Predicting Long-Term Care Service Demands for Cancer Patients: A Machine Learning Approach.

Background: Long-term care (LTC) service demands among cancer patients are significantly understudied, leading to gaps in healthcare resource allocation and policymaking.

Objective: This study aimed to predict LTC service demands for cancer patients and identify the crucial factors.

Methods: 3333 cases of cancers were included. We further developed two specialized prediction models: a Unified Prediction Model (UPM) and a Category-Specific Prediction Model (CSPM). The UPM offered generalized forecasts by treating all services as identical, while the CSPM built individual predictive models for each specific service type. Sensitivity analysis was also conducted to find optimal usage cutoff points for determining the usage and non-usage cases.

Results: Service usage differences in lung, liver, brain, and pancreatic cancers were significant. For the UPM, the top 20 performance model cutoff points were adopted, such as through Logistic Regression (LR), Quadratic Discriminant Analysis (QDA), and XGBoost (XGB), achieving an AUROC range of 0.707 to 0.728. The CSPM demonstrated performance with an AUROC ranging from 0.777 to 0.837 for the top five most frequently used services. The most critical predictive factors were the types of cancer, patients' age and female caregivers, and specific health needs.

Conclusion: The results of our study provide valuable information for healthcare decisions, resource allocation optimization, and personalized long-term care usage for cancer patients.