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 ca...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Cancers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-6694/15/18/4598 |
| _version_ | 1797580849963597824 |
|---|---|
| author | Shuo-Chen Chien Yu-Hung Chang Chia-Ming Yen Ying-Erh Chen Chia-Chun Liu Yu-Ping Hsiao Ping-Yen Yang Hong-Ming Lin Xing-Hua Lu I-Chien Wu Chih-Cheng Hsu Hung-Yi Chiou Ren-Hua Chung |
| author_facet | Shuo-Chen Chien Yu-Hung Chang Chia-Ming Yen Ying-Erh Chen Chia-Chun Liu Yu-Ping Hsiao Ping-Yen Yang Hong-Ming Lin Xing-Hua Lu I-Chien Wu Chih-Cheng Hsu Hung-Yi Chiou Ren-Hua Chung |
| author_sort | Shuo-Chen Chien |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T22:56:51Z |
| format | Article |
| id | doaj.art-02e8a9303b5946abbaf95893cdd2537e |
| institution | Directory Open Access Journal |
| issn | 2072-6694 |
| language | English |
| last_indexed | 2024-03-10T22:56:51Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Cancers |
| spelling | doaj.art-02e8a9303b5946abbaf95893cdd2537e2023-11-19T09:56:02ZengMDPI AGCancers2072-66942023-09-011518459810.3390/cancers15184598Predicting Long-Term Care Service Demands for Cancer Patients: A Machine Learning ApproachShuo-Chen Chien0Yu-Hung Chang1Chia-Ming Yen2Ying-Erh Chen3Chia-Chun Liu4Yu-Ping Hsiao5Ping-Yen Yang6Hong-Ming Lin7Xing-Hua Lu8I-Chien Wu9Chih-Cheng Hsu10Hung-Yi Chiou11Ren-Hua Chung12Institute of Population Health Sciences, National Health Research Institutes, Miaoli County 350, TaiwanInstitute of Population Health Sciences, National Health Research Institutes, Miaoli County 350, TaiwanNational Center for Geriatrics and Welfare Research, National Health Research Institutes, Yunlin County 632, TaiwanDepartment of Risk Management and Insurance, Tamkang University, New Taipei City 251, TaiwanInstitute of Population Health Sciences, National Health Research Institutes, Miaoli County 350, TaiwanInstitute of Population Health Sciences, National Health Research Institutes, Miaoli County 350, TaiwanInstitute of Population Health Sciences, National Health Research Institutes, Miaoli County 350, TaiwanInstitute of Population Health Sciences, National Health Research Institutes, Miaoli County 350, TaiwanInstitute of Population Health Sciences, National Health Research Institutes, Miaoli County 350, TaiwanInstitute of Population Health Sciences, National Health Research Institutes, Miaoli County 350, TaiwanInstitute of Population Health Sciences, National Health Research Institutes, Miaoli County 350, TaiwanInstitute of Population Health Sciences, National Health Research Institutes, Miaoli County 350, TaiwanInstitute of Population Health Sciences, National Health Research Institutes, Miaoli County 350, TaiwanBackground: 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.https://www.mdpi.com/2072-6694/15/18/4598machine learninglong-term care servicesdemands predictioncancer patientshealthcare advancementssensitivity analysis |
| spellingShingle | Shuo-Chen Chien Yu-Hung Chang Chia-Ming Yen Ying-Erh Chen Chia-Chun Liu Yu-Ping Hsiao Ping-Yen Yang Hong-Ming Lin Xing-Hua Lu I-Chien Wu Chih-Cheng Hsu Hung-Yi Chiou Ren-Hua Chung Predicting Long-Term Care Service Demands for Cancer Patients: A Machine Learning Approach Cancers machine learning long-term care services demands prediction cancer patients healthcare advancements sensitivity analysis |
| title | Predicting Long-Term Care Service Demands for Cancer Patients: A Machine Learning Approach |
| title_full | Predicting Long-Term Care Service Demands for Cancer Patients: A Machine Learning Approach |
| title_fullStr | Predicting Long-Term Care Service Demands for Cancer Patients: A Machine Learning Approach |
| title_full_unstemmed | Predicting Long-Term Care Service Demands for Cancer Patients: A Machine Learning Approach |
| title_short | Predicting Long-Term Care Service Demands for Cancer Patients: A Machine Learning Approach |
| title_sort | predicting long term care service demands for cancer patients a machine learning approach |
| topic | machine learning long-term care services demands prediction cancer patients healthcare advancements sensitivity analysis |
| url | https://www.mdpi.com/2072-6694/15/18/4598 |
| work_keys_str_mv | AT shuochenchien predictinglongtermcareservicedemandsforcancerpatientsamachinelearningapproach AT yuhungchang predictinglongtermcareservicedemandsforcancerpatientsamachinelearningapproach AT chiamingyen predictinglongtermcareservicedemandsforcancerpatientsamachinelearningapproach AT yingerhchen predictinglongtermcareservicedemandsforcancerpatientsamachinelearningapproach AT chiachunliu predictinglongtermcareservicedemandsforcancerpatientsamachinelearningapproach AT yupinghsiao predictinglongtermcareservicedemandsforcancerpatientsamachinelearningapproach AT pingyenyang predictinglongtermcareservicedemandsforcancerpatientsamachinelearningapproach AT hongminglin predictinglongtermcareservicedemandsforcancerpatientsamachinelearningapproach AT xinghualu predictinglongtermcareservicedemandsforcancerpatientsamachinelearningapproach AT ichienwu predictinglongtermcareservicedemandsforcancerpatientsamachinelearningapproach AT chihchenghsu predictinglongtermcareservicedemandsforcancerpatientsamachinelearningapproach AT hungyichiou predictinglongtermcareservicedemandsforcancerpatientsamachinelearningapproach AT renhuachung predictinglongtermcareservicedemandsforcancerpatientsamachinelearningapproach |