Real-world evaluation of supportive care using an electronic health record text-mining tool: G-CSF use in breast cancer patients

Abstract

Purpose Chemotherapy-induced febrile neutropenia (FN) is a life-threatening and chemotherapy dose-limiting adverse event. FN can be prevented with granulocyte-colony stimulating factors (G-CSFs). Guidelines recommend primary G-CSF use for patients receiving either high (> 20%) FN risk (HR) chemotherapy, or intermediate (10–20%) FN risk (IR) chemotherapy if the overall risk with additional patient-related risk factors exceeds 20%. In this study, we applied an EHR text-mining tool for real-world G-CSF treatment evaluation in breast cancer patients. Methods Breast cancer patients receiving IR or HR chemotherapy treatments between January 2015 and February 2021 at LUMC, the Netherlands, were included. We retrospectively collected data from EHR with a text-mining tool and assessed G-CSF use, risk factors, and the FN and neutropenia (grades 3–4) and incidence. Results A total of 190 female patients were included, who received 77 HR and 113 IR treatments. In 88.3% of the HR regimens, G-CSF was administered; 7.3% of these patients developed FN vs. 33.3% without G-CSF. Although most IR regimen patients had ≥ 2 risk factors, only 4% received G-CSF, of which none developed neutropenia. However, without G-CSF, 11.9% developed FN and 31.2% severe neutropenia. Conclusions Our text-mining study shows high G-CSF use among HR regimen patients, and low use among IR regimen patients, although most had ≥ 2 risk factors. Therefore, current practice is not completely in accordance with the guidelines. This shows the need for increased awareness and clarity regarding risk factors. Also, text-mining can effectively be implemented for the evaluation of patient care.

Application of Electronic Health Record Text Mining: Real-World Tolerability, Safety, and Efficacy of Adjuvant Melanoma Treatments

“…Previously, we validated a text-mining tool to extract data from EHR for the evaluation of metastatic renal cell carcinoma treatments (mRCCs) and showed that this method is accurate and seven times faster than manual data extraction [ 18 ]. This tool has already been used in other real-world studies, e.g., to review mRCC treatment patterns and outcomes in two hospitals, to review the use of granulocyte-colony stimulating factor and incidence of febrile neutropenia in breast cancer patients [ 19 , 20 ].…”

TNFα inhibitor treatment trajectories

“…In addition, only transitioning patients with stable disease from originator to biosimilar is not in line with the principle of the biosimilar being similar to the originator. 42,43 Finally, less retransitioning was reported in studies in which patients received adalimumab than in studies of other TNF inhibitors. Adalimumab was the last biosimilar to be introduced in clinical care, which could mean that the introduction of adalimumab biosimilars benefited from knowledge gained from and experience with the introduction of previous biosimilars for clinicians, pharmacists and patients.…”

“…For most patients, the loss of effect or the appearance of adverse events in these studies was not clinically verifiable (objectively) by a physician and could be considered as having been subjective. 40,43 This could be attributed to the 'nocebo effect' (i.e., patients' negative expectations that lead to the experience of adverse events or the perception of a decrease in response). 43,44 However, the nocebo effect is difficult to confirm.…”

“…40,43 This could be attributed to the 'nocebo effect' (i.e., patients' negative expectations that lead to the experience of adverse events or the perception of a decrease in response). 43,44 However, the nocebo effect is difficult to confirm. A previous study reported that 87% of patients had regained effect after retransitioning, 45 suggesting a psychological component to the complaints.…”

“…Advancements in techniques for extracting structured information are already under development but are not yet sufficient for unstructured text. 43 Unstructured text is less suitable for automatic information extraction; thus, it requires advanced methods and machine learning techniques for reliable extraction. 44 Moreover, they should be tailored to the specific terminology and characteristics of IMID patients, for example, to the large variety of descriptions of disease recurrence or adverse events.…”