PTH-105 Hyperglycaemia in steroid treated hospitalised IBD inpatients and its risk factors identified by machine learning

Introduction Glucocorticoids (GC) have been first line treatment for hospitalised IBD patients for over 60 years, despite the introduction of biologic therapy. IBD patients often have systemic inflammation complicated by malnutrition leading to metabolic stress. Frequency and risk factors for hyperglycaemia in hospitalised IBD patients receiving GC are unknown. Methods 112 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 HbA1c >48 mmol/mol. Machine learning (random forest regressor, RFR) was applied to data to evaluate risk factors of hyperglycaemia. Results 51% of hospitalised IVH treated IBD patients met the WHO criteria of DM (CBG>11 mmol/L), while 20% and 6% had a CBG >14 mmol/l and >20 mmol/l, respectively. 8 patients had pre-existing DM, which was confirmed by admission HbA1c. RFR indicated disease severity score, duration of IVH, HbA1c and electrolyte imbalances (64%) were best predictors of hyperglycaemia. 49% were started on or switched biological therapy during admissions. 55% were discharged on prednisolone, 14% on budesonide and 34% on no GC. 48 patients had HbA1c checked at 3 month follow-up of which 4 were in the diabetic range. 1 was known DM with elevated CBG during admission whose insulin had been titrated, 2 had elevated CBG as inpatients with no prior DM discharged on gliclazide and insulin respectively and 1 was on long-term steroids for asthma who did not have CBG >11.0 mmol/L as inpatient. 4 other patients discharged on gliclazide for steroid induced DM had documented repeat HbA1c recorded, which were all in the normal range. Conclusions 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 physician-modifiable. Alternative treatment strategies such as earlier introduction of biologics, rapid steroid taper and nutritional support could be used to minimise medication associated metabolic instability in high risk patients.