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

Abstract

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.

Estimating the indirect economic burden of cancer in Jordan: a retrospective observational study

“… 41 Investing in research to reduce long-term disability can help lower productivity losses by minimising the long-term effects of cancer and its treatment. 42 Promoting early detection and prevention can lead to higher survival rates and lower long-term disability, as many cancers are more manageable when detected early. 43 Finally, transitioning to value-based reimbursement models can incentivise healthcare providers to focus on long-term outcomes and quality of life, which can ultimately reduce indirect productivity losses.…”

Understanding and alleviating informal caregiver burden through the development and validation of a caregiver strain index-based model in Taiwan

“…It is also essential to continuously evaluate and adjust these policies and support services to ensure their effectiveness. Lastly, employing machine learning or deep learning methods to predict caregivers’ burdens, similar to forecasting LTC service usage, is proposed to enhance policy effectiveness and support precision [ 27 ].…”

Multimodal Deep Learning for Classifying Diabetes: Analyzing Carotid Ultrasound Images from UK and Taiwan Biobanks and Their Cardiovascular Disease Associations

“…In the era of AI for clinical applications, numerous works have been established utilizing Deep Learning (DL) and Machine Learning (ML) techniques, speci cally for various tasks such as classi cation 6 , prediction 7 , detection 8 , segmentation 9 , etc. In the case of DM classi cations, a few studies have applied various medical imaging techniques.…”