Cognitive impairment prediction in cancer survivors

Objectives: Cancer-related cognitive impairment (CI) refers to the reduction of cognitive abilities following treatment that affects the quality of survivors’ lives. Self-report instruments such as Cognitive Failure Questionnaire (CFQ) provide a quick and economical method for early detection. The objective of this study is to develop machine learning models by utilizing demographic predictors to categorize survivors into low, medium, and high CI groups.Methods: Data from 570 cancer survivors were analyzed using CFQ scores as the outcome measure. Demographic variables were employed as inputs to four supervised algorithms: Logistic Regression (LR), Support Vector Machine (SVM), Artificial Neural Network (ANN), and k-Nearest Neighbors (KNN). Model performance was assessed using accuracy, sensitivity, specificity, and area under the ROC curve (AUC).