Cargando…

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

SIMPLE SUMMARY: Understanding the long-term care needs of cancer patients is crucial for healthcare providers and policymakers, as this area remains understudied. This research aims to fill this knowledge gap by employing machine learning algorithms to predict the kinds of services that these patien...

Descripción completa

Detalles Bibliográficos
Autores principales: Chien, Shuo-Chen, Chang, Yu-Hung, Yen, Chia-Ming, Chen, Ying-Erh, Liu, Chia-Chun, Hsiao, Yu-Ping, Yang, Ping-Yen, Lin, Hong-Ming, Lu, Xing-Hua, Wu, I-Chien, Hsu, Chih-Cheng, Chiou, Hung-Yi, Chung, Ren-Hua
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10526410/
https://www.ncbi.nlm.nih.gov/pubmed/37760567
http://dx.doi.org/10.3390/cancers15184598
Descripción
Sumario:SIMPLE SUMMARY: Understanding the long-term care needs of cancer patients is crucial for healthcare providers and policymakers, as this area remains understudied. This research aims to fill this knowledge gap by employing machine learning algorithms to predict the kinds of services that these patients may require. We have developed two specialized models: one provides a generalized view of potential service needs, and the other makes more specific service-type predictions. Our findings identify not only the types of cancer that significantly differ in their care service usage but also key demographic and health-related factors that influence these needs. This research offers valuable insights that could guide the allocation of healthcare resources and customized care interventions for cancer patients. 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.