Development and Validation of a Predictive Model for Severe Hematological Toxicity in Adult Colorectal Cancer Patients Taking Chemotherapy at Tikur Anbessa Specialized Hospital
No Thumbnail Available
Date
2021-10
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Addis Ababa University
Abstract
Background: Hematological toxicities are common in colorectal cancer patients taking
chemotherapy. The development of a valid predictive model would go a long way in
preventing for such toxicities.
Objectives: To develop and validate a prediction model for severe hematological
toxicities in adult colorectal cancer patients taking chemotherapy at Tikur Anbessa
Specialized Hospital
Methods: A retrospective cohort study was conducted using medical records of adult
colorectal cancer patients who received chemotherapy from 2017 to 2021 at Tikur
Anbessa Specialized Hospital. The model was developed using uni-variable and
multivariable logistic regression analyses, and it was validated using bootstrapping. The
model was developed for severe neutropenia only because of limited number of outcomes
for anemia and thrombocytopenia. Discrimination and calibration were used to determine
the model’s prediction accuracy. All statistical tests were two-sided and P-value < 0.05
was considered statistically significant.
Results: A total of 224 colorectal cancer patients were considered for analysis. About
114 (50.9%), 25 (11.2%) and four (1.8%) patients developed severe neutropenia, anemia
and thrombocytopenia respectively. Age, polychemotherapy, type of therapy, and longer
duration of chemotherapy were predictors of severe neutropenia. The model had
sensitivity of (71.05% versus 73.24%) and specificity of (71.82% versus 68.49%) in the
derivation and validation cohorts respectively. The area under receiver operating curve
was 0.7995 for the derivation and 0.7741 for the validation cohorts.
Conclusions: Neutropenia was the most common hematological toxicity. The application
of the developed model could help to identify high-risk patients for severe neutropenia
and to institute preventive strategies before neutropenia develops.
Description
Keywords
Chemotherapy, Colorectal Cancer, Hematological toxicity, Predictive model, Tikur Anbessa Specialized Hospital