Development of a simple, serum biomarker-based model predictive of the need for early biologic therapy in Crohn's disease

Background: Early or first-line treatment with biologics as opposed to conventional immunomodulators is not always necessary to achieve remission in Crohn's disease (CD) and may not be cost-effective. This study aimed to develop a simple model to predict the need for early biologic therapy in order to risk stratify CD patients and guide initial treatment selection.

Methods: A model-building study using supervised statistical learning methods was conducted utilising a retrospective cohort across two tertiary centres. All biologic-naïve CD patients who commenced an immunomodulator between 1/1/2004 and 31/12/2016 were included. A predictive score was derived using Cox regression modelling of immunomodulator failure and was internally validated using bootstrap resampling.

Results: Of 410 patients (median age 37 years, 47% male, median disease duration 4.7 years), 229 (56%) experienced immunomodulator failure (39 required surgery, 24 experienced a new stricture, 44 experienced a new fistula/abscess, 122 required biologic escalation) with a median time to failure of 16 months. Independent predictors of treatment failure included raised CRP, low albumin, complex disease behaviour, younger age and baseline steroids. Highest CRP and lowest albumin measured within 3 months prior to immunomodulator initiation outperformed baseline measurements. After model selection, only highest CRP and lowest albumin remained and the resultant Crohn's Immunomodulator CRP-Albumin (CICA) index demonstrated robust optimism-corrected discriminative performance at 12, 24 and 36 months (AUC 0.84, 0.83, 0.81 respectively).

Conclusions: The derived CICA index based on simple, widely available markers is feasible, internally valid and has a high utility in predicting immunomodulator failure. This requires external, prospective validation.

Keywords: precision medicine; prediction; predictive model; statistical learning.