to such events when oral is compared with intravenous iron delivery. Other outcomes were poorly reported and once again no conclusions can be made as to the impact of IDA on any of these outcomes. Given the widespread use of many of these treatments in practice and the only guideline that exists recommending the use of intravenous iron in favour of oral iron, research to investigate this key issue is clearly needed. Considering the current ongoing trials identified in this review, these are more focussed on the impact in specific patient groups (young people) or on other symptoms (such as fatigue). Therefore, there is a need for studies to be performed to fill this evidence gap.

Treatment persistence and colectomy-free outcomes in patients with ulcerative colitis receiving golimumab or adalimumab: a UK experience.

OBJECTIVE: To examine real-world treatment persistence, colectomy-free survival and treatment switching patterns in UK patients with ulcerative colitis (UC) prescribed golimumab or adalimumab. DESIGN: This was a retrospective chart review study in adult patients diagnosed with UC using data from 16 National Health Service sites in the UK. Patient records were included in the study if they had initiated first or second-line adalimumab or golimumab between 1 March 2016 and 30 September 2017 (index date). Subjects were required for ≥6 months post treatment initiation. Demographics, clinical characteristics, treatment-related data and colectomy data were extracted over a follow-up period of 6-12 months. Treatment persistence rate was the primary outcome. Colectomy-free survival and treatment switching were secondary outcomes. Outcomes were compared between treatments using χ2 tests and Fisher's exact test for categorical variables. The t-tests were used for continuous variables. Time-to-event variables were evaluated using Kaplan-Meier curves and log-rank tests. RESULTS: The study included a total of 183 patients (96 (52.5%) prescribed adalimumab; 87 (47.5%) golimumab), and patients were mostly first line (79.8%). Demographic and clinical characteristics were generally similar between treatment groups. Persistence rates within 12 months were 64.6% for adalimumab and 64.4% for golimumab (p=0.681). Overall, 20.2% switched to other therapy within 1 year, with 8.2% golimumab and 12.0% adalimumab switching to another biologic. Of patients prescribed adalimumab, 14.6% had ≥1 dose change, mainly dose escalations. In the 12 months post treatment initiation, 8.2% of patients underwent colectomy, with no significant difference in colectomy-free survival by treatment, p=0.73. CONCLUSION: This study provides evidence of clinical outcomes and real-world persistence for adalimumab and golimumab in UC. The persistence rates of both therapies were above 64.0% at 12 months following treatment initiation. In addition, the 1-year colectomy-free survival was relatively similar between the two treatments.

Masquerading in the midgut: a rare diagnosis in a patient with recurrent abdominal pain.

A 38-year-old woman who had been previously diagnosed with irritable bowel syndrome was seen in the outpatient clinic with a 2-year history of intermittent cramp-like abdominal pain which was often followed by watery diarrhoea. She had presented several times previously to the emergency department with episodes of severe pain and collapse although on arrival examination findings were mostly unremarkable other than some mild lower abdominal tenderness. On each occasion, the symptoms resolved spontaneously with conservative management. She had been extensively investigated by her general practitioner to establish the cause of her symptoms but all laboratory findings, cross-sectional imaging, ultrasound and oesophagogastroduodenoscopy to date were unremarkable. After being seen in gastroenterology outpatients' clinic, a colonoscopy was performed and was described as being macroscopically normal but microscopic evaluation of colonic biopsies suggested a possible 'resolving infection'. She was treated symptomatically, but within 6 months she represented to hospital with progressively worsening symptoms of severe abdominal pain, now associated with vomiting, followed by watery diarrhoea and then resolution of the symptoms. An abdominal CT scan was performed which showed a small intraluminal-filling defect in the mid-terminal ileum. A wireless capsule endoscopy was organised to further characterise the lesion although this was reported as showing no abnormality. Prior to any further outpatient investigations, she represented as an emergency to hospital in small bowel obstruction, underwent further cross-sectional imaging followed by surgical resection of the lesion. Histological characterisation revealed a small bowel inflammatory fibroid polyp.

Mesalazine-induced myocarditis: a case report.

BACKGROUND: Myocarditis is a rare complication of therapy with mesalazine, a drug widely prescribed in the treatment of inflammatory bowel disease. CASE PRESENTATION: We report a case of myocarditis occurring in a 49-year-old British man 10 days following initiation of mesalazine therapy for treatment of ulcerative colitis. He presented with troponin-positive chest pain, and the diagnosis of myocarditis was confirmed on the basis of cardiac magnetic resonance imaging, which showed subepicardial delayed gadolinium enhancement in the basal to middle inferior and inferolateral segments of the heart. The patient's symptoms and condition improved upon stopping mesalazine, and he made a full recovery. CONCLUSIONS: Mesalazine-induced myocarditis may be more common than first appreciated and is potentially fatal. Therefore, it is imperative that clinicians be aware of this potentially life-threatening adverse effect of mesalazine therapy and warn patients to seek urgent medical attention if cardiac symptoms arise.

'Pre-endoscopy point of care test (Simtomax- IgA/IgG-Deamidated Gliadin Peptide) for coeliac disease in iron deficiency anaemia: diagnostic accuracy and a cost saving economic model'.

BACKGROUND: International guidelines recommend coeliac serology in iron deficiency anaemia, and duodenal biopsy for those tested positive to detect coeliac disease. However, pre-endoscopy serology is often unavailable, thus committing endoscopists to take routine duodenal biopsies. Some endoscopists consider duodenal biopsy mandatory in anaemia to exclude other pathologies. We hypothesise that using a point of care test at endoscopy could fill this gap, by providing rapid results to target anaemic patients who require biopsies, and save costs by biopsy avoidance. We therefore assessed three key aspects to this hypothesis: 1) the availability of pre-endoscopy serology in anaemia; 2) the sensitivities and cost effectiveness of pre-endoscopy coeliac screening with Simtomax in anaemia; 3) whether other anaemia-related pathologies could be missed by this targeted-biopsy approach. METHODS: Group 1: pre-endoscopy serology availability was retrospectively analysed in a multicentre cohort of 934 anaemic patients at 4 UK hospitals. Group 2: the sensitivities of Simtomax, endomysial and tissue-transglutaminase antibodies were compared in 133 prospectively recruited patients with iron deficiency anaemia attending for a gastroscopy. The sensitivities were measured against duodenal histology as the reference standard in all patients. The cost effectiveness of Simtomax was calculated based on the number of biopsies that could have been avoided compared to an all-biopsy approach. Group 3: the duodenal histology of 153 patients presenting to a separate iron deficiency anaemia clinic were retrospectively reviewed. RESULTS: In group 1, serology was available in 361 (33.8 %) patients. In group 2, the sensitivity and negative predictive value (NPV) were 100 % and 100 % for Simtomax, 96.2 % and 98.9 % for IgA-TTG, and 84.6 % and 96.4 % for EMA respectively. In group 3, the duodenal histology found no causes for anaemia other than coeliac disease. CONCLUSION: Simtomax had excellent diagnostic accuracy in iron deficiency anaemia and was comparable to conventional serology. Duodenal biopsy did not identify any causes other than coeliac disease for iron deficiency anaemia, suggesting that biopsy avoidance in Simtomax negative anaemic patients is unlikely to miss other anaemia-related pathologies. Due to its 100 % NPV, Simtomax could reduce unnecessary biopsies by 66 % if only those with a positive Simtomax were biopsied, potentially saving £3690/100 gastroscopies. TRIAL REGISTRATION: The group 2 study was retrospectively registered with clinicaltrials.gov. Trial registration date: 13(th) July 2016; TRIAL REGISTRATION NUMBER: NCT02834429 .

Infliximab, adalimumab and golimumab for treating moderately to severely active ulcerative colitis after the failure of conventional therapy (including a review of TA140 and TA262): clinical effectiveness systematic review and economic model.

BACKGROUND: Ulcerative colitis (UC) is the most common form of inflammatory bowel disease in the UK. UC can have a considerable impact on patients' quality of life. The burden for the NHS is substantial. OBJECTIVES: To evaluate the clinical effectiveness and safety of interventions, to evaluate the incremental cost-effectiveness of all interventions and comparators (including medical and surgical options), to estimate the expected net budget impact of each intervention, and to identify key research priorities. DATA SOURCES: Peer-reviewed publications, European Public Assessment Reports and manufacturers' submissions. The following databases were searched from inception to December 2013 for clinical effectiveness searches and from inception to January 2014 for cost-effectiveness searches for published and unpublished research evidence: MEDLINE, EMBASE, Cumulative Index to Nursing and Allied Health Literature, The Cochrane Library including the Cochrane Systematic Reviews Database, Cochrane Controlled Trials Register, Database of Abstracts of Reviews of Effects, the Health Technology Assessment database and NHS Economic Evaluation Database; ISI Web of Science, including Science Citation Index, and the Conference Proceedings Citation Index-Science and Bioscience Information Service Previews. The US Food and Drug Administration website and the European Medicines Agency website were also searched, as were research registers, conference proceedings and key journals. REVIEW METHODS: A systematic review [including network meta-analysis (NMA)] was conducted to evaluate the clinical effectiveness and safety of named interventions. The health economic analysis included a review of published economic evaluations and the development of a de novo model. RESULTS: Ten randomised controlled trials were included in the systematic review. The trials suggest that adult patients receiving infliximab (IFX) [Remicade(®), Merck Sharp & Dohme Ltd (MSD)], adalimumab (ADA) (Humira(®), AbbVie) or golimumab (GOL) (Simponi(®), MSD) were more likely to achieve clinical response and remission than those receiving placebo (PBO). Hospitalisation data were limited, but suggested more favourable outcomes for ADA- and IFX-treated patients. Data on the use of surgical intervention were sparse, with a potential benefit for intervention-treated patients. Data were available from one trial to support the use of IFX in paediatric patients. Safety issues identified included serious infections, malignancies and administration site reactions. Based on the NMA, in the induction phase, all biological treatments were associated with statistically significant beneficial effects relative to PBO, with the greatest effect associated with IFX. For patients in response following induction, all treatments except ADA and GOL 100 mg at 32-52 weeks were associated with beneficial effects when compared with PBO, although these were not significant. The greatest effects at 8-32 and 32-52 weeks were associated with 100 mg of GOL and 5 mg/kg of IFX, respectively. For patients in remission following induction, all treatments except ADA at 8-32 weeks and GOL 50 mg at 32-52 weeks were associated with beneficial effects when compared with PBO, although only the effect of ADA at 32-52 weeks was significant. The greatest effects were associated with GOL (at 8-32 weeks) and ADA (at 32-52 weeks). The economic analysis suggests that colectomy is expected to dominate drug therapies, but for some patients, colectomy may not be considered acceptable. In circumstances in which only drug options are considered, IFX and GOL are expected to be ruled out because of dominance, while the incremental cost-effectiveness ratio for ADA versus conventional treatment is approximately £50,300 per QALY gained. LIMITATIONS: The health economic model is subject to several limitations: uncertainty associated with extrapolating trial data over a lifetime horizon, the model does not consider explicit sequential pathways of non-biological treatments, and evidence relating to complications of colectomy was identified through consideration of approaches used within previous models rather than a full systematic review. CONCLUSIONS: Adult patients receiving IFX, ADA or GOL were more likely to achieve clinical response and remission than those receiving PBO. Further data are required to conclusively demonstrate the effect of interventions on hospitalisation and surgical outcomes. The economic analysis indicates that colectomy is expected to dominate medical treatments for moderate to severe UC. STUDY REGISTRATION: This study is registered as PROSPERO CRD42013006883. FUNDING: The National Institute for Health Research Health Technology Assessment programme.

A Model-Based Economic Evaluation of Biologic and Non-Biologic Options for the Treatment of Adults with Moderately-to-Severely Active Ulcerative Colitis after the Failure of Conventional Therapy.

BACKGROUND: Ulcerative colitis (UC) is the most common form of inflammatory bowel disease in the UK. Medical management aims to induce and maintain remission and to avoid complications and the necessity for surgical intervention. Colectomy removes the source of inflammation but is associated with morbidity and mortality. Newer anti-tumour necrosis factor (TNF)-α therapies may improve medical outcomes, albeit at an increased cost. OBJECTIVE: Our objective was to assess the incremental cost effectiveness of infliximab, adalimumab and golimumab versus conventional therapy and surgery from a National Health Service (NHS) and Personal Social Services (PSS) perspective over a lifetime horizon. METHODS: A Markov model was developed with health states defined according to whether the patient is alive or dead, current treatments received, history of colectomy and level of disease control. Transition probabilities were derived from network meta-analyses (NMAs) of trials of anti-TNF-α agents in the moderate-to-severe UC population. Health utilities, colectomy rates, surgical complications and resource use estimates were derived from literature. Unit costs were drawn from standard costing sources and literature and were valued at year 2013/2014 values. RESULTS: For patients in whom surgery is an option, colectomy is expected to dominate all medical treatment options. For patients in whom colectomy is not an option, infliximab and golimumab are expected to be ruled out due to dominance, whilst the incremental cost-effectiveness ratio (ICER) for adalimumab versus conventional treatment is expected to be approximately £50,278 per quality-adjusted life-year (QALY) gained. CONCLUSIONS: Based on the NMAs, the ICERs for anti-TNF-α therapy versus conventional treatment or surgery are expected to be at best, in excess of £50,000 per QALY gained. The cost effectiveness of withdrawing biologic therapy upon remission and re-treating relapse is unknown.

Vedolizumab for the Treatment of Adults with Moderate-to-Severe Active Ulcerative Colitis: An Evidence Review Group Perspective of a NICE Single Technology Appraisal.

As part of its single technology appraisal (STA) process, the National Institute for Health and Care Excellence (NICE) invited the manufacturer of vedolizumab (Takeda UK) to submit evidence of the clinical effectiveness and cost effectiveness of vedolizumab for the treatment of patients with moderate-to-severe active ulcerative colitis (UC). The Evidence Review Group (ERG) produced a critical review of the evidence for the clinical effectiveness and cost effectiveness of the technology, based upon the company's submission to NICE. The evidence was derived mainly from GEMINI 1, a Phase 3, multicentre, randomised, double-blinded, placebo-controlled study of the induction and maintenance of clinical response and remission by vedolizumab (MLN0002) in patients with moderate-to-severe active UC with an inadequate response to, loss of response to or intolerance of conventional therapy or anti-tumour necrosis factor (TNF)-α. The clinical evidence showed that vedolizumab performed significantly better than placebo in both the induction and maintenance phases. In the post hoc subgroup analyses in patients with or without prior anti-TNF-α therapy, vedolizumab performed better then placebo (p value not reported). In addition, a greater improvement in health-related quality of life was observed in patients treated with vedolizumab, and the frequency and types of adverse events were similar in the vedolizumab and placebo groups, but the evidence was limited to short-term follow-up. There were a number of limitations and uncertainties in the clinical evidence base, which warrants caution in its interpretation--in particular, the post hoc subgroup analyses and high dropout rates in the maintenance phase of GEMINI 1. The company also presented a network meta-analysis of vedolizumab versus other biologic therapies indicated for moderate-to-severe UC. However, the ERG considered that the results presented may have underestimated the uncertainty in treatment effects, since fixed-effects models were used, despite clear evidence of heterogeneity among the trials included in the network. Results from the company's economic evaluation (which included price reductions to reflect the proposed patient access scheme for vedolizumab) suggested that vedolizumab is the most effective option compared with surgery and conventional therapy in the following three populations: (1) a mixed intention-to-treat population, including patients who have previously received anti-TNF-α therapy and those who are anti-TNF-α naïve; (2) patients who are anti-TNF-α naïve only; and (3) patients who have previously failed anti-TNF-α therapy only. The ERG concluded that the results of the company's economic evaluation could not be considered robust, because of errors in model implementation, omission of relevant comparators, deviations from the NICE reference case and questionable model assumptions. The ERG amended the company's model and demonstrated that vedolizumab is expected to be dominated by surgery in all three populations.