Identifying CLL patients at high risk of atrial fibrillation on treatment using machine learning

Abstract

An increased risk of developing atrial fibrillation (AF) has been observed in patients with chronic lymphocytic leukemia (CLL) who were treated with ibrutinib and other BTK inhibitors. Previous studies have explored the prevalence of AF in CLL and the risk of developing AF at time of diagnosis. However, the interaction between treatment type with other risk factors on risk of developing atrial fibrillation at the time of treatment initiation has not been investigated. This becomes particularly crucial in CLL, as there is often a substantial time gap between diagnosis and treatment, unlike many other cancers. We propose a treatment-aware approach using predictive modeling to identify the risk factors associated with AF at time of treatment initiation. Moreover, the model provides treatment-dependent risk factors by including the interaction between the treatment types and other risk factors. The results demonstrated that the treatment-aware modeling including interactions outperformed currentrisk scores.

Keywords:

• Chronic lymphocytic leukemia
• machine learning
• atrial fibrillation
• ibrutinib

Author contributions

C.U.N. and M.P. conceived the study; N.V., K.A., and E.C.R. curated the data; M.P. performed the data preparation and analysis with help from R.A.; M.P. wrote the original manuscript together with C.U.N., with input from all authors, who reviewed and approved the final manuscript.

Disclosure statement

Mehdi Parviz received research grant from AstraZeneca. Noomi Vainer received research grants from AstraZeneca and Rigshospitalet. Emelie Curovic Rotbain received consultancy fees from AstraZeneca, travel grants from Abbvie and AstraZeneca, payment for presentations from Abbvie, AstraZeneca, and Janssen, and board membership from Janssen. Carsten Utoft Niemann received research grants from Octapharma and AstraZeneca, as well as consultancy fees from Janssen, Lilly, Beigene, Genmab, Octapharma, Takeda, CSL Behring, Abbvie, AstraZeneca.

Notes

1 All the confidence intervals are estimated at the 95% confidence level.

Additional information

Funding

This work is supported by grants from AstraZeneca.