P384 High incidence of hyperglycaemia in steroid treated hospitalised inflammatory bowel disease (IBD) patients and its risk factors identified by machine learning methods

Abstract

Introduction: Glucocorticoids (GC) have been first line treatment for hospitalised inflammatory bowel disease (IBD) patients for over 60 years, despite the introduction of biologic therapy. The use of steroids in IBD inpatients is common and remains prominent in international guidelines. IBD patients often have systemic inflammation complicated by malnutrition leading to metabolic stress. The frequency and specific risk factors for hyperglycaemia in hospitalised IBD patients receiving GC are unknown Aims & Methods: 100 consecutive IBD inpatients receiving intravenous hydrocortisone (IVH) for acute flares had capillary blood glucose (CBG) monitoring automatically triggered by the electronic prescription. CBG, biomarkers, IBD severity scores (Harvey Bradshaw, partial Mayo) and weight loss were prospectively recorded. Undiagnosed Diabetes Mellitus (DM) was defined as baseline HbA1c >48 mmol/mol. Machine learning (random forest regressor, RFR) was applied to the data to evaluate risk factors of hyperglycaemia. Results: 55% of hospitalised IVH treated IBD patients had a CBG meeting the WHO criteria of DM (>11mmol/L), while 21% and 7% had a CBG >14mmol/l and >20mmol/l, respectively. Only 7 patients had pre-existing DM, which was confirmed by admission HbA1c. RFR indicated disease severity score, duration of IVH, HbA1c and electrolyte imbalances (which affected 64%) were best predictors of hyperglycaemia. 50% were started on or switched biological therapy during hospitalisation. 59% were discharged on prednisolone, 14% on budesonide and 28% on no GC. 47 patients had HbA1c checked at 3 month follow-up of which 4 were in the diabetic range. 1 had known DM with elevated CBG during admission treated with insulin titration, 2 had elevated CBG as inpatients with no prior DM and were discharged on anti-diabetic medications (1 gliclazide, 1 insulin) and 1 was on long-term steroids for asthma who did not have CBG >11.0mmol/L as an inpatient. 4 patients discharged on gliclazide for steroid induced DM had documented repeat HbA1c recorded, which were all in the normal range. Conclusion: Our data demonstrates that hyperglycaemia is common in IVH treated inpatients, therefore CBG monitoring should be routine practice. Predictive modelling (RFR) identifies more severe disease activity, duration of IVH treatment and HbA1c as risk factors for hyperglycaemia. The importance of IVH duration suggests hyperglycaemia risk may be physicianmodifiable. Alternative treatment strategies such as earlier introduction of biologics (which were used in half of the cohort), rapid steroid taper and nutritional therapies could be used to minimise medication associated metabolic instability in high risk patients. Limited follow-up HbA1c data suggests oral hypoglycaemic medication may be effective to mitigate further hyperglycaemia. (Table Presented) .