[Development of the use of artificial intelligence in the management of chronic inflammatory bowel disease]. / Mise au point de l'utilisation de l'intelligence artificielle dans la prise en charge des maladies inflammatoires chroniques de l'intestin.

Complexity of inflammatory bowel diseases (IBD) lies on their management and their biology. Clinics, blood and fecal samples tests, endoscopy and histology are the main tools guiding IBD treatment, but they generate a large amount of data, difficult to analyze by clinicians. Because of its capacity to analyze large number of data, artificial intelligence is currently generating enthusiasm in medicine, and this technology could be used to improve IBD management. In this review, after a short summary on IBD management and artificial intelligence, we will report pragmatic examples of artificial intelligence utilisation in IBD. Lastly, we will discuss the limitations of this technology.

Prognostic value of the early change in neutrophil-to-lymphocyte ratio in metastatic pancreatic adenocarcinoma.

In metastatic pancreatic adenocarcinoma, a high neutrophil-to-lymphocyte ratio (NLR) at diagnosis is a marker of poor prognosis. The prognostic role of baseline NLR and NLR change during first-line chemotherapy were determined. We conducted a retrospective study by using data from a single-center prospective cohort and a randomized open-label, multicenter, randomized trial. Two hundred and twelve patients were analyzed. Baseline NLR>5 was an independent marker of poor prognosis for overall survival (HR=2.01, 95% CI 1.33-3.05; P=0.001) and progression-free survival (PFS; HR=1.80, 95% CI 1.23-2.65; P=0.0026). According to NLR dynamics (n=172), patients with NLR≤5 on days 1 and 15 had a significantly better prognosis than those with NLR≤5 on day 1 and NLR>5 on day 15 (HR=2.23, 95% CI 1.18-4.21; P=0.013), NLR >5 on day 1 and NLR ≤5 on day 15 (HR=3.25, 95% CI 1.86-5.68; P<0.001), and NLR>5 on days 1 and 15 (HR=3.37, 95% CI 1.93-5.90; P<0.001). Over time, bad responders (PFS <6 months) had significantly higher mean NLR than good responders (PFS>6 months; group effect: P<0.0001). Seven out of eight patients with baseline NLR>5 had circulating tumor DNA. This study confirmed the independent prognostic value of baseline NLR >5 in metastatic pancreatic cancer. The change in NLR early during chemotherapy was also a prognostic indicator in patients with NLR ≤5.

Safety of Hydrocortisone Premedication Discontinuation in Patients with Inflammatory Bowel Disease on Maintenance Therapy with Infliximab: a Prospective Clinical and Pharmacological Study.

BACKGROUND: Hydrocortisone premedication reduces the risk of antibodies to infliximab [ATIs] formation in patients receiving infliximab [IFX] therapy for inflammatory bowel disease [IBD]. AIM: We aimed to determine the safety of hydrocortisone premedication withdrawal in IBD patients with sustained clinical response on maintenance therapy with IFX. METHODS: We performed an observational prospective pharmacoclinical study in a tertiary referral centre, including all consecutive IBD outpatients with no previous IFX infusion reaction and in clinical remission on maintenance IFX [alone or in combination therapy] for at least 6 months. This cohort was followed for 1 year after discontinuation of hydrocortisone premedication. RESULTS: Among the 268 IBD outpatients, 95 patients met the inclusion criteria [mean age 38 years; 64% male; 80% Crohn's disease; 45% combination therapy]. The median IFX duration was 5 years [0.54-14] with a mean infused dose of 533 mg [200-1000] and a mean interval duration of 7.9 weeks [4-10]. None of the patients developed permanent ATIs or infusion-related reaction at 1 year. Four patients developed transient ATIs without loss of clinical response. There was no significant variation of infliximab serum trough levels [5.5 µg/mL vs 5.9 µg/mL] measured at the time of the three IFX infusions before and after hydrocortisone withdrawal. Loss of response rate to IFX was 18% at 1 year. CONCLUSIONS: Hydrocortisone discontinuation is safe in IBD patients with sustained clinical remission on maintenance therapy with IFX. Our data suggest that routine premedication with hydrocortisone is unnecessary in patients in prolonged remission under IFX maintenance therapy.