Real-World Evidence on Adverse Events and Healthcare Resource Utilization in Patients with Chronic Lymphocytic Leukaemia in Spain Using Natural Language Processing : The SRealCLL Study

Objectives: The SRealCLL study described the occurrence of adverse events (AEs) and healthcare resource utilization in patients with chronic lymphocytic leukaemia (CLL) using artificial intelligence in a real-world scenario in Spain. Methods: We collected real-world data on patients with CLL from seven Spanish hospitals between January 2016 and December 2018, focusing on their AE and healthcare service utilization. Data extraction from electronic health records of 385,904 patients was performed using the EHRead technology, which is based on natural language processing and machine learning. Results: Among the 534 CLL patients finally included, 270 (50.6%) were categorized as watch and wait (W&W), 230 (43.1%) as first-line treatment (1L), and 58 (10.9%) as relapse/refractory with second-line treatment (2L). The median study follow-up periods were 14.4, 8.4, and 6 months for W&W, 1L, and 2L, respectively. The most common antineoplastic treatments were ibrutinib (64.8%) and bendamustine + rituximab (12.6%) in 1L, and ibrutinib (62.1%) and venetoclax (15.5%) in 2L. Among the most frequent AEs, anaemia and thrombocytopenia presented higher rates in the treated groups (1L and 2L) compared with W&W (2.01 and 2.32 vs. 0.93; p ≤ 0.05 and 1.29 and 1.62 vs. 0.42; p ≤ 0.05). Moreover, several AEs, such as major bleeding, digestive symptoms, general symptoms, or Richter syndrome, were more frequent in 1L than W&W (all p ≤ 0.05). No differences were shown between groups in the rates of outpatient visits. However, rates of outpatient visits due to AE were higher in 1L than in W&W (1.07 vs. 0.65, p ≤ 0.05). The rates of patients being hospitalized were higher in the treated groups compared to W&W (1.68 and 1.9 vs. 0.88; p ≤ 0.05), and those due to AE were higher in 1L than W&W (1.23 vs. 0.60; p ≤ 0.05). Conclusions: Patients with CLL in 1L or 2L treatments often require healthcare resources due to AEs, particularly cytopenias. The methodology used in this study likely enabled us to identify higher rates of AEs that may be underreported using other real-world approaches. Addressing AEs with effective agents that maximize patient safety and optimize healthcare resource use is crucial in this typically older and comorbid population.